@Preamble{
"\hyphenation{ }"
}
@String{ack-nhfb = "Nelson H. F. Beebe,
University of Utah,
Department of Mathematics, 110 LCB,
155 S 1400 E RM 233,
Salt Lake City, UT 84112-0090, USA,
Tel: +1 801 581 5254,
FAX: +1 801 581 4148,
e-mail: \path|beebe@math.utah.edu|,
\path|beebe@acm.org|,
\path|beebe@computer.org| (Internet),
URL: \path|https://www.math.utah.edu/~beebe/|"}
@String{j-BIT = "BIT"}
@String{j-CACM = "Communications of the ACM"}
@String{j-TODS = "ACM Transactions on Database Systems"}
@String{pub-ACM = "ACM Press"}
@String{pub-ACM:adr = "New York, NY 10036, USA"}
@String{pub-IEEE = "IEEE Computer Society Press"}
@String{pub-IEEE:adr = "1109 Spring Street, Suite 300, Silver
Spring, MD 20910, USA"}
@String{pub-MORGAN-KAUFMANN = "Morgan Kaufmann Publishers"}
@String{pub-MORGAN-KAUFMANN:adr = "Los Altos, CA 94022, USA"}
@Article{Yao:1977:ABA,
author = "S. B. Yao",
title = "Approximating Block Accesses in Database
Organization",
journal = j-CACM,
volume = "20",
number = "4",
pages = "260--261",
month = apr,
year = "1977",
CODEN = "CACMA2",
ISSN = "0001-0782 (print), 1557-7317 (electronic)",
bibdate = "Tue Sep 20 23:14:33 1994",
bibsource = "ftp://ftp.ira.uka.de/pub/bibliography/Database/Graefe.bib;
ftp://ftp.ira.uka.de/pub/bibliography/Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite{Yao:1977:ABM}.",
ajournal = "Commun. ACM",
fjournal = "Communications of the ACM",
journal-URL = "https://dl.acm.org/loi/tods",
keywords = "selectivity estimation I/O cost query optimization
CACM",
}
@Article{Hsiao:1976:ATD,
author = "David K. Hsiao",
title = "{ACM Transactions on Database Systems}: aim and
scope",
journal = j-TODS,
volume = "1",
number = "1",
pages = "1--2",
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p1-hsiao/p1-hsiao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p1-hsiao/",
abstract = "Record-keeping and decision-making in industry and
government are increasingly based on data stored in
computer processable databases. Thus the need for
improved computer technology for building, managing,
and using these databases is clearly evident. This need
is particularly acute in a complex society where the
interrelationships among various aspects of the society
must be identified and represented. The data which must
be used to represent these relationships are growing
more complex in nature and becoming greater in size.
Furthermore, the increasing on-line use of computer
systems and the proliferation and mass introduction of
multilevel secondary storage suggests that future
computer systems will be primarily oriented toward
database management. The large size of future on-line
databases will require the computer system to manage
local as well as physical resources. The management of
logical resources is concerned with the organization,
access, update, storage, and sharing of the data and
programs in the database. In addition, the sharing of
data means that the database system must be capable of
providing privacy protection and of controlling access
to the users' data. The term {\em data\/} is
interpreted broadly to include textual, numeric, and
signal data as well as data found in structured
records.\par
The aim of {\em ACM Transactions on Database Systems\/}
(TODS) is to serve as a focal point for an integrated
dissemination of database research and development on
storage and processor hardware, system software,
applications, information science, information
analysis, and file management. These areas are
particularly relevant to the following ACM Special
Interest Groups: Business Data Processing (SIGBDP),
Information Retrieval (SIGIR), and Management of Data
(SIGMOD). TODS will also embrace parts of the
Management/Database Systems and the Information
Retrieval and Language Processing sections of {\em
Communications of the ACM}.\par
High quality papers on all aspects of computer database
systems will be published in TODS. The scope of TODS
emphasizes data structures; storage organization; data
collection and dissemination; search and retrieval
strategies; update strategies; access control
techniques; data integrity; security and protection;
design and implementation of database software;
database related languages including data description
languages, query languages, and procedural and
nonprocedural data manipulation languages; language
processing; analysis and classification of data;
database utilities; data translation techniques;
distributed database problems and techniques; database
recovery and restart; database restructuring; adaptive
data structures; concurrent access techniques; database
computer hardware architecture; performance and
evaluation; intelligent front ends; and related
subjects such as privacy and economic issues.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "Information Systems --- Database Management ---
Systems (H.2.4)",
}
@Article{Chen:1976:ERM,
author = "Peter Pin-Shan S. Chen",
title = "The Entity-Relationship Model: Toward a Unified View
of Data",
journal = j-TODS,
volume = "1",
number = "1",
pages = "9--36",
month = mar,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compiler/prog.lang.theory.bib; Database/Graefe.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib; Object/Nierstrasz.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p9-chen/p9-chen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p9-chen/",
abstract = "A data model, called the entity-relationship model, is
proposed. This model incorporates some of the important
semantic information about the real world. A special
diagrammatic technique is introduced as a tool for
database design. An example of database design and
description using the model and the diagrammatic
technique is given. Some implications for data
integrity, information retrieval, and data manipulation
are discussed.\par
The entity-relationship model can be used as a basis
for unification of different views of data: the network
model, the relational model, and the entity set model.
Semantic ambiguities in these models are analyzed.
Possible ways to derive their views of data from the
entity-relationship model are presented.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data Base Task Group; data definition and
manipulation; data integrity and consistency; data
models; database design; dblit; entity set model;
entity-relationship; entity-relationship model; logical
view of data; network model; relational model;
semantics of data; TODS",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Bayer:1976:EST,
author = "R. Bayer and J. K. Metzger",
title = "On the Encipherment of Search Trees and Random Access
Files",
journal = j-TODS,
volume = "1",
number = "1",
pages = "37--52",
month = mar,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite[p.~508--510]{Kerr:1975:PIC}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p37-bayer/p37-bayer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p37-bayer/",
abstract = "The securing of information in indexed, random access
files by means of privacy transformations must be
considered as a problem distinct from that for
sequential files. Not only must processing overhead due
to encrypting be considered, but also threats to
encipherment arising from updating and the file
structure itself must be countered. A general
encipherment scheme is proposed for files maintained in
a paged structure in secondary storage. This is applied
to the encipherment of indexes organized as $B$-trees;
a $B$-tree is a particular type of multiway search
tree. Threats to the encipherment of $B$-trees,
especially relating to updating, are examined, and
countermeasures are proposed for each. In addition, the
effect of encipherment on file access and update, on
paging mechanisms, and on files related to the
enciphered index are discussed. Many of the concepts
presented may be readily transferred to other forms of
multiway index trees and to binary search trees.",
acknowledgement = ack-nhfb,
annote = "Trees versus hashing as his 1974 IFIP paper?",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "",
subject = "Software --- Operating Systems --- Security and
Protection (D.4.6): {\bf Access controls}; Software ---
Operating Systems --- Security and Protection (D.4.6):
{\bf Cryptographic controls}",
}
@Article{Lin:1976:DRA,
author = "Chyuan Shiun Lin and Diane C. P. Smith and John Miles
Smith",
title = "The design of a rotating associative memory for
relational database applications",
journal = j-TODS,
volume = "1",
number = "1",
pages = "53--65",
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p53-lin/p53-lin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p53-lin/",
abstract = "The design and motivation for a rotating associative
relational store (RARES) is described. RARES is
designed to enhance the performance of an optimizing
relational query interface by supporting important high
level optimization techniques. In particular, it can
perform tuple selection operations at the storage
device and also can provide a mechanism for efficient
sorting. Like other designs for rotating associative
stores, RARES contains search logic which is attached
to the heads of a rotating head-per-track storage
device. RARES is distinct from other designs in that it
utilizes a novel ``orthogonal'' storage layout. This
layout allows a high output rate of selected tuples
even when a sort order in the stored relation must be
preserved. As in certain other designs, RARES can
usually output a tuple as soon as it is found to
satisfy the selection criteria. However, relative to
these designs, the orthogonal layout allows an order of
magnitude reduction in the capacity of storage local to
the search logic.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative memory; content addressability; data
organization; head-per-track disks; memory systems;
relational database; rotating devices; search logic;
sorting technique",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Mahmoud:1976:OAR,
author = "Samy Mahmoud and J. S. Riordon",
title = "Optimal Allocation of Resources in Distributed
Information Networks",
journal = j-TODS,
volume = "1",
number = "1",
pages = "66--78",
month = mar,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p66-mahmoud/p66-mahmoud.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p66-mahmoud/",
abstract = "The problems of file allocation and capacity
assignment in a fixed topology distributed computer
network are examined. These two aspects of the design
are tightly coupled by means of an average message
delay constraint. The objective is to allocate copies
of information files to network nodes and capacities to
network links so that a minimum cost is achieved
subject to network delay and file availability
constraints. A model for solving the problem is
formulated and the resulting optimization problem is
shown to fall into a class of nonlinear integer
programming problems. Deterministic techniques for
solving this class of problems are computationally
cumbersome, even for small size problems. A new
heuristic algorithm is developed, which is based on a
decomposition technique that greatly reduces the
computational complexity of the problem. Numerical
results for a variety of network configurations
indicate that the heuristic algorithm, while not
theoretically convergent, yields practicable low cost
solutions with substantial savings in computer
processing time and storage requirements. Moreover, it
is shown that this algorithm is capable of solving
realistic network problems whose solutions using
deterministic techniques are computationally
intractable.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data files; distributed computed; information
networks; link capacities; resource sharing",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2)",
}
@Article{Stemple:1976:DMF,
author = "David W. Stemple",
title = "A Database Management Facility for Automatic
Generation of Database Managers",
journal = j-TODS,
volume = "1",
number = "1",
pages = "79--94",
month = mar,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite[p.~252]{Kerr:1975:PIC}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-1/p79-stemple/p79-stemple.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-1/p79-stemple/",
abstract = "A facility is described for the implementation of
database management systems having high degrees of {\em
horizontal\/} data independence, i.e. independence from
chosen logical properties of a database as opposed to
{\em vertical\/} independence from storage structures.
The facility consists of a high level language for the
specification of virtual database managers, a compiler
from this language to a pseudomachine language, and an
interpreter for the pseudomachine language.\par
It is shown how this facility can be used to produce
efficient database management systems with any degree
of both horizontal and vertical data independence. Two
key features of this tool are the compilation of
tailored database managers from individual schemas and
multiple levels of optional binding.",
acknowledgement = ack-nhfb,
annote = "Describes SLUSH and SLIM, a proposed compiler and
interpreter to operate on network schemas with
adjustable binding times.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data independence; database management systems",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management (H.2); Software --- Operating Systems ---
Systems Programs and Utilities (D.4.9): {\bf make}",
}
@Article{Astrahan:1976:SRR,
author = "M. M. Astrahan and M. W. Blasgen and D. D. Chamberlin
and K. P. Eswaran and J. N. Gray and P. P. Griffiths
and W. F. King and R. A. Lorie and P. R. McJones and J.
W. Mehl and G. R. Putzolu and I. L. Traiger and B. W.
Wade and V. Watson",
title = "{System R}: a Relational Approach to Database
Management",
journal = j-TODS,
volume = "1",
number = "2",
pages = "97--137",
month = jun,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Object/Nierstrasz.bib",
note = "Also published in/as: IBM, San Jose, Research Report.
No. RJ-1738, Feb. 1976. Reprinted in
\cite{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-2/p97-astrahan/p97-astrahan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-2/p97-astrahan/",
abstract = "System R is a database management system which
provides a high level relational data interface. The
systems provides a high level of data independence by
isolating the end user as much as possible from
underlying storage structures. The system permits
definition of a variety of relational views on common
underlying data. Data control features are provided,
including authorization, integrity assertions,
triggered transactions, a logging and recovery
subsystem, and facilities for maintaining data
consistency in a shared-update environment.\par
This paper contains a description of the overall
architecture and design of the system. At the present
time the system is being implemented and the design
evaluated. We emphasize that System R is a vehicle for
research in database architecture, and is not planned
as a product.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "authorization; data structures; database; dblit; index
structures; locking; nonprocedural language; recovery;
relational model; TODS relation database IBM San Jose",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf System R}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Relational databases}; Information Systems --- Database
Management (H.2)",
}
@Article{Navathe:1976:RLD,
author = "Shamkant B. Navathe and James P. Fry",
title = "Restructuring for Large Data Bases: Three Levels of
Abstraction",
journal = j-TODS,
volume = "1",
number = "2",
pages = "138--158",
month = mar,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite[p.~174]{Kerr:1975:PIC}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-2/p138-navathe/p138-navathe.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-2/p138-navathe/",
abstract = "The development of a powerful restructuring function
involves two important components--the unambiguous
specification of the restructuring operations and the
realization of these operations in a software system.
This paper is directed to the first component in the
belief that a precise specification will provide a firm
foundation for the development of restructuring
algorithms and, subsequently, their implementation. The
paper completely defines the semantics of the
restructuring of tree structured databases.\par
The delineation of the restructuring function is
accomplished by formulating three different levels of
abstraction, with each level of abstraction
representing successively more detailed semantics of
the function.\par
At the first level of abstraction, the schema
modification, three types are identified--naming,
combining, and relating; these three types are further
divided into eight schema operations. The second level
of abstraction, the instance operations, constitutes
the transformations on the data instances; they are
divided into group operations such as replication,
factoring, union, etc., and group relation operations
such as collapsing, refinement, fusion, etc. The final
level, the item value operations, includes the actual
item operations, such as copy value, delete value, or
create a null value.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data definition; data translation; database; database
management systems; logical restructuring",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5): {\bf Data
translation**}",
}
@Article{Yao:1976:DDR,
author = "S. B. Yao and K. S. Das and T. J. Teorey",
title = "A Dynamic Database Reorganization Algorithm",
journal = j-TODS,
volume = "1",
number = "2",
pages = "159--174",
month = jun,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Purdue Un., TR-168, Nov. 1975.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-2/p159-yao/p159-yao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-2/p159-yao/",
abstract = "Reorganization is necessary in some databases for
overcoming the performance deterioration caused by
updates. The paper presents a dynamic reorganization
algorithm which makes the reorganization decision by
measuring the database search costs. Previously, the
reorganization intervals could only be determined for
linear deterioration and known database lifetime. It is
shown that the dynamic reorganization algorithm is near
optimum for constant reorganization cost and is
superior for increasing reorganization cost. In
addition, it can be applied to cases of unknown
database lifetime and nonlinear performance
deterioration. The simplicity, generality, and
efficiency appear to make this good heuristic for
database reorganization.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database; file organization; information retrieval;
reorganization",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Retrieval models}",
}
@Article{Burkhard:1976:HTA,
author = "Walter A. Burkhard",
title = "Hashing and Trie Algorithms for Partial-Match
Retrieval",
journal = j-TODS,
volume = "1",
number = "2",
pages = "175--187",
month = jun,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; Graphics/siggraph/76.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: UCSD, Appl. Physics and Inf. Sc,
CS TR.2, Jun. 1975.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-2/p175-burkhard/p175-burkhard.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-2/p175-burkhard/",
abstract = "File designs suitable for retrieval from a file of
$k$-letter words when queries may be only partially
specified are examined. A new class of partial match
file designs (called PMF designs) based upon hash
coding and trie search algorithms which provide good
worst-case performance is introduced. Upper bounds on
the worst-case performance of these designs are given
along with examples of files achieving the bound. Other
instances of PMF designs are known to have better
worst-case performances. The implementation of the file
designs with associated retrieval algorithms is
considered. The amount of storage required is
essentially that required of the records themselves.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; analysis; associative retrieval; hash
coding; partial match; retrieval; searching; trie
search",
oldlabel = "geom-96",
subject = "Mathematics of Computing --- Mathematical Software
(G.4): {\bf Algorithm design and analysis}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf
Retrieval models}",
}
@Article{Stonebraker:1976:DII,
author = "Michael Stonebraker and Eugene Wong and Peter Kreps
and Gerald Held",
title = "The Design and Implementation of {INGRES}",
journal = j-TODS,
volume = "1",
number = "3",
pages = "189--222",
month = sep,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}. Also
published in/as: UCB, Elec. Res. Lab, Memo No.
ERL-M577, Jan. 1976.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-3/p189-stonebraker/p189-stonebraker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-3/p189-stonebraker/",
abstract = "The currently operational (March 1976) version of the
INGRES database management system is described. This
multiuser system gives a relational view of data,
supports two high level nonprocedural data
sublanguages, and runs as a collection of user
processes on top of the UNIX operating system for
Digital Equipment Corporation PDP 11/40, 11/45, and
11/70 computers. Emphasis is on the design decisions
and tradeoffs related to (1) structuring the system
into processes, (2) embedding one command language in a
general purpose programming language, (3) the
algorithms implemented to process interactions, (4) the
access methods implemented, (5) the concurrency and
recovery control currently provided, and (6) the data
structures used for system catalogs and the role of the
database administrator.\par
Also discussed are (1) support for integrity
constraints (which is only partly operational), (2) the
not yet supported features concerning views and
protection, and (3) future plans concerning the
system.",
acknowledgement = ack-nhfb,
annote = "Describes implementation of INGRES, a non-distributed
relational database system. This paper is useful for
understanding the distributed INGRES paper.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; data integrity; data organization; data
sublanguage; database optimization; nonprocedural
language; protection; QUEL EQUEL query modification
process structure Halloween problem TODS; query
decomposition; query language; relational database",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3); Information Systems --- Database
Management --- General (H.2.0): {\bf Security,
integrity, and protection**}",
}
@Article{Wong:1976:DSQ,
author = "Eugene Wong and Karel Youssefi",
title = "Decomposition --- {A} Strategy for Query Processing",
journal = j-TODS,
volume = "1",
number = "3",
pages = "223--241",
month = sep,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: UCB, Elec. Res. Lab, Memo No.
ERL-574, Jan. 1976",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-3/p223-wong/p223-wong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-3/p223-wong/",
abstract = "Strategy for processing multivariable queries in the
database management system INGRES is considered. The
general procedure is to decompose the query into a
sequence of one-variable queries by alternating between
(a) reduction: breaking off components of the query
which are joined to it by a single variable, and (b)
tuple substitution: substituting for one of the
variables a tuple at a time. Algorithms for reduction
and for choosing the variable to be substituted are
given. In most cases the latter decision depends on
estimation of costs; heuristic procedures for making
such estimates are outlined.",
acknowledgement = ack-nhfb,
annote = "INGRES query decomposition by reduction to single
variable queries, and tuple substitution --- choosing a
variable and for it from all tuples, generating a
family of queries in one fewer variable.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "connected query; decomposition; detachment; Ingres
TODS; irreducible query; joining (overlapping)
variable; query processing; relational database; tuple
substitution; variable selection",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}",
}
@Article{Griffiths:1976:AMR,
author = "Patricia P. Griffiths and Bradford W. Wade",
title = "An Authorization Mechanism for a Relational Database
System",
journal = j-TODS,
volume = "1",
number = "3",
pages = "242--255",
month = sep,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-3/p242-griffiths/p242-griffiths.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-3/p242-griffiths/",
abstract = "A multiuser database system must selectively permit
users to share data, while retaining the ability to
restrict data access. There must be a mechanism to
provide protection and security, permitting information
to be accessed only by properly authorized users.
Further, when tables or restricted views of tables are
created and destroyed dynamically, the granting,
authentication, and revocation of authorization to use
them must also be dynamic. Each of these issues and
their solutions in the context of the relational
database management system System R are discussed.
\par
When a database user creates a table, he is fully and
solely authorized to perform upon it actions such as
read, insert, update, and delete. He may explicitly
grant to any other user any or all of his privileges on
the table. In addition he may specify that that user is
authorized to further grant these privileges to still
other users. The result is a directed graph of granted
privileges originating from the table creator.\par
At some later time a user A may revoke some or all of
the privileges which he previously granted to another
user B. This action usually revokes the entire subgraph
of the grants originating from A's grant to B. It may
be, however, that B will still possess the revoked
privileges by means of a grant from another user C, and
therefore some or all of B's grants should not be
revoked. This problem is discussed in detail, and an
algorithm for detecting exactly which of B's grants
should be revoked is presented.",
acknowledgement = ack-nhfb,
annote = "Defines a dynamic authorization mechanism. A database
user can grant or revoke privileges (such as to read,
insert, or delete) on a file that he has created.
Furthermore, he can authorize others to grant these
same privileges. The database management system keeps
track of a directed graph, emanating from the creator
of granted privileges.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access control; authorization; data dependent
authorization; database systems; privacy; protection in
databases; revocation of authorization; security",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Systems
(H.2.4); Information Systems --- Database Management
--- General (H.2.0): {\bf Security, integrity, and
protection**}",
}
@Article{Severance:1976:DFT,
author = "Dennis G. Severance and Guy M. Lohman",
title = "Differential Files: Their Application to the
Maintenance of Large Databases",
journal = j-TODS,
volume = "1",
number = "3",
pages = "256--267",
month = sep,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-3/p256-severance/p256-severance.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-3/p256-severance/",
abstract = "The representation of a collection of data in terms of
its differences from some preestablished point of
reference is a basic storage compaction technique which
finds wide applicability. This paper describes a
differential database representation which is shown to
be an efficient method for storing large and volatile
databases. The technique confines database
modifications to a relatively small area of physical
storage and as a result offers two significant
operational advantages. First, because the ``reference
point'' for the database is inherently static, it can
be simply and efficiently stored. Second, since all
modifications to the database are physically localized,
the process of backup and the process of recovery are
relatively fast and inexpensive.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backup and recovery; data sharing; database
maintenance; differential files",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Shneiderman:1976:BSS,
author = "Ben Shneiderman and Victor Goodman",
title = "Batched Searching of Sequential and Tree Structured
Files",
journal = j-TODS,
volume = "1",
number = "3",
pages = "268--275",
month = sep,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See comments in \cite{Piwowarski:1985:CBS}. Also
published in/as: Indiana Un., CSD Tech. Ref. 0132.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-3/p268-shneiderman/p268-shneiderman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-3/p268-shneiderman/",
abstract = "The technique of batching searches has been ignored in
the context of disk based online data retrieval
systems. This paper suggests that batching be
reconsidered for such systems since the potential
reduction in processor demand may actually reduce
response time. An analysis with sample numerical
results and algorithms is presented.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval (H.3)",
}
@Article{Bernstein:1976:STN,
author = "Philip A. Bernstein",
title = "Synthesizing Third Normal Form Relations from
Functional Dependencies",
journal = j-TODS,
volume = "1",
number = "4",
pages = "277--298",
month = dec,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-4/p277-bernstein/p277-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-4/p277-bernstein/",
abstract = "It has been proposed that the description of a
relational database can be formulated as a set of
functional relationships among database attributes.
These functional relationships can then be used to
synthesize algorithmically a relational scheme. It is
the purpose of this paper to present an effective
procedure for performing such a synthesis. The schema
that results from this procedure is proved to be in
Codd's third normal form and to contain the fewest
possible number of relations. Problems with earlier
attempts to construct such a procedure are also
discussed.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database schema; functional dependency; relational
model; semantics of data; third normal form",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Normal forms}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Schema and subschema}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Data models}",
}
@Article{Liu:1976:APS,
author = "Jane W. S. Liu",
title = "Algorithms for parsing search queries in systems with
inverted file organization",
journal = j-TODS,
volume = "1",
number = "4",
pages = "299--316",
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-4/p299-liu/p299-liu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-4/p299-liu/",
abstract = "In an inverted file system a query is in the form of a
Boolean expression of index terms. In response to a
query the system accesses the inverted lists
corresponding to the index terms, merges them, and
selects from the merged list those records that satisfy
the search logic. Considered in this paper is the
problem of determining a Boolean expression which leads
to the minimum total merge time among all Boolean
expressions that are equivalent to the expression given
in the query. This problem is the same as finding an
optimal merge tree among all trees that realize the
truth function determined by the Boolean expression in
the query. Several algorithms are described which
generate optimal merge trees when the sizes of overlaps
between different lists are small compared with the
length of the lists.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "inverted file systems; merge algorithms; parsing
Boolean queries",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Mathematics of Computing ---
Mathematical Software (G.4): {\bf Algorithm design and
analysis}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Query processing}",
}
@Article{Sherman:1976:PDM,
author = "Stephen W. Sherman and Richard S. Brice",
title = "Performance of a Database Manager in a Virtual Memory
System",
journal = j-TODS,
volume = "1",
number = "4",
pages = "317--343",
month = dec,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-4/p317-sherman/p317-sherman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-4/p317-sherman/",
abstract = "Buffer space is created and managed in database
systems in order to reduce accesses to the I/O devices
for database information. In systems using virtual
memory any increase in the buffer space may be
accompanied by an increase in paging. The effects of
these factors on system performance are quantified
where system performance is a function of page faults
and database accesses to I/O devices. This phenomenon
is examined through the analysis of empirical data
gathered in a multifactor experiment. The factors
considered are memory size, size of buffer space,
memory replacement algorithm, and buffer management
algorithm. The improvement of system performance
through an increase in the size of the buffer space is
demonstrated. It is also shown that for certain values
of the other factors an increase in the size of the
buffer space can cause performance to deteriorate.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer manager; Buffer operating system support TODS;
database management; double paging; page faults; page
replacement algorithm; performance; virtual buffer;
virtual memory",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Database Manager}; Mathematics of
Computing --- Mathematical Software (G.4): {\bf
Algorithm design and analysis}; Computer Systems
Organization --- Performance of Systems (C.4)",
}
@Article{Donovan:1976:DSA,
author = "John J. Donovan",
title = "Database System Approach to Management Decision
Support",
journal = j-TODS,
volume = "1",
number = "4",
pages = "344--369",
month = dec,
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-4/p344-donovan/p344-donovan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-4/p344-donovan/",
abstract = "Traditional intuitive methods of decision-making are
no longer adequate to deal with the complex problems
faced by the modern policymaker. Thus systems must be
developed to provide the information and analysis
necessary for the decisions which must be made. These
systems are called decision support systems. Although
database systems provide a key ingredient to decision
support systems, the problems now facing the
policymaker are different from those problems to which
database systems have been applied in the past. The
problems are usually not known in advance, they are
constantly changing, and answers are needed quickly.
Hence additional technologies, methodologies, and
approaches must expand the traditional areas of
database and operating systems research (as well as
other software and hardware research) in order for them
to become truly effective in supporting policymakers.
\par
This paper describes recent work in this area and
indicates where future work is needed. Specifically the
paper discusses: (1) why there exists a vital need for
decision support systems; (2) examples from work in the
field of energy which make explicit the characteristics
which distinguish these decision support systems from
traditional operational and managerial systems; (3) how
an awareness of decision support systems has evolved,
including a brief review of work done by others and a
statement of the computational needs of decision
support systems which are consistent with contemporary
technology; (4) an approach which has been made to meet
many of these computational needs through the
development and implementation of a computational
facility, the Generalized Management Information System
(GMIS); and (5) the application of this computational
facility to a complex and important energy problem
facing New England in a typical study within the New
England Energy Management Information System (NEEMIS)
Project.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; decision support systems; management
applications; modeling; networking; relational; virtual
machines",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management --- Systems
(H.2.4)",
}
@Article{McGee:1976:UCD,
author = "William C. McGee",
title = "On user criteria for data model evaluation",
journal = j-TODS,
volume = "1",
number = "4",
pages = "370--387",
year = "1976",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1976-1-4/p370-mcgee/p370-mcgee.pdf;
http://www.acm.org/pubs/citations/journals/tods/1976-1-4/p370-mcgee/",
abstract = "The emergence of a database technology in recent years
has focused interest on the subject of data models. A
data model is the class of logical data structures
which a computer system or language makes available to
the user for the purpose of formulating data processing
applications. The diversity of computer systems and
languages has resulted in a corresponding diversity of
data models, and has created a problem for the user in
selecting a data model which is in some sense
appropriate to a given application. An evaluation
procedure is needed which will allow the user to
evaluate alternative models in the context of a
specific set of applications. This paper takes a first
step toward such a procedure by identifying the
attributes of a data model which can be used as
criteria for evaluating the model. Two kinds of
criteria are presented: use criteria, which measure the
usability of the model; and implementation criteria,
which measure the implementability of the model and the
efficiency of the resulting implementation. The use of
the criteria is illustrated by applying them to three
specific models: an $n$-ary relational model, a
hierarchic model, and a network model.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data model; data model evaluation; data model
selection; hierarchic model; network model; relational
model",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}",
}
@Article{Kam:1977:MSD,
author = "John B. Kam and Jeffrey D. Ullman",
title = "A Model of Statistical Databases and Their Security",
journal = j-TODS,
volume = "2",
number = "1",
pages = "1--10",
month = mar,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-1/p1-kam/p1-kam.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-1/p1-kam/",
abstract = "Considered here, for a particular model of databases
in which only information about relatively large sets
of records can be obtained, is the question of whether
one can from statistical information obtain information
about individuals. Under the assumption that the data
in the database is taken from arbitrary integers, it is
shown that essentially nothing can be inferred. It is
also shown that when the values are known to be
imprecise in some fixed range, one can often deduce the
values of individual records.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromisability; data security; linear independence;
statistical database; vector spece",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- General (H.2.0): {\bf Security, integrity, and
protection**}",
}
@Article{Bayer:1977:PBT,
author = "Rudolf Bayer and Karl Unterauer",
title = "Prefix {B}-trees",
journal = j-TODS,
volume = "2",
number = "1",
pages = "11--26",
month = mar,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: IBM Yorktwon, Technical Report
RJ1796, Jun. 1976.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-1/p11-bayer/p11-bayer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-1/p11-bayer/",
abstract = "Two modifications of $B$-trees are described, simple
prefix $B$-trees and prefix $B$-trees. Both store only
parts of keys, namely prefixes, in the index part of a
$B$ *-tree. In simple prefix $B$-trees those prefixes
are selected carefully to minimize their length. In
prefix $B$-trees the prefixes need not be fully stored,
but are reconstructed as the tree is searched. Prefix
$B$-trees are designed to combine some of the
advantages of $B$-trees, digital search trees, and key
compression techniques while reducing the processing
overhead of compression techniques.",
acknowledgement = ack-nhfb,
annote = "Index Btree structures can easily be compressed.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "truncation compression TODS",
subject = "Data --- Data Structures (E.1): {\bf Trees}",
}
@Article{Schkolnick:1977:CAH,
author = "Mario Schkolnick",
title = "A Clustering Algorithm for Hierarchical Structures",
journal = j-TODS,
volume = "2",
number = "1",
pages = "27--44",
month = may,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 09:36:45 1996",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
annote = "Optimal file partitioning, applied to IMS.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yao:1977:ABM,
author = "S. B. Yao",
title = "An Attribute Based Model for Database Access Cost
Analysis",
journal = j-TODS,
volume = "2",
number = "1",
pages = "45--67",
month = mar,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite{Yao:1977:ABA}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-1/p45-yao/p45-yao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-1/p45-yao/",
abstract = "A generalized model for physical database
organizations is presented. Existing database
organizations are shown to fit easily into the model as
special cases. Generalized access algorithms and cost
equations associated with the model are developed and
analyzed. The model provides a general design framework
in which the distinguishing properties of database
organizations are made explicit and their performances
can be compared.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "B-tree; database model; database organization;
database performance; estimation approximation TODS;
evaluation; index organization; index sequential;
inverted file; multilist",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1); Information Systems ---
Information Storage and Retrieval --- Content Analysis
and Indexing (H.3.1); Data --- Data Structures (E.1):
{\bf Trees}",
}
@Article{Anderson:1977:MCS,
author = "Henry D. Anderson and P. Bruce Berra",
title = "Minimum Cost Selection of Secondary Indexes for
Formatted Files",
journal = j-TODS,
volume = "2",
number = "1",
pages = "68--90",
month = mar,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-1/p68-anderson/p68-anderson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-1/p68-anderson/",
abstract = "Secondary indexes are often used in database
management systems for secondary key retrieval.
Although their use can improve retrieval time
significantly, the cost of index maintenance and
storage increases the overhead of the file processing
application. The optimal set of indexed secondary keys
for a particular application depends on a number of
application dependent factors. In this paper a cost
function is developed for the evaluation of candidate
indexing choices and applied to the optimization of
index selection. Factors accounted for include file
size, the relative rates of retrieval and maintenance
and the distribution of retrieval and maintenance over
the candidate keys, index structure, and system
charging rates. Among the results demonstrated are the
increased effectiveness of secondary indexes for large
files, the effect of the relative rates of retrieval
and maintenance, the greater cost of allowing for
arbitrarily formulated queries, and the impact on cost
of the use of different index structures.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access methods; access path; Boolean query; cost
function; data management; database; file design; file
organization; inverted file; inverted index;
maintenance; optimization; retrieval; secondary index;
secondary key; secondary key access",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Indexing methods}; Information Systems ---
Information Storage and Retrieval --- Information
Storage (H.3.2): {\bf File organization}; Information
Systems --- Database Management --- Physical Design
(H.2.2): {\bf Access methods}; Information Systems ---
Database Management (H.2)",
}
@Article{Lorie:1977:PIL,
author = "Raymond A. Lorie",
title = "Physical Integrity in a Large Segmented Database",
journal = j-TODS,
volume = "2",
number = "1",
pages = "91--104",
month = mar,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-1/p91-lorie/p91-lorie.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-1/p91-lorie/",
abstract = "A database system can generally be divided into three
major components. One component supports the logical
database as seen by the user. Another component maps
the information into physical records. The third
component, called the storage component, is responsible
for mapping these records onto auxiliary storage
(generally disks) and controlling their transfer to and
from main storage.\par
This paper is primarily concerned with the
implementation of a storage component. It considers a
simple and classical interface to the storage
component: Seen at this level the database is a
collection of segments. Each segment is a linear
address space.\par
A recovery scheme is first proposed for system failure
(hardware or software error which causes the contents
of main storage to be lost). It is based on maintaining
a dual mapping between pages and their location on
disk. One mapping represents the current state of a
segment being modified; the other represents a previous
backup state. At any time the backup state can be
replaced by the current state without any data merging.
Procedures for segment modification, save, and restore
are analyzed. Another section proposes a facility for
protection against damage to the auxiliary storage
itself. It is shown how such protection can be obtained
by copying on a tape (checkpoint) only those pages that
have been modified since the last checkpoint.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "checkpoint-restart; database; recovery; storage
management",
subject = "Information Systems --- Database Management ---
General (H.2.0): {\bf Security, integrity, and
protection**}; Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2);
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart}",
}
@Article{Smith:1977:DAA,
author = "John Miles Smith and Diane C. P. Smith",
title = "Database abstractions: Aggregation and
Generalization",
journal = j-TODS,
volume = "2",
number = "2",
pages = "105--133",
month = jun,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Object/Nierstrasz.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-2/p105-smith/p105-smith.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-2/p105-smith/",
abstract = "Two kinds of abstraction that are fundamentally
important in database design and usage are defined.
Aggregation is an abstraction which turns a
relationship between objects into an aggregate object.
Generalization is an abstraction which turns a class of
objects into a generic object. It is suggested that all
objects (individual, aggregate, generic) should be
given uniform treatment in models of the real world. A
new data type, called generic, is developed as a
primitive for defining such models. Models defined with
this primitive are structured as a set of aggregation
hierarchies intersecting with a set of generalization
hierarchies. Abstract objects occur at the points of
intersection. This high level structure provides a
discipline for the organization of relational
databases. In particular this discipline allows: (i) an
important class of views to be integrated and
maintained; (ii) stability of data and programs under
certain evolutionary changes; (iii) easier
understanding of complex models and more natural {\em
query formulation;\/} (iv) {\em a more systematic
approach to database design;\/} (v) {\em more
optimization\/} to be performed at lower implementation
levels. The generic type is formalized by a set of
invariant properties. These properties should be
satisfied by all relations in a database if
abstractions are to be preserved. A triggering
mechanism for automatically maintaining these
invariants during update operations is proposed. A
simple mapping of aggregation/generalization
hierarchies onto owner-coupled set structures is
given.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregation; data abstraction; data model; data type;
database design; dblit data abstraction;
generalization; integrity constraints; knowledge
representation; relational database",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Relational databases}; Software --- Software
Engineering --- Software Architectures (D.2.11): {\bf
Data abstraction}",
}
@Article{Shu:1977:EDE,
author = "N. C. Shu and B. C. Housel and R. W. Taylor and S. P.
Ghosh and V. Y. Lum",
title = "{EXPRESS}: a data {EXtraction, Processing, and
Restructuring System}",
journal = j-TODS,
volume = "2",
number = "2",
pages = "134--174",
month = jun,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-2/p134-shu/p134-shu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-2/p134-shu/",
abstract = "EXPRESS is an experimental prototype data translation
system which can access a wide variety of data and
restructure it for new uses. The system is driven by
two very high level nonprocedural languages: DEFINE for
data description and CONVERT for data restructuring.
Program generation and cooperating process techniques
are used to achieve efficient operation.\par
This paper describes the design and implementation of
EXPRESS. DEFINE and CONVERT are summarized and the
implementation architecture presented.\par
The DEFINE description is compiled into a customized
PL/1 program for accessing source data. The
restructuring specified in CONVERT is compiled into a
set of customized PL/1 procedures to derive multiple
target files from multiple input files. Job steps and
job control statements are generated automatically.
During execution, the generated procedures run under
control of a process supervisor, which coordinates
buffer management and handles file allocation,
deallocation, and all input/output requests.\par
The architecture of EXPRESS allows efficiency in
execution by avoiding unnecessary secondary storage
references while at the same time allowing the
individual procedures to be independent of each other.
Its modular structure permits the system to be extended
or transferred to another environment easily.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data conversion; data description languages; data
manipulation languages; data restructuring; data
translation; file conversion; program generation; very
high level languages",
subject = "Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5): {\bf Data
translation**}; Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2):
{\bf File organization}; Information Systems ---
Database Management --- Languages (H.2.3)",
}
@Article{Ozkarahan:1977:PER,
author = "E. A. Ozkarahan and S. A. Schuster and K. C. Sevcik",
title = "Performance Evaluation of a Relational Associative
Processor",
journal = j-TODS,
volume = "2",
number = "2",
pages = "175--195",
month = jun,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-2/p175-ozkarahan/p175-ozkarahan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-2/p175-ozkarahan/",
abstract = "An associative processor called RAP has been designed
to provide hardware support for the use and
manipulation of databases. RAP is particularly suited
for supporting relational databases. In this paper, the
relational operations provided by the RAP hardware are
described, and a representative approach to providing
the same relational operations with conventional
software and hardware is devised. Analytic models are
constructed for RAP and the conventional system. The
execution times of several of the operations are shown
to be vastly improved with RAP for large relations.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative processors; database machines; performance
evaluation; RAP hardware support database machine TODS;
relational databases",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}; Hardware
--- Control Structures and Microprogramming --- Control
Structure Performance Analysis and Design Aids
(B.1.2)",
}
@Article{Brice:1977:EPD,
author = "Richard S. Brice and Stephen W. Sherman",
title = "An Extension on the Performance of a Database Manager
in a Virtual Memory System Using Partially Locked
Virtual Buffers",
journal = j-TODS,
volume = "2",
number = "2",
pages = "196--207",
month = jun,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-2/p196-brice/p196-brice.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-2/p196-brice/",
abstract = "Buffer pools are created and managed in database
systems in order to reduce the total number of accesses
to the I/O devices. In systems using virtual memory,
any reduction in I/O accesses may be accompanied by an
increase in paging. The effects of these factors on
system performance are quantified, where system
performance is a function of page faults and database
accesses to the I/O devices. A previous study of this
phenomenon is extended through the analysis of
empirical data gathered in a multifactor experiment. In
this study memory is partitioned between the program
and the buffer so that the impact of the controlled
factors can be more effectively evaluated. It is
possible to improve system performance through the use
of different paging algorithms in the program partition
and the buffer partition. Also, the effects on system
performance as the virtual buffer size is increased
beyond the real memory allocated to the buffer
partition are investigated.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer manager; database management; double paging;
locked buffer; page faults; page replacement algorithm;
performance; pinning fixing TODS; virtual buffer;
virtual memory",
subject = "Hardware --- Control Structures and Microprogramming
--- Control Structure Performance Analysis and Design
Aids (B.1.2); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Database
Manager}",
}
@Article{Lohman:1977:OPB,
author = "Guy M. Lohman and John A. Muckstadt",
title = "Optimal Policy for Batch Operations: Backup,
Checkpointing, Reorganization, and Updating",
journal = j-TODS,
volume = "2",
number = "3",
pages = "209--222",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p209-lohman/p209-lohman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p209-lohman/",
abstract = "Many database maintenance operations are performed
periodically in batches, even in realtime systems. The
purpose of this paper is to present a general model for
determining the optimal frequency of these batch
operations. Specifically, optimal backup,
checkpointing, batch updating, and reorganization
policies are derived. The approach used exploits
inventory parallels by seeking the optimal number of
items--rather than a time interval--to trigger a batch.
The Renewal Reward Theorem is used to find the average
long run costs for backup, recovery, and item storage,
per unit time, which is then minimized to find the
optimal backup policy. This approach permits far less
restrictive assumptions about the update arrival
process than did previous models, as well as inclusion
of storage costs for the updates. The optimal
checkpointing, batch updating, and reorganization
policies are shown to be special cases of this optimal
backup policy. The derivation of previous results as
special cases of this model, and an example,
demonstrate the generality of the methodology
developed.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backup frequency; batch operations; batch update;
checkpoint interval; data base systems; database
maintenance; file reorganization; inventory theory;
real-time systems; renewal theory",
subject = "Information Systems --- Database Management ---
General (H.2.0)",
}
@Article{Wong:1977:IHT,
author = "Kai C. Wong and Murray Edelberg",
title = "Interval Hierarchies and Their Application to
Predicate Files",
journal = j-TODS,
volume = "2",
number = "3",
pages = "223--232",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p223-wong/p223-wong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p223-wong/",
abstract = "Predicates are used extensively in modern database
systems for purposes ranging from user specification of
associative accesses to data, to user-invisible system
control functions such as concurrency control and data
distribution. Collections of predicates, or predicate
files, must be maintained and accessed efficiently. A
dynamic index is described, called an interval
hierarchy, which supports several important retrieval
operations on files of simple conjunctive predicates.
Search and maintenance algorithms for interval
hierarchies are given. For a file of n predicates,
typical of the kind expected in practice, these
algorithms require time equal to $ O(\log n) $.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; data base systems; database
system; distributed data; index; interval; predicate
file",
subject = "Software --- Operating Systems --- Storage Management
(D.4.2): {\bf Storage hierarchies}; Information Systems
--- Information Storage and Retrieval --- Information
Storage (H.3.2): {\bf File organization}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Distributed databases}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Concurrency}; Information Systems --- Information
Storage and Retrieval --- Content Analysis and Indexing
(H.3.1): {\bf Indexing methods}",
}
@Article{Ries:1977:ELG,
author = "Daniel R. Ries and Michael Stonebraker",
title = "Effects of Locking Granularity in a Database
Management System",
journal = j-TODS,
volume = "2",
number = "3",
pages = "233--246",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p233-ries/p233-ries.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p233-ries/",
abstract = "Many database systems guarantee some form of integrity
control upon multiple concurrent updates by some form
of locking. Some ``granule'' of the database is chosen
as the unit which is individually locked, and a lock
management algorithm is used to ensure integrity. Using
a simulation model, this paper explores the desired
size of a granule. Under a wide variety of seemingly
realistic conditions, surprisingly coarse granularity
is called for. The paper concludes with some
implications of these results concerning the viability
of so-called predicate locking.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; consistency; data base systems; database
management; locking granularity; multiple updates;
predicate locks",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management (H.2); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Concurrency}",
}
@Article{Schmidt:1977:SHL,
author = "Joachim W. Schmidt",
title = "Some High Level Language Constructs for Data of Type
Relation",
journal = j-TODS,
volume = "2",
number = "3",
pages = "247--261",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p247-schmidt/p247-schmidt.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p247-schmidt/",
abstract = "For the extension of high level languages by data
types of mode relation, three language constructs are
proposed and discussed: a repetition statement
controlled by relations, predicates as a generalization
of Boolean expressions, and a constructor for relations
using predicates. The language constructs are developed
step by step starting with a set of elementary
operations on relations. They are designed to fit into
PASCAL without introducing too many additional
concepts.",
acknowledgement = ack-nhfb,
annote = "PASCAL/R",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data type; database;
high level language; language extension; nonprocedural
language; relational calculus; relational model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3)",
}
@Article{Fagin:1977:MVD,
author = "Ronald Fagin",
title = "Multi-Valued Dependencies and a New Normal Form for
Relational Databases",
journal = j-TODS,
volume = "2",
number = "3",
pages = "262--278",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p262-fagin/p262-fagin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p262-fagin/",
abstract = "A new type of dependency, which includes the
well-known functional dependencies as a special case,
is defined for relational databases. By using this
concept, a new (``fourth'') normal form for relation
schemata is defined. This fourth normal form is
strictly stronger than Codd's ``improved third normal
form'' (or ``Boyce-Codd normal form''). It is shown
that every relation schema can be decomposed into a
family of relation schemata in fourth normal form
without loss of information (that is, the original
relation can be obtained from the new relations by
taking joins).",
acknowledgement = ack-nhfb,
annote = "Multivalued dependency is defined for relational
databases, a new (``fourth'') normal form is strictly
stronger than Codd's.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "3NF; 4NF; Boyce-Codd normal form; data base systems;
database design; decomposition; fourth normal form;
functional dependency; multivalued dependency;
normalization; relational database; third normal form",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Normal forms}",
}
@Article{March:1977:DER,
author = "Salvatore T. March and Dennis G. Severance",
title = "The Determination of Efficient Record Segmentations
and Blocking Factors for Shared Data Files",
journal = j-TODS,
volume = "2",
number = "3",
pages = "279--296",
month = sep,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-3/p279-march/p279-march.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-3/p279-march/",
abstract = "It is generally believed that 80 percent of all
retrieval from a commercial database is directed at
only 20 percent of the stored data items. By
partitioning data items into primary and secondary
record segments, storing them in physically separate
files, and judiciously allocating available buffer
space to the two files, it is possible to significantly
reduce the average cost of information retrieval from a
shared database. An analytic model, based upon
knowledge of data item lengths, data access costs, and
user retrieval patterns, is developed to assist an
analyst with this assignment problem. A computationally
tractable design algorithm is presented and results of
its application are described.",
acknowledgement = ack-nhfb,
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bicriterion mathematical programs; branch and bound;
buffer allocation; data base systems; data management;
information science --- information retrieval; network
flows; record design; record segmentation",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Ozkarahan:1977:AAF,
author = "E. A. Ozkarahan and K. C. Sevcik",
title = "Analysis of Architectural Features for Enhancing the
Performance of a Database Machine",
journal = j-TODS,
volume = "2",
number = "4",
pages = "297--316",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p297-ozkarahan/p297-ozkarahan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p297-ozkarahan/",
abstract = "RAP (Relational Associative Processor) is a
``back-end'' database processor that is intended to
take over much of the effort of database management in
a computer system. In order to enhance RAP's
performance its design includes mechanisms for
permitting features analogous to multiprogramming and
virtual memory as in general purpose computer systems.
It is the purpose of this paper to present the detailed
design of these mechanisms, along with some analysis
that supports their value. Specifically, (1) the
response time provided by RAP under several scheduling
disciplines involving priority by class is analyzed,
(2) the cost effectiveness of the additional hardware
in RAP necessary to support multiprogramming is
assessed, and (3) a detailed design of the RAP virtual
memory system and its monitor is presented.",
acknowledgement = ack-nhfb,
annote = "RAP (Relational Associative Processor) is a ``back-end
database processor''; its design includes mechanisms
for multiprogramming and virtual memory.",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative processors; computer architecture;
computer architecture, hardware support TODS; data base
systems; database machines; database management",
subject = "Information Systems --- Database Management (H.2)",
}
@Article{Rissanen:1977:ICR,
author = "Jorma Rissanen",
title = "Independent Components of Relations",
journal = j-TODS,
volume = "2",
number = "4",
pages = "317--325",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p317-rissanen/p317-rissanen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p317-rissanen/",
abstract = "In a multiattribute relation or, equivalently, a
multicolumn table a certain collection of the
projections can be shown to be independent in much the
same way as the factors in a Cartesian product or
orthogonal components of a vector. A precise notion of
independence for relations is defined and studied. The
main result states that the operator which reconstructs
the original relation from its independent components
is the natural join, and that independent components
split the full family of functional dependencies into
corresponding component families. These give an
easy-to-check criterion for independence.",
acknowledgement = ack-nhfb,
annote = "In a multi-attribute relation a certain collection of
projections can be shown to be independent. The
operator which reconstructs the original relation is
the natural join. Independent components split the full
family of functional dependencies into corresponding
component families.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database; functional dependencies;
relations",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Bonczek:1977:TGB,
author = "Robert H. Bonczek and James I. Cash and Andrew B.
Whinston",
title = "A Transformational Grammar-Based Query Processor for
Access Control in a Planning System",
journal = j-TODS,
volume = "2",
number = "4",
pages = "326--338",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p326-bonczek/p326-bonczek.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p326-bonczek/",
abstract = "Providing computer facilities and data availability to
larger numbers of users generates increased system
vulnerability which is partially offset by software
security systems. Much too often these systems are
presented as ad hoc additions to the basic data
management system. One very important constituent of
software security systems is the access control
mechanism which may be the last resource available to
prohibit unauthorized data retrieval. This paper
presents a specification for an access control
mechanism. The mechanism is specified in a context for
use with the GPLAN decision support system by a
theoretical description consistent with the formal
definition of GPLAN's query language. Incorporation of
the mechanism into the language guarantees it will not
be an ad hoc addition. Furthermore, it provides a
facile introduction of data security dictates into the
language processor.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access control; data processing; data security;
database; decision support system; planning system",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- General (H.2.0):
{\bf Security, integrity, and protection**};
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods}",
}
@Article{Lang:1977:DBP,
author = "Tom{\'a}s Lang and Christopher Wood and Eduardo B.
Fern{\'a}ndez",
title = "Database Buffer Paging in Virtual Storage Systems",
journal = j-TODS,
volume = "2",
number = "4",
pages = "339--351",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p339-lang/p339-lang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p339-lang/",
abstract = "Three models, corresponding to different sets of
assumptions, are analyzed to study the behavior of a
database buffer in a paging environment. The models
correspond to practical situations and vary in their
search strategies and replacement algorithms. The
variation of I/O cost with respect to buffer size is
determined for the three models. The analysis is valid
for arbitrary database and buffer sizes, and the I/O
cost is obtained in terms of the miss ratio, the buffer
size, the number of main memory pages available for the
buffer, and the relative buffer and database access
costs.",
acknowledgement = ack-nhfb,
annote = "The variation of I/O cost with respect to buffer size
is determined for three models: the IMS/360 database
buffer, with LRU memory replacement, and a prefix table
in main memory indicating which database pages are in
the VSAM buffer.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer management; computer systems performance; data
base systems; database performance; page replacement
algorithm; virtual memory",
subject = "Information Systems --- Database Management ---
General (H.2.0); Information Systems --- Database
Management --- Systems (H.2.4)",
}
@Article{Thomas:1977:VAP,
author = "D. A. Thomas and B. Pagurek and R. J. Buhr",
title = "Validation Algorithms for Pointer Values in {DBTG}
Databases",
journal = j-TODS,
volume = "2",
number = "4",
pages = "352--369",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p352-thomas/p352-thomas.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p352-thomas/",
abstract = "This paper develops algorithms for verifying pointer
values in DBTG (Data Base Task Group) type databases.
To validate pointer implemented access paths and set
structures, two algorithms are developed. The first
procedure exploits the ``typed pointer'' concept
employed in modern programming languages to diagnose
abnormalities in directories and set instances. The
second algorithm completes pointer validation by
examining set instances to ensure that each DBTG set
has a unique owner. Sequential processing is used by
both algorithms, allowing a straightforward
implementation which is efficient in both time and
space. As presented, the algorithms are independent of
implementation schema and physical structure.",
acknowledgement = ack-nhfb,
annote = "Type Checking algorithm detects and locates errors in
the pointers which are used to represent chained and
pointer array implemented sets. In addition to invalid
set pointers, the algorithm has been extended to check
index sequential and inverted access directories
provided by EDMS.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database integrity; database
utilities; type checking; validation",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management --- General
(H.2.0): {\bf Security, integrity, and protection**}",
}
@Article{Claybrook:1977:FDM,
author = "Billy G. Claybrook",
title = "A Facility for Defining and Manipulating Generalized
Data Structures",
journal = j-TODS,
volume = "2",
number = "4",
pages = "370--406",
month = dec,
year = "1977",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1977-2-4/p370-claybrook/p370-claybrook.pdf;
http://www.acm.org/pubs/citations/journals/tods/1977-2-4/p370-claybrook/",
abstract = "A data structure definition facility (DSDF) is
described that provides definitions for several
primitive data types, homogeneous and heterogeneous
arrays, cells, stacks, queues, trees, and general
lists. Each nonprimitive data structure consists of two
separate entities--a head and a body. The head contains
the entry point(s) to the body of the structure; by
treating the head like a cell, the DSDF operations are
capable of creating and manipulating very general data
structures. A template structure is described that
permits data structures to share templates.\par
The primary objectives of the DSDF are: (1) to develop
a definition facility that permits the programmer to
explicitly define and manipulate generalized data
structures in a consistent manner, (2) to detect
mistakes and prevent the programmer from creating
(either inadvertently or intentionally) undesirable (or
illegal) data structures, (3) to provide a syntactic
construction mechanism that separates the
implementation of a data structure from its use in the
program in which it is defined, and (4) to facilitate
the development of reliable software.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data definition languages; data processing; data
structure definition facility; data structures;
database management",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management ---
Languages (H.2.3)",
}
@Article{Minker:1978:SSS,
author = "Jack Minker",
title = "Search Strategy and Selection Function for an
Inferential Relational System",
journal = j-TODS,
volume = "3",
number = "1",
pages = "1--31",
month = mar,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-1/p1-minker/p1-minker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-1/p1-minker/",
abstract = "An inferential relational system is one in which data
in the system consists of both explicit facts and
general axioms (or ``views''). The general axioms are
used together with the explicit facts to derive the
facts that are implicit (virtual relations) within the
system. A top-down algorithm, as used in artificial
intelligence work, is described to develop inferences
within the system. The top-down approach starts with
the query, a conjunction of relations, to be answered.
Either a relational fact solves a given relation in a
conjunct, or the relation is replaced by a conjunct of
relations which must be solved to solve the given
relation. The approach requires that one and only one
relation in a conjunction be replaced (or expanded) by
the given facts and general axioms. The decision to
expand only a single relation is termed a selection
function. It is shown for relational systems that such
a restriction still guarantees that a solution to the
problem will be found if one exists.\par
The algorithm provides for heuristic direction in the
search process. Experimental results are presented
which illustrate the techniques. A bookkeeping
mechanism is described which permits one to know when
subproblems are solved. It further facilitates the
outputting of reasons for the deductively found answer
in a coherent fashion.",
acknowledgement = ack-nhfb,
annote = "Data in the system consists of both explicit facts and
general axioms. The top-down approach starts with the
query, a conjunction of relations, to be answered.
Either a relational fact solves a given relation in a
conjunct, or the relation is replaced by a conjunct of
relations which must be solved to solve the given
relation. Experimental results are presented which
illustrate the techniques.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "answer and reason extraction; data base systems;
heuristics; inference mechanism; logic; predicate
calculus; relational databases; search strategy;
selection function; top-down search; virtual
relations",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Search process}",
}
@Article{Tuel:1978:ORP,
author = "William G. {Tuel, Jr.}",
title = "Optimum Reorganization Points for Linearly Growing
Files",
journal = j-TODS,
volume = "3",
number = "1",
pages = "32--40",
month = mar,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-1/p32-tuel/p32-tuel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-1/p32-tuel/",
abstract = "The problem of finding optimal reorganization
intervals for linearly growing files is solved. An
approximate reorganization policy, independent of file
lifetime, is obtained. Both the optimum and approximate
policies are compared to previously published results
using a numerical example.",
acknowledgement = ack-nhfb,
annote = "The problem of finding optimal reorganization
intervals for linearly growing files is solved.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing --- file organization; database; file
organization; optimization; physical database design
TODS, data base systems; reorganization",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Yu:1978:END,
author = "C. T. Yu and W. S. Luk and M. K. Siu",
title = "On the Estimation of the Number of Desired Records
with Respect to a Given Query",
journal = j-TODS,
volume = "3",
number = "1",
pages = "41--56",
month = mar,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-1/p41-yu/p41-yu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-1/p41-yu/",
abstract = "The importance of the estimation of the number of
desired records for a given query is outlined. Two
algorithms for the estimation in the ``closest
neighbors problem'' are presented. The numbers of
operations of the algorithms are $ O(m \ell^2) $ and $
O(m \ell) $, where $m$ is the number of clusters and $
\ell $ is the ``length'' of the query.",
acknowledgement = ack-nhfb,
annote = "Two Algorithms for the estimation in the `closest
neighbors problem'",
classification = "901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "closest neighbors; database; estimate; information
science, CTYu selectivity TODS; query",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}",
}
@Article{Su:1978:CCS,
author = "Stanley Y. W. Su and Ahmed Emam",
title = "{CASDAL}: {{\em CAS\/}SM}'s {{\em DA\/}}ta {{\em
L\/}}anguage",
journal = j-TODS,
volume = "3",
number = "1",
pages = "57--91",
month = mar,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1978-3-1/p57-su/",
abstract = "CASDAL is a high level data language designed and
implemented for the database machine CASSM. The
language is used for the manipulation and maintenance
of a database using an unnormalized (hierarchically
structured) relational data model. It also has
facilities to define, modify, and maintain the data
model definition. The uniqueness of CASDAL lies in its
power to specify complex operations in terms of several
new language constructs and its concepts of tagging or
marking tuples and of matching values when walking from
relation to relation. The language is a result of a
top-down design and development effort for a database
machine in which high level language constructs are
directly supported by the hardware. This paper (1)
gives justifications for the use of an unnormalized
relational model on which the language is based, (2)
presents the CASDAL language constructs with examples,
and (3) describes CASSM's architecture and hardware
primitives which match closely with the high level
language constructs and facilitate the translation
process. This paper also attempts to show how the
efficiency of the language and the translation task can
be achieved and simplified in a system in which the
language is the result of a top-down system design and
development.",
acknowledgement = ack-nhfb,
annote = "CASDAL is a high level data language for the database
machine CASSM. It uses an unnormalized (hierarchically
structured) relational data model. This paper (1)
justifies the use of this model (2) presents the Casdal
language constructs with examples, and (3) describes
CASSM's architecture.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative memory; computer programming languages;
data language; database; nonprocedural language; query
language; relational model; SYWSu hardware support
database machine TODS, data base systems",
subject = "Information Systems --- Database Management ---
Languages (H.2.3); Information Systems --- Database
Management --- Languages (H.2.3): {\bf Query
languages}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Relational databases}",
}
@Article{Chin:1978:SSD,
author = "Francis Y. Chin",
title = "Security in Statistical Databases for Queries with
Small Counts",
journal = j-TODS,
volume = "3",
number = "1",
pages = "92--104",
month = mar,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-1/p92-chin/p92-chin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-1/p92-chin/",
abstract = "The security problem of statistical databases
containing anonymous but individual records which may
be evaluated by queries about sums and averages is
considered. A model, more realistic than the previous
ones, is proposed, in which nonexisting records for
some keys can be allowed. Under the assumption that the
system protects the individual's information by the
well-known technique which avoids publishing summaries
with small counts, several properties about the system
and a necessary and sufficient condition for
compromising the database have been derived. The
minimum number of queries needed to compromise the
database is also discussed.",
acknowledgement = ack-nhfb,
annote = "Under the assumption that the system protects the
individual's information by the technique which avoids
publishing summaries with small counts, properties
about the system and a necessary and sufficient
condition for compromising the database have been
derived.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromisability; data base systems; data processing
--- security of data; data security; protection;
statistical databases",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Query processing};
Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Hendrix:1978:DNL,
author = "Gary G. Hendrix and Earl D. Sacerdoti and Daniel
Sagalowicz and Jonathan Slocum",
title = "Developing a Natural Language Interface to Complex
Data",
journal = j-TODS,
volume = "3",
number = "2",
pages = "105--147",
month = jun,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/Ai.misc.bib; Compendex database;
Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-2/p105-hendrix/p105-hendrix.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-2/p105-hendrix/",
abstract = "Aspects of an intelligent interface that provides
natural language access to a large body of data
distributed over a computer network are described. The
overall system architecture is presented, showing how a
user is buffered from the actual database management
systems (DBMSs) by three layers of insulating
components. These layers operate in series to convert
natural language queries into calls to DBMSs at remote
sites. Attention is then focused on the first of the
insulating components, the natural language system. A
pragmatic approach to language access that has proved
useful for building interfaces to databases is
described and illustrated by examples. Special language
features that increase system usability, such as
spelling correction, processing of incomplete inputs,
and run-time system personalization, are also
discussed. The language system is contrasted with other
work in applied natural language processing, and the
system's limitations are analyzed.",
acknowledgement = ack-nhfb,
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database access; human engineering;
intelligent access semantic grammar human engineering
run-time personalization, computer interfaces;
intelligent interface; natural language; Natural
Language, Intelligent Interface, Database Access,
Semantic Grammar, Human Engineering, Runtime
Personalization; run-time personalization; semantic
grammar",
subject = "Information Systems --- Database Management ---
Languages (H.2.3); Information Systems --- Database
Management --- Physical Design (H.2.2): {\bf Access
methods}",
}
@Article{Langdon:1978:NAP,
author = "Glen G. {Langdon, Jr.}",
title = "A Note on Associative Processors for Data Management",
journal = j-TODS,
volume = "3",
number = "2",
pages = "148--158",
month = jun,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-2/p148-langdon/p148-langdon.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-2/p148-langdon/",
abstract = "Associative ``logic-per-track'' processors for data
management are examined from a technological and
engineering point of view. Architectural and design
decisions are discussed. Some alternatives to the
design of comparators, garbage collection, and domain
extraction for architectures like the Relational
Associative Processor (RAP) are offered.",
acknowledgement = ack-nhfb,
annote = "Associative ``logic-per-track'' processors for data
management are examined from a technological and
engineering point of view (RAP).",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative processors; computer operating systems;
data base systems, hardware support database machine
TODS; database machines",
subject = "Information Systems --- Database Management (H.2)",
}
@Article{Kluge:1978:DFM,
author = "Werner E. Kluge",
title = "Data File Management in Shift-Register Memories",
journal = j-TODS,
volume = "3",
number = "2",
pages = "159--177",
month = jun,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-2/p159-kluge/p159-kluge.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-2/p159-kluge/",
abstract = "The paper proposes a shift-register memory, structured
as a two-dimensional array of uniform shift-register
loops which are linked by flow-steering switches, whose
switch control scheme is tailored to perform with great
efficiency data management operations on sequentially
organized files. The memory operates in a linear
input/output mode to perform record insertion,
deletion, and relocation on an existing file, and in a
sublinear mode for rapid internal file movement to
expedite file positioning and record retrieval and
update operations.\par
The memory, implemented as a large capacity
charge-coupled device or magnetic domain memory,
permits efficient data management on very large
databases at the level of secondary storage and lends
itself to applications as a universal disk replacement,
particularly in database computers.",
acknowledgement = ack-nhfb,
annote = "Shift-register memory, structured as a two-dimensional
array tailored to perform with great efficiency data
management operations on sequentially organized files",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data transformations; deletion; hardware support
database machine TODS, computer operating systems;
insertion; LIFO/FIFO operation modes; management of
sequentially organized files; record retrieval;
relocation; shift-register memories; updating",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3)",
}
@Article{Rosenkrantz:1978:SLC,
author = "David J. Rosenkrantz and Richard E. Stearns and Philip
M. {Lewis, II}",
title = "System Level Concurrency Control for Distributed
Database Systems",
journal = j-TODS,
volume = "3",
number = "2",
pages = "178--198",
month = jun,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-2/p178-rosenkrantz/p178-rosenkrantz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-2/p178-rosenkrantz/",
abstract = "A distributed database system is one in which the
database is spread among several sites and application
programs ``move'' from site to site to access and
update the data they need. The concurrency control is
that portion of the system that responds to the read
and write requests of the application programs. Its job
is to maintain the global consistency of the
distributed database while ensuring that the
termination of the application programs is not
prevented by phenomena such as deadlock. We assume each
individual site has its own local concurrency control
which responds to requests at that site and can only
communicate with concurrency controls at other sites
when an application program moves from site to site,
terminates, or aborts.\par
This paper presents designs for several distributed
concurrency controls and demonstrates that they work
correctly. It also investigates some of the
implications of global consistency of a distributed
database and discusses phenomena that can prevent
termination of application programs.",
acknowledgement = ack-nhfb,
annote = "Later arriving transactions may be aborted if not yet
in the commit stage.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; consistency; data base systems; database;
deadlock; deadly embrace; distributed; integrity; lock;
readers and writers; restart; rollback; transaction",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Concurrency}",
}
@Article{Delobel:1978:NHD,
author = "Claude Delobel",
title = "Normalization and Hierarchical Dependencies in the
Relational Data Model",
journal = j-TODS,
volume = "3",
number = "3",
pages = "201--222",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p201-delobel/p201-delobel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p201-delobel/",
abstract = "The purpose of this paper is to present a new approach
to the conceptual design of logical schemata for
relational databases. One-to-one, one-to-many, and
many-to-many relationships between the attributes of
database relations are modeled by means of functional
dependencies and multivalued dependencies. A new type
of dependency is introduced: first-order hierarchical
decomposition. The properties of this new type of
dependency are studied and related to the normalization
process of relations. The relationship between the
concept of first-order hierarchical decomposition and
the notion of hierarchical organization of data is
discussed through the normalization process.",
acknowledgement = ack-nhfb,
annote = "One-to-one, one-to-many relationships between the
attributes of database relations are modeled by means
of functional dependencies and multivalued
dependencies. A new type of dependency is first-order
hierarchical.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; data model; first-order
hierarchical dependency; functional dependency;
hierarchical schema; multivalued dependency;
normalization process; relational database; relational
model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Information Systems
--- Database Management --- Logical Design (H.2.1):
{\bf Schema and subschema}",
}
@Article{Smith:1978:SPD,
author = "Alan Jay Smith",
title = "Sequentiality and Prefetching in Database Systems",
journal = j-TODS,
volume = "3",
number = "3",
pages = "223--247",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p223-smith/p223-smith.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p223-smith/",
abstract = "Sequentiality of access is an inherent characteristic
of many database systems. We use this observation to
develop an algorithm which selectively prefetches data
blocks ahead of the point of reference. The number of
blocks prefetched is chosen by using the empirical run
length distribution and conditioning on the observed
number of sequential block references immediately
preceding reference to the current block. The optimal
number of blocks to prefetch is estimated as a function
of a number of ``costs,'' including the cost of
accessing a block not resident in the buffer (a miss),
the cost of fetching additional data blocks at fault
times, and the cost of fetching blocks that are never
referenced. We estimate this latter cost, described as
memory pollution, in two ways. We consider the
treatment (in the replacement algorithm) of prefetched
blocks, whether they are treated as referenced or not,
and find that it makes very little difference. Trace
data taken from an operational IMS database system is
analyzed and the results are presented. We show how to
determine optimal block sizes. We find that
anticipatory fetching of data can lead to significant
improvements in system operation.",
acknowledgement = ack-nhfb,
annote = "An algorithm which selectively prefetches data blocks
ahead of the point of reference. The optimal number of
blocks to prefetch is estimated as a function, the cost
(a miss), the cost of fetching blocks that are never
referenced of fetching additional data blocks, and the
cost of fetching blocks that are never referenced.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer management; database systems; dynamic
programming; IMS; paging; prefetching; read-ahead
caches caching buffer management TODS, data base
systems; sequentiality",
subject = "Information Systems --- Database Management ---
Systems (H.2.4)",
}
@Article{Schlageter:1978:PSD,
author = "Gunter Schlageter",
title = "Process Synchronization in Database Systems",
journal = j-TODS,
volume = "3",
number = "3",
pages = "248--271",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See errata report in \cite{Bernstein:1979:CPS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p248-schlageter/p248-schlageter.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p248-schlageter/",
abstract = "The problem of process synchronization in database
systems is analyzed in a strictly systematic way, on a
rather abstract level; the abstraction is chosen such
that the essential characteristics of the problem can
be distinctly modeled and investigated. Using a small
set of concepts, a consistent description of the whole
problem is developed; many widely used, but only
vaguely defined, notions are defined exactly within
this framework. The abstract treatment of the problem
immediately leads to practically useful insights with
respect to possible solutions, although
implementational aspects are not discussed in detail.",
acknowledgement = ack-nhfb,
annote = "Process synchronization in database systems is
analyzed on a rather abstract level. [see Bernstein for
comments]",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database consistency; database systems; integrity;
locking; operating system support TODS, data base
systems; parallel process systems; process
synchronization",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management (H.2)",
}
@Article{Hollaar:1978:SMP,
author = "Lee A. Hollaar",
title = "Specialized Merge Processor Networks for Combining
Sorted Lists",
journal = j-TODS,
volume = "3",
number = "3",
pages = "272--284",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p272-hollaar/p272-hollaar.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p272-hollaar/",
abstract = "In inverted file database systems, index lists
consisting of pointers to items within the database are
combined to form a list of items which potentially
satisfy a user's query. This list merging is similar to
the common data processing operation of combining two
or more sorted input files to form a sorted output
file, and generally represents a large percentage of
the computer time used by the retrieval system.
Unfortunately, a general purpose digital computer is
better suited for complicated numeric processing rather
than the simple combining of data. The overhead of
adjusting and checking pointers, aligning data, and
testing for completion of the operation overwhelm the
processing of the data.\par
A specialized processor can perform most of these
overhead operations in parallel with the processing of
the data, thereby offering speed increases by a factor
from 10 to 100 over conventional computers, depending
on whether a higher speed memory is used for storing
the lists. These processors can also be combined into
networks capable of directly forming the result of a
complex expression, with another order of magnitude
speed increase possible. The programming and operation
of these processors and networks is discussed, and
comparisons are made with the speed and efficiency of
conventional general purpose computers.",
acknowledgement = ack-nhfb,
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backend processors; binary tree networks; computer
architecture --- program processors; computer system
architecture; full text retrieval systems; hardware
support database machine TODS, data base systems;
inverted file databases; nonnumeric processing;
pipelined networks; sorted list merging",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Haerder:1978:IGA,
author = "Theo Haerder",
title = "Implementing a Generalized Access Path Structure for a
Relational Database System",
journal = j-TODS,
volume = "3",
number = "3",
pages = "285--298",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p285-haerder/p285-haerder.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p285-haerder/",
abstract = "A new kind of implementation technique for access
paths connecting sets of tuples qualified by attribute
values is described. It combines the advantages of
pointer chain and multilevel index implementation
techniques. Compared to these structures the
generalized access path structure is at least
competitive in performing retrieval and update
operations, while a considerable storage space saving
is gained. Some additional features of this structure
support $m$-way joins and the evaluation of
multirelation queries, and allow efficient checks of
integrity assertions and simple reorganization
schemes.",
acknowledgement = ack-nhfb,
annote = "Implementation technique for access paths connecting
sets of tuples qualified by attribute values combines
the advantages of pointer chains and multilevel
indexes. Features of this structure support m-way
joins.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems, Harder multi-relation indices
TODS",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Yu:1978:PP,
author = "C. T. Yu and M. K. Siu and K. Lam",
title = "On a Partitioning Problem",
journal = j-TODS,
volume = "3",
number = "3",
pages = "299--309",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p299-yu/p299-yu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p299-yu/",
abstract = "This paper investigates the problem of locating a set
of ``boundary points'' of a large number of records.
Conceptually, the boundary points partition the records
into subsets of roughly the same number of elements,
such that the key values of the records in one subset
are all smaller or all larger than those of the records
in another subset. We guess the locations of the
boundary points by linear interpolation and check their
accuracy by reading the key values of the records on
one pass. This process is repeated until all boundary
points are determined. Clearly, this problem can also
be solved by performing an external tape sort. Both
analytical and empirical results indicate that the
number of passes required is small in comparison with
that in an external tape sort. This kind of record
partitioning may be of interest in setting up a
statistical database system.",
acknowledgement = ack-nhfb,
annote = "Boundary points partition the records into subsets of
roughly the same number of elements. We guess the
locations of the boundary points by linear
interpolation and check their accuracy by reading the
key values of the records on one pass. This process is
repeated until all boundary points are determined.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CTYu TODS, data base systems; external sort; key
value; partition; passes; tape probability",
subject = "Computing Methodologies --- Image Processing And
Computer Vision --- Segmentation (I.4.6): {\bf Region
growing, partitioning}",
}
@Article{Fagin:1978:AM,
author = "Ronald Fagin",
title = "On an Authorization Mechanism",
journal = j-TODS,
volume = "3",
number = "3",
pages = "310--319",
month = sep,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-3/p310-fagin/p310-fagin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-3/p310-fagin/",
abstract = "Griffiths and Wade ({\em ACM Trans. Database Syst.
1,3}, (Sept. 1976), 242-255) have defined a dynamic
authorization mechanism that goes beyond the
traditional password approach. A database user can
grant or revoke privileges (such as to read, insert, or
delete) on a file that he has created. Furthermore, he
can authorize others to grant these same privileges.
The database management system keeps track of a
directed graph, emanating from the creator, of granted
privileges. The nodes of the graph correspond to users,
and the edges (each of which is labeled with a
timestamp) correspond to grants. The edges are of two
types, corresponding to whether or not the recipient of
the grant has been given the option to make further
grants of this privilege. Furthermore, for each pair $
A, B $ of nodes, there can be no more than one edge of
each type from $A$ to $B$. We modify this approach by
allowing graphs in which there can be multiple edges of
each type from one node to another. We prove
correctness (in a certain strong sense) for our
modified authorization mechanism. Further, we show by
example that under the original mechanism, the system
might forbid some user from exercising or granting a
privilege that he ``should'' be allowed to exercise or
grant.",
acknowledgement = ack-nhfb,
annote = "We prove correctness for our modified authorization
mechanism",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access control; authorization; data base systems;
database; privacy; proof of correctness; protection;
revocation; security",
subject = "Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Salton:1978:GSC,
author = "G. Salton and A. Wong",
title = "Generation and Search of Clustered Files",
journal = j-TODS,
volume = "3",
number = "4",
pages = "321--346",
month = dec,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-4/p321-salton/p321-salton.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-4/p321-salton/",
abstract = "A classified, or clustered file is one where related,
or similar records are grouped into classes, or
clusters of items in such a way that all items within a
cluster are jointly retrievable. Clustered files are
easily adapted to broad and narrow search strategies,
and simple file updating methods are available. An
inexpensive file clustering method applicable to large
files is given together with appropriate file search
methods. An abstract model is then introduced to
predict the retrieval effectiveness of various search
methods in a clustered file environment. Experimental
evidence is included to test the versatility of the
model and to demonstrate the role of various parameters
in the cluster search process.",
acknowledgement = ack-nhfb,
annote = "Automatic classification for information retrieval",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "automatic classification; cluster searching; clustered
files; data processing; fast classification; file
organization; probabilistic models",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Clustering}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}",
}
@Article{Banerjee:1978:CCD,
author = "Jayanta Banerjee and Richard I. Baum and David K.
Hsiao",
title = "Concepts and Capabilities of a Database Computer",
journal = j-TODS,
volume = "3",
number = "4",
pages = "347--384",
month = dec,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-4/p347-banerjee/p347-banerjee.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-4/p347-banerjee/",
abstract = "The concepts and capabilities of a database computer
(DBC) are given in this paper. The proposed design
overcomes many of the traditional problems of database
system software and is one of the first to describe a
complete data-secure computer capable of handling large
databases.\par
This paper begins by characterizing the major problems
facing today's database system designers. These
problems are intrinsically related to the nature of
conventional hardware and can only be solved by
introducing new architectural concepts. Several such
concepts are brought to bear in the later sections of
this paper. These architectural principles have a major
impact upon the design of the system and so they are
discussed in some detail. A key aspect of these
principles is that they can be implemented with
near-term technology. The rest of the paper is devoted
to the functional characteristics and the theory of
operation of the DBC. The theory of operation is based
on a series of abstract models of the components and
data structures employed by the DBC. These models are
used to illustrate how the DBC performs access
operations, manages data structures and security
specifications, and enforces security requirements.
Short Algol-like algorithms are used to show how these
operations are carried out. This part of the paper
concludes with a high-level description of the DBC
organization. The actual details of the DBC hardware
are quite involved and so their presentation is not the
subject of this paper.\par
A sample database is included in the Appendix to
illustrate the working of the security and clustering
mechanisms of the DBC.",
acknowledgement = ack-nhfb,
annote-1 = "The concepts of a database computer (DBC) are given.
The theory of operation is based on abstract models.
The DBC performs access operations, manages data
structures and security specifications.",
annote-2 = "The correct author order (from the running heads and
table of contents) is Banerjee, Baum, Hsiao: the
article cover page has Banerjee, Hsiao, Baum, because
the first two share a common address.",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "clustering; content-addressable memory; data base
systems; database computers; hardware support machine
TODS, computer architecture; keywords; mass memory;
performance; security; structure memory",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Clustering}",
}
@Article{Bradley:1978:EOC,
author = "J. Bradley",
title = "An Extended Owner-Coupled Set Data Model and Predicate
Calculus for Database Management",
journal = j-TODS,
volume = "3",
number = "4",
pages = "385--416",
month = dec,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-4/p385-bradley/p385-bradley.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-4/p385-bradley/",
abstract = "A data model is presented, based on the extension of
the concept of a DBTG owner-coupled set to permit {\em
static\/} and {\em dynamic\/} sets and a new kind of
set referred to as a {\em virtual\/} set. The notion of
{\em connection fields\/} is introduced, and it is
shown how connection fields may be used to construct
derived information bearing set names, and hence permit
the specification of (dynamic) sets which are not
predeclared in a schema. Virtual sets are shown to
reflect the functional dependencies which can exist
within a file. A technique which permits the data model
to be fully described diagrammatically by {\em extended
Bachman diagrams\/} is described. A predicate calculus
for manipulation of this data model is presented.
Expressions written in this calculus are compared with
corresponding expressions in a relational predicate
calculus, DSL ALPHA. An argument for the relational
completeness of the language is given.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Codasyl DBTG; connection field; data base systems; DSL
AlPHA; dynamic set; extended Bachman diagram; extended
owner-coupled set data model; extended owner-coupled
set predicate calculus; functional dependency;
information bearing set name; owner-coupled set; static
set; virtual set",
subject = "Information Systems --- Database Management (H.2)",
}
@Article{Shneiderman:1978:IHF,
author = "Ben Shneiderman",
title = "Improving the Human Factors Aspect of Database
Interactions",
journal = j-TODS,
volume = "3",
number = "4",
pages = "417--439",
month = dec,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-4/p417-shneiderman/p417-shneiderman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-4/p417-shneiderman/",
abstract = "The widespread dissemination of computer and
information systems to nontechnically trained
individuals requires a new approach to the design and
development of database interfaces. This paper provides
the motivational background for controlled
psychological experimentation in exploring the
person\slash machine interface. Frameworks for the
reductionist approach are given, research methods
discussed, research issues presented, and a small
experiment is offered as an example of what can be
accomplished. This experiment is a comparison of
natural and artificial language query facilities.
Although subjects posed approximately equal numbers of
valid queries with either facility, natural language
users made significantly more invalid queries which
could not be answered from the database that was
described.",
acknowledgement = ack-nhfb,
classification = "461; 723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; data models; database systems;
experimentation; human engineering; human factors;
natural language interfaces; psychology; query
languages; systems science and cybernetics --- man
machine systems",
subject = "Information Systems --- Models and Principles ---
User/Machine Systems (H.1.2): {\bf Human factors};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Query languages}; Information Systems --- Database
Management --- Systems (H.2.4)",
}
@Article{Comer:1978:DOI,
author = "Douglas Comer",
title = "The Difficulty of Optimum Index Selection",
journal = j-TODS,
volume = "3",
number = "4",
pages = "440--445",
month = dec,
year = "1978",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1978-3-4/p440-comer/p440-comer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1978-3-4/p440-comer/",
abstract = "Given a file on a secondary store in which each record
has several attributes, it is usually advantageous to
build an index mechanism to decrease the cost of
conducting transactions to the file. The problem of
selecting attributes over which to index has been
studied in the context of various storage structures
and access assumptions. One algorithm to make an
optimum index selection requires 2 $k$ steps in the
worst case, where $k$ is the number of attributes in
the file. We examine the question of whether a more
efficient algorithm might exist and show that even
under a simple cost criterion the problem is
computationally difficult in a precise sense. Our
results extend directly to other related problems where
the cost of the index depends on fixed values which are
assigned to each attribute. Some practical implications
are discussed.",
acknowledgement = ack-nhfb,
annote = "Theorem: optimum index selection problem OISP is
NP-complete for files of degree $ d \ge 2 $.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "attribute selection; complexity; index selection;
physical database design; secondary index",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Indexing methods}",
}
@Article{Babb:1979:IRD,
author = "E. Babb",
title = "Implementing a Relational Database by Means of
Specialized Hardware",
journal = j-TODS,
volume = "4",
number = "1",
pages = "1--29",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p1-babb/p1-babb.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p1-babb/",
abstract = "New hardware is described which allows the rapid
execution of queries demanding the joining of
physically stored relations. The main feature of the
hardware is a special store which can rapidly remember
or recall data. This data might be pointers from one
file to another, in which case the memory helps with
queries on joins of files. Alternatively, the memory
can help remove redundant data during projection[s??],
giving a considerable speed advantage over conventional
hardware.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bit array; CAFS; content addressing; database;
hardware support machine bit vector filter
probabilistic semi-join TODS, data base systems;
hashing; information retrieval; join; projection;
relational model; selection; special hardware",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Beeri:1979:CPR,
author = "Catriel Beeri and Philip A. Bernstein",
title = "Computational Problems Related to the Design of Normal
Form Relational Schemas",
journal = j-TODS,
volume = "4",
number = "1",
pages = "30--59",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Compiler/prog.lang.theory.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: errata in ACM Transactions on
Database Systems, Vol. 4 No. 3, Sep. 1979, pp. 396.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p30-beeri/p30-beeri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p30-beeri/",
abstract = "Problems related to functional dependencies and the
algorithmic design of relational schemas are examined.
Specifically, the following results are presented: (1)
a tree model of derivations of functional dependencies
from other functional dependencies; (2) a linear-time
algorithm to test if a functional dependency is in the
closure of a set of functional dependencies; (3) a
quadratic-time implementation of Bernstein's third
normal form schema synthesis algorithm.
\par
Furthermore, it is shown that most interesting
algorithmic questions about Boyce-Codd normal form and
keys are {\em NP\/}-complete and are therefore probably
not amenable to fast algorithmic solutions.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1); Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Lockemann:1979:DAD,
author = "Peter C. Lockemann and Heinrich C. Mayr and Wolfgang
H. Weil and Wolfgang H. Wohlleber",
title = "Data Abstractions for Database Systems",
journal = j-TODS,
volume = "4",
number = "1",
pages = "60--75",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p60-lockemann/p60-lockemann.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p60-lockemann/",
abstract = "Data abstractions were originally conceived as a
specification tool in programming. They also appear to
be useful for exploring and explaining the capabilities
and shortcomings of the data definition and
manipulation facilities of present-day database
systems. Moreover they may lead to new approaches to
the design of these facilities. In the first section
the paper introduces an axiomatic method for specifying
data abstractions and, on that basis, gives precise
meaning to familiar notions such as data model, data
type, and database schema. In a second step the various
possibilities for specifying data types within a given
data model are examined and illustrated. It is shown
that data types prescribe the individual operations
that are allowed within a database. Finally, some
additions to the method are discussed which permit the
formulation of interrelationships between arbitrary
operations.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data type; data abstraction; data base
systems; data definition language; data manipulation
language; data model; data structure; data type;
database consistency; database design; database schema;
integrity constraints; specification",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Languages (H.2.3): {\bf Data
manipulation languages (DML)}; Information Systems ---
Database Management --- Logical Design (H.2.1): {\bf
Data models}; Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Schema and
subschema}",
}
@Article{Denning:1979:TTS,
author = "Dorothy E. Denning and Peter J. Denning and Mayer D.
Schwartz",
title = "The Tracker: a Threat to Statistical Database
Security",
journal = j-TODS,
volume = "4",
number = "1",
pages = "76--96",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p76-denning/p76-denning.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p76-denning/",
abstract = "The query programs of certain databases report raw
statistics for query sets, which are groups of records
specified implicitly by a characteristic formula. The
raw statistics include query set size and sums of
powers of values in the query set. Many users and
designers believe that the individual records will
remain confidential as long as query programs refuse to
report the statistics of query sets which are too
small. It is shown that the compromise of small query
sets can in fact almost always be accomplished with the
help of characteristic formulas called trackers. J.
Schl{\"o}rer's individual tracker is reviewed; it is
derived from known characteristics of a given
individual and permits deducing additional
characteristics he may have. The general tracker is
introduced: It permits calculating statistics for
arbitrary query sets, without requiring preknowledge of
anything in the database. General trackers always exist
if there are enough distinguishable classes of
individuals in the database, in which case the trackers
have a simple form. Almost all databases have a general
tracker, and general trackers are almost always easy to
find. Security is not guaranteed by the lack of a
general tracker.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; data base systems; data processing;
data security; database security; secure query
functions; statistical database; tracker",
subject = "Information Systems --- Database Management ---
General (H.2.0): {\bf Security, integrity, and
protection**}; Information Systems --- Database
Management --- Database Applications (H.2.8): {\bf
Statistical databases}",
}
@Article{Dobkin:1979:SDP,
author = "David Dobkin and Anita K. Jones and Richard J.
Lipton",
title = "Secure Databases: Protection Against User Influence",
journal = j-TODS,
volume = "4",
number = "1",
pages = "97--106",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p97-dobkin/p97-dobkin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p97-dobkin/",
abstract = "Users may be able to compromise databases by asking a
series of questions and then inferring new information
from the answers. The complexity of protecting a
database against this technique is discussed here.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromise; data base systems; database; inference;
information flow; protection; security; Security TODS,
data processing; statistical query",
subject = "Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Kent:1979:LRB,
author = "William Kent",
title = "Limitations of Record-Based Information Models",
journal = j-TODS,
volume = "4",
number = "1",
pages = "107--131",
month = mar,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-1/p107-kent/p107-kent.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-1/p107-kent/",
abstract = "Record structures are generally efficient, familiar,
and easy to use for most current data processing
applications. But they are not complete in their
ability to represent information, nor are they fully
self-describing.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual model; data model; entities; first normal
form; information model; normalization; records;
relationships; semantic model",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Normal forms}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Yao:1979:OQE,
author = "S. Bing Yao",
title = "Optimization of Query Evaluation Algorithms",
journal = j-TODS,
volume = "4",
number = "2",
pages = "133--155",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p133-yao/p133-yao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p133-yao/",
abstract = "A model of database storage and access is presented.
The model represents many evaluation algorithms as
special cases, and helps to break a complex algorithm
into simple access operations. Generalized access cost
equations associated with the model are developed and
analyzed. Optimization of these cost equations yields
an optimal access algorithm which can be synthesized by
a query subsystem whose design is based on the modular
access operations.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data base systems;
data manipulation language; database optimization;
inverted file; query language; query languages; query
optimization; relational data model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Data models}; Information Systems ---
Database Management --- Languages (H.2.3): {\bf Data
manipulation languages (DML)}",
}
@Article{Schwartz:1979:LQS,
author = "M. D. Schwartz and D. E. Denning and P. J. Denning",
title = "Linear Queries in Statistical Databases",
journal = j-TODS,
volume = "4",
number = "2",
pages = "156--167",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p156-schwartz/p156-schwartz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p156-schwartz/",
abstract = "A database is compromised if a user can determine the
data elements associated with keys which he did not
know previously. If it is possible, compromise can be
achieved by posing a finite set of queries over sets of
data elements and employing initial information to
solve the resulting system of equations. Assuming the
allowable queries are linear, that is, weighted sums of
data elements, we show how compromise can be achieved
and we characterize the maximal initial information
permitted of a user in a secure system. When compromise
is possible, the initial information and the number of
queries required to achieve it is surprisingly small.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; data base systems; data processing
--- security of data; data security; database security;
inference; linear query; secure query functions;
statistical database",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Query processing};
Information Systems --- Database Management --- General
(H.2.0): {\bf Security, integrity, and protection**}",
}
@Article{Aho:1979:OPM,
author = "Alfred V. Aho and Jeffrey D. Ullman",
title = "Optimal Partial-Match Retrieval When Fields are
Independently Specified",
journal = j-TODS,
volume = "4",
number = "2",
pages = "168--179",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Graphics/siggraph/79.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p168-aho/p168-aho.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p168-aho/",
abstract = "This paper considers the design of a system to answer
partial-match queries from a file containing a
collection of records, each record consisting of a
sequence of fields. A partial-match query is a
specification of values for zero or more fields of a
record, and the answer to a query is a listing of all
records in the file whose fields match the specified
values.\par
A design is considered in which the file is stored in a
set of bins. A formula is derived for the optimal
number of bits in a bin address to assign to each
field, assuming the probability that a given field is
specified in a query is independent of what other
fields are specified. Implications of the optimality
criterion on the size of bins are also discussed.",
acknowledgement = ack-nhfb,
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative searching; data processing --- file
organization; file organization; hashing; information
retrieval; information science; partial-match
retrieval; searching",
oldlabel = "geom-2",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Retrieval models}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Thomas:1979:MCA,
author = "Robert H. Thomas",
title = "A Majority Consensus Approach to Concurrency Control
for Multiple Copy Databases",
journal = j-TODS,
volume = "4",
number = "2",
pages = "180--209",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p180-thomas/p180-thomas.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p180-thomas/",
abstract = "A ``majority consensus'' algorithm which represents a
new solution to the update synchronization problem for
multiple copy databases is presented. The algorithm
embodies distributed control and can function
effectively in the presence of communication and
database site outages. The correctness of the algorithm
is demonstrated and the cost of using it is analyzed.
Several examples that illustrate aspects of the
algorithm operation are included in the Appendix.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "clock synchronization; computer networks; concurrency
control; data base systems; distributed computation;
distributed control; distributed databases;
multiprocess systems; update synchronization",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}; Information Systems
--- Information Storage and Retrieval --- Systems and
Software (H.3.4): {\bf Distributed systems}",
}
@Article{Ries:1979:LGR,
author = "Daniel R. Ries and Michael R. Stonebraker",
title = "Locking Granularity Revisited",
journal = j-TODS,
volume = "4",
number = "2",
pages = "210--227",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p210-ries/p210-ries.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p210-ries/",
abstract = "Locking granularity refers to the size and hence the
number of locks used to ensure the consistency of a
database during multiple concurrent updates. In an
earlier simulation study we concluded that coarse
granularity, such as area or file locking, is to be
preferred to fine granularity such as individual page
or record locking.\par
However, alternate assumptions than those used in the
original paper can change that conclusion. First, we
modified the assumptions concerning the placement of
the locks on the database with respect to the accessing
transactions. In the original model the locks were
assumed to be well placed. Under worse case and random
placement assumptions when only very small transactions
access the database, fine granularity is preferable.
\par
Second, we extended the simulation to model a lock
hierarchy where large transactions use large locks and
small transactions use small locks. In this scenario,
again under the random and worse case lock placement
assumptions, fine granularity is preferable if all
transactions accessing more than 1 percent of the
database use large locks.\par
Finally, the simulation was extended to model a ``claim
as needed'' locking strategy together with the
resultant possibility of deadlock. In the original
study all locks were claimed in one atomic operation at
the beginning of a transaction. The claim as needed
strategy does not change the conclusions concerning the
desired granularity.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; database management; locking granularity;
locking hierarchies; multiple updates; TODS Ingres,
data base systems",
subject = "Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Concurrency}; Information Systems --- Database
Management (H.2); Information Systems --- Database
Management --- Physical Design (H.2.2): {\bf Deadlock
avoidance}",
}
@Article{Burkhard:1979:PMH,
author = "Walter A. Burkhard",
title = "Partial-Match Hash Coding: Benefits of Redundancy",
journal = j-TODS,
volume = "4",
number = "2",
pages = "228--239",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Graphics/siggraph/79.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p228-burkhard/p228-burkhard.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p228-burkhard/",
abstract = "File designs suitable for retrieval from a file of
$k$-field records when queries may be partially
specified are examined. Storage redundancy is
introduced to obtain improved worst-case and
average-case performances. The resulting storage
schemes are appropriate for replicated distributed
database environments; it is possible to improve the
overall average and worst-case behavior for query
response as well as provide an environment with very
high reliability. Within practical systems it will be
possible to improve the query response time performance
as well as reliability over comparable systems without
replication.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access methods; algorithms; analysis; data base
systems; data processing --- file organization; data
structures; database systems; replication; searching",
oldlabel = "geom-100",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Search process}",
}
@Article{Raghavan:1979:EDR,
author = "Vijay V. Raghavan and C. T. Yu",
title = "Experiments on the Determination of the Relationships
Between Terms",
journal = j-TODS,
volume = "4",
number = "2",
pages = "240--260",
month = jun,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-2/p240-raghavan/p240-raghavan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-2/p240-raghavan/",
abstract = "The retrieval effectiveness of an automatic method
that uses relevance judgments for the determination of
positive as well as negative relationships between
terms is evaluated. The term relationships are
incorporated into the retrieval process by using a
generalized similarity function that has a term match
component, a positive term relationship component, and
a negative term relationship component. Two strategies,
query partitioning and query clustering, for the
evaluation of the effectiveness of the term
relationships are investigated. The latter appears to
be more attractive from linguistic as well as economic
points of view. The positive and the negative
relationships are verified to be effective both when
used individually, and in combination. The importance
attached to the term relationship components relative
to that of term match component is found to have a
substantial effect on the retrieval performance. The
usefulness of discriminant analysis as a technique for
determining the relative importance of these components
is investigated.",
acknowledgement = ack-nhfb,
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "antonym; document retrieval; feedback; information
science; pseudoclassification; semantics; statistical
discrimination; synonym; term associations; thesaurus",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Thesauruses}; Information Systems --- Database
Management --- Database Applications (H.2.8): {\bf
Statistical databases}",
}
@Article{Lipski:1979:SIC,
author = "Witold {Lipski, Jr.}",
title = "On Semantic Issues Connected with Incomplete
Information Databases",
journal = j-TODS,
volume = "4",
number = "3",
pages = "262--296",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Compendex database;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-3/p262-lipski/p262-lipski.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p262-lipski/",
abstract = "Various approaches to interpreting queries in a
database with incomplete information are discussed. A
simple model of a database is described, based on
attributes which can take values in specified attribute
domains. Information incompleteness means that instead
of having a single value of an attribute, we have a
subset of the attribute domain, which represents our
knowledge that the actual value, though unknown, is one
of the values in this subset. This extends the idea of
Codd's null value, corresponding to the case when this
subset is the whole attribute domain. A simple query
language to communicate with such a system is described
and its various semantics are precisely defined. We
emphasize the distinction between two different
interpretations of the query language--the external
one, which refers the queries directly to the real
world modeled in an incomplete way by the system, and
the internal one, under which the queries refer to the
system's information about this world, rather than to
the world itself. Both external and internal
interpretations are provided with the corresponding
sets of axioms which serve as a basis for equivalent
transformations of queries. The technique of equivalent
transformations of queries is then extensively
exploited for evaluating the interpretation of (i.e.,
the response to) a query.",
acknowledgement = ack-nhfb,
annote = "Attributes can take values in specified attribute
domains. Instead a single value of an attribute, we
have a subset of the attribute domain, which represents
our knowledge that the actual value, though unknown, is
one of the values in this subset. This extends the idea
of Codd's null value, corresponding to the case when
this subset is the whole attribute domain.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database; incomplete information;
model logic; null values; query language semantics;
relational model",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Relational databases}; Information Systems ---
Database Management --- Languages (H.2.3): {\bf Query
languages}",
}
@Article{Aho:1979:TJR,
author = "A. V. Aho and C. Beeri and J. D. Ullman",
title = "The theory of joins in relational databases",
journal = j-TODS,
volume = "4",
number = "3",
pages = "297--314",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See corrigendum \cite{Ullman:1983:CTJ}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-3/p297-aho/p297-aho.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p297-aho/",
abstract = "Answering queries in a relational database often
requires that the natural join of two or more relations
be computed. However, the result of a join may not be
what one expects. In this paper we give efficient
algorithms to determine whether the join of several
relations has the intuitively expected value (is {\em
lossless\/}) and to determine whether a set of
relations has a subset with a lossy join. These
algorithms assume that all data dependencies are
functional. We then discuss the extension of our
techniques to the case where data dependencies are
multivalued.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; decomposition of database schemes;
functional dependencies; lossless join; multivalued
dependencies; natural join; projection of dependencies;
relational databases",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Models and Principles ---
Systems and Information Theory (H.1.1)",
}
@Article{Fagin:1979:EHF,
author = "Ronald Fagin and J{\"u}rg Nievergelt and Nicholas
Pippenger and H. Raymond Strong",
key = "Fagin et al.",
title = "Extendible Hashing --- a Fast Access Method for
Dynamic Files",
journal = j-TODS,
volume = "4",
number = "3",
pages = "315--344",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/bin-packing.bib; Misc/is.bib",
note = "Also published in/as: IBM Research Report RJ2305, Jul.
1978. See \cite{Regnier:1985:AGF}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-3/p315-fagin/p315-fagin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p315-fagin/",
abstract = "Extendible hashing is a new access technique, in which
the user is guaranteed no more than two page faults to
locate the data associated with a given unique
identifier, or key. Unlike conventional hashing,
extendible hashing has a dynamic structure that grows
and shrinks gracefully as the database grows and
shrinks. This approach simultaneously solves the
problem of making hash tables that are extendible and
of making radix search trees that are balanced. We
study, by analysis and simulation, the performance of
extendible hashing. The results indicate that
extendible hashing provides an attractive alternative
to other access methods, such as balanced trees.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
journalabr = "ACM Trans Database Syst",
keywords = "access method; B-tree; data processing; directory;
extendible hashing; external hashing; file
organization; hashing; index; radix search; searching;
trie",
remark = "The user is guaranteed no more than two page faults to
locate the data associated with a given unique
identifier, or key. Extendible hashing has a dynamic
structure that grows and shrinks as the database grows
and shrinks.",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Search process}",
}
@Article{Lam:1979:PSH,
author = "Chat Yu Lam and Stuart E. Madnick",
title = "Properties of Storage Hierarchy Systems with Multiple
Page Sizes and Redundant Data",
journal = j-TODS,
volume = "4",
number = "3",
pages = "345--367",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p345-lam/",
abstract = "The need for high performance, highly reliable storage
for very large on-line databases, coupled with rapid
advances in storage device technology, has made the
study of generalized storage hierarchies an important
area of research.\par
This paper analyzes properties of a data storage
hierarchy system specifically designed for handling
very large on-line databases. To attain high
performance and high reliability, the data storage
hierarchy makes use of multiple page sizes in different
storage levels and maintains multiple copies of the
same information across the storage levels. Such a
storage hierarchy system is currently being designed as
part of the INFOPLEX database computer project.
Previous studies of storage hierarchies have primarily
focused on virtual memories for program storage and
hierarchies with a single page size across all storage
levels and/or a single copy of information in the
hierarchy.\par
In the INFOPLEX design, extensions to the least
recently used (LRU) algorithm are used to manage the
storage levels. The read-through technique is used to
initially load a referenced page of the appropriate
size into all storage levels above the one in which the
page is found. Since each storage level is viewed as an
extension of the immediate higher level, an overflow
page from level $i$ is always placed in level $ i + 1
$. Important properties of these algorithms are
derived. It is shown that depending on the types of
algorithms used and the relative sizes of the storage
levels, it is not always possible to guarantee that the
contents of a given storage level $i$ is always a
superset of the contents of its immediate higher
storage level $ i - 1 $. The necessary and sufficient
conditions for this property to hold are identified and
proved. Furthermore, it is possible that increasing the
size of intermediate storage levels may actually
increase the number of references to lower storage
levels, resulting in reduced performance. Conditions
necessary to avoid such an anomaly are also identified
and proved.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; data storage hierarchy; database
computer; inclusion properties; modeling; perform and
reliability analysis; storage management algorithms;
very large databases",
subject = "Information Systems --- Database Management (H.2);
Software --- Operating Systems --- Storage Management
(D.4.2): {\bf Storage hierarchies}",
}
@Article{Buneman:1979:EMR,
author = "O. Peter Buneman and Eric K. Clemons",
title = "Efficiently Monitoring Relational Databases",
journal = j-TODS,
volume = "4",
number = "3",
pages = "368--382",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Working paper, 76-10-08, Dep.
Decision Sciences, The Wharton School, Un. Penn, PA,
Jun. 1977.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-3/p368-buneman/p368-buneman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p368-buneman/",
abstract = "An alerter is a program which monitors a database and
reports to some user or program when a specified
condition occurs. It may be that the condition is a
complicated expression involving several entities in
the database; in this case the evaluation of the
expression may be computationally expensive. A scheme
is presented in which alerters may be placed on a
complex query involving a relational database, and a
method is demonstrated for reducing the amount of
computation involved in checking whether an alerter
should be triggered.",
acknowledgement = ack-nhfb,
annote = "An alerter monitors a database and reports when a
specific condition occurs. Alerters may be placed on a
query, a method is demonstrated for reducing the amount
of computation involved in checking whether an alerter
should be triggered. Recomputation of derived data with
pruning, viz. identity connection.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "alerters; data base systems; exception reporting;
integrity constraints; programming techniques;
relational databases",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Comer:1979:HTI,
author = "Douglas Comer",
title = "Heuristics For Trie Index Minimization",
journal = j-TODS,
volume = "4",
number = "3",
pages = "383--395",
month = sep,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-3/p383-comer/p383-comer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-3/p383-comer/",
abstract = "A trie is a digital search tree in which leaves
correspond to records in a file. Searching proceeds
from the root to a leaf, where the edge taken at each
node depends on the value of an attribute in the query.
Trie implementations have the advantage of being fast,
but the disadvantage of achieving that speed at great
expense in storage space. Of primary concern in making
a trie practical, therefore, is the problem of
minimizing storage requirements. One method for
reducing the space required is to reorder attribute
testing. Unfortunately, the problem of finding an
ordering which guarantees a minimum-size trie is
NP-complete. In this paper we investigate several
heuristics for reordering attributes, and derive bounds
on the sizes of the worst tries produced by them in
terms of the underlying file. Although the analysis is
presented for a binary file, extensions to files of
higher degree are shown.\par
Another alternative for reducing the space required by
a trie is an implementation, called an $ \Omega $-trie,
in which the order of attribute testing is contained in
the trie itself. We show that for most applications, $
\Omega $-tries are smaller than other implementations
of tries, even when heuristics for improving storage
requirements are employed.",
acknowledgement = ack-nhfb,
annote = "Of primary concern in making a trie practical is the
problem of minimizing storage requirements. One method
for reducing the space is attribute testing which is
NP-complete. Another alternative is an $ \Omega $-trie,
in which the order of attribute testing is contained in
the trie itself. $ \Omega $-tries are smaller than
other implementations of tries.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; doubly chained tree; index; trie;
trie minimization",
subject = "Data --- Data Structures (E.1); Information Systems
--- Database Management (H.2)",
}
@Article{Codd:1979:EDR,
author = "E. F. Codd",
title = "Extending the Database Relational Model to Capture
More Meaning",
journal = j-TODS,
volume = "4",
number = "4",
pages = "397--434",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Compendex database;
Compiler/prog.lang.theory.bib; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Reprinted in
\cite[pp.~457--475]{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p397-codd/p397-codd.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p397-codd/",
abstract = "During the last three or four years several
investigators have been exploring ``semantic models''
for formatted databases. The intent is to capture (in a
more or less formal way) more of the meaning of the
data so that database design can become more systematic
and the database system itself can behave more
intelligently. Two major thrusts are clear.\par
(1) the search for meaningful units that are as small
as possible-- {\em atomic semantics\/};\par
(2) the search for meaningful units that are larger
than the usual $n$-ary relation-- {\em molecular
semantics}.\par
In this paper we propose extensions to the relational
model to support certain atomic and molecular
semantics. These extensions represent a synthesis of
many ideas from the published work in semantic modeling
plus the introduction of new rules for insertion,
update, and deletion, as well as new algebraic
operators.",
acknowledgement = ack-nhfb,
acmcrnumber = "8905-0330",
annote = "``Semantic models'' for formatted databases, to
capture in a more or less formal way more of the
meaning of the data. Two major thrusts: relation and
molecular semantics. Extensions to the relational model
(RM/T). New rules for insertion, update, and deletion,
as well as new algebraic operators (Theta-select, outer
join,\ldots{}.).",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual model; conceptual schema; data base
systems; data model; data semantics; database; database
schema; entity model; knowledge base; knowledge
representation; relation; relational database;
relational model; relational schema; semantic model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Information Systems
--- Database Management --- Logical Design (H.2.1):
{\bf Schema and subschema}",
}
@Article{Aho:1979:EOC,
author = "A. V. Aho and Y. Sagiv and J. D. Ullman",
title = "Efficient Optimization of a Class of Relational
Expressions",
journal = j-TODS,
volume = "4",
number = "4",
pages = "435--454",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p435-aho/p435-aho.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p435-aho/",
abstract = "The design of several database query languages has
been influenced by Codd's relational algebra. This
paper discusses the difficulty of optimizing queries
based on the relational algebra operations select,
project, and join. A matrix, called a tableau, is
proposed as a useful device for representing the value
of a query, and optimization of queries is couched in
terms of finding a minimal tableau equivalent to a
given one. Functional dependencies can be used to imply
additional equivalences among tableaux. Although the
optimization problem is NP-complete, a polynomial time
algorithm exists to optimize tableaux that correspond
to an important subclass of queries.",
acknowledgement = ack-nhfb,
annote = "Optimizing queries based on select, project, and
join.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems, TODS tableaux optimization;
equivalence of queries; NP-completeness; query
optimization; relational algebra; relational database;
tableaux",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}",
}
@Article{Maier:1979:TID,
author = "David Maier and Alberto O. Mendelzon and Yehoshua
Sagiv",
title = "Testing Implications of Data Dependencies",
journal = j-TODS,
volume = "4",
number = "4",
pages = "455--469",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p455-maier/p455-maier.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p455-maier/",
abstract = "Presented is a computation method --- the {\em
chase\/} --- for testing implication of data
dependencies by a set of data dependencies. The chase
operates on tableaux similar to those of Aho, Sagiv,
and Ullman. The chase includes previous tableau
computation methods as special cases. By interpreting
tableaux alternately as mappings or as templates for
relations, it is possible to test implication of join
dependencies (including multivalued dependencies) and
functional dependencies by a set of dependencies.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "chase; data base systems; data dependencies;
functional dependencies; join dependencies; multivalued
dependencies; relational databases; tableaux",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Housel:1979:PTI,
author = "Barron C. Housel",
title = "Pipelining: a Technique for Implementing Data
Restructurers",
journal = j-TODS,
volume = "4",
number = "4",
pages = "470--492",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p470-housel/p470-housel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p470-housel/",
abstract = "In the past several years much attention has been
given to the problem of data translation. The focus has
been mainly on methodologies and specification
languages for accomplishing this task. Recently,
several prototype systems have emerged, and now the
issues of implementation and performance must be
addressed. In general, a data restructuring
specification may contain multiple source and target
files. This specification can be viewed as a ``process
graph'' which is a network of restructuring operations
subject to precedence constraints. One technique used
to achieve good performance is that of pipelining data
in the process graph.\par
In this paper we address a number of issues pertinent
to a pipelining architecture. Specifically, we give
algorithms for resolving deadlock situations which can
arise, and partitioning the process graph to achieve an
optimal schedule for executing the restructuring steps.
In addition, we discuss how pipelining has influenced
the design of the restructuring operations and the file
structures used in an actual system.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; data translation; database
conversion; deadlock; pipelining; process scheduling",
subject = "Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5): {\bf Data
translation**}; Information Systems --- Database
Management --- Physical Design (H.2.2): {\bf Deadlock
avoidance}",
}
@Article{Shopiro:1979:TPL,
author = "Jonathan E. Shopiro",
title = "{Theseus} --- {A} Programming Language for Relational
Databases",
journal = j-TODS,
volume = "4",
number = "4",
pages = "493--517",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p493-shopiro/p493-shopiro.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p493-shopiro/",
abstract = "Theseus, a very high-level programming language
extending EUCLID, is described. Data objects in Theseus
include relations and a-sets, a generalization of
records. The primary design goals of Theseus are to
facilitate the writing of well-structured programs for
database applications and to serve as a vehicle for
research in automatic program optimization.",
acknowledgement = ack-nhfb,
annote = "Extending EUCLID. Data objects in Theseus include
relations and a-sets",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compiler organization; computer programming languages;
data base systems; relational database languages; very
high-level languages",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Database (persistent)
programming languages}",
}
@Article{Yamamoto:1979:DBM,
author = "Sumiyasu Yamamoto and Shinsei Tazawa and Kazuhiko
Ushio and Hideto Ikeda",
title = "Design of a Balanced Multiple-Valued File-Organization
Scheme with the Least Redundancy",
journal = j-TODS,
volume = "4",
number = "4",
pages = "518--530",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p518-yamamoto/p518-yamamoto.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p518-yamamoto/",
abstract = "A new balanced file-organization scheme of order two
for multiple-valued records is presented. This scheme
is called HUBMFS 2 (Hiroshima University Balanced
Multiple-valued File-organization Scheme of order two).
It is assumed that records are characterized by $m$
attributes having $n$ possible values each, and the
query set consists of queries which specify values of
two attributes. It is shown that the redundancy of the
bucket (the probability of storing a record in the
bucket) is minimized if and only if the structure of
the bucket is a partite-claw. A necessary and
sufficient condition for the existence of an HUBMFS 2,
which is composed exclusively of partite-claw buckets,
is given. A construction algorithm is also given. The
proposed HUBMFS 2 is superior to existing BMFS 2
(Balanced Multiple-valued File-organization Schemes of
order two) in that it has the least redundancy among
all possible BMFS 2 's having the same parameters and
that it can be constructed for a less restrictive set
of parameters.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "balanced filing scheme; bucket; claw; data processing;
file organization; graph decomposition; information
retrieval; information storage; inverted file;
multipartite graph; multiple-valued attributes;
redundancy; secondary index",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Schema and
subschema}; Information Systems --- Information Storage
and Retrieval --- Information Storage (H.3.2)",
}
@Article{Batory:1979:STF,
author = "Don S. Batory",
title = "On Searching Transposed Files",
journal = j-TODS,
volume = "4",
number = "4",
pages = "531--544",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p531-batory/p531-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p531-batory/",
abstract = "A transposed file is a collection of nonsequential
files called subfiles. Each subfile contains selected
attribute data for all records. It is shown that
transposed file performance can be enhanced by using a
proper strategy to process queries. Analytic cost
expressions for processing conjunctive, disjunctive,
and batched queries are developed and an effective
heuristic for minimizing query processing costs is
presented. Formulations of the problem of optimally
processing queries for a particular family of
transposed files are shown to be NP-complete. Query
processing performance comparisons of multilist,
inverted, and nonsequential files with transposed files
are also considered.",
acknowledgement = ack-nhfb,
annote = "Analytic cost expressions for processing conjunctive,
disjunctive, and batch queries are developed and an
effective heuristic for minimizing query processing
costs is presented.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; file searching; inverted file;
multilist; NP-complete; query processing; transposed
file",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Search process}",
}
@Article{Bernstein:1979:CPS,
author = "Philip A. Bernstein and Marco A. Casanova and Nathan
Goodman",
title = "Comments on {``Process Synchronization in Database
Systems''}",
journal = j-TODS,
volume = "4",
number = "4",
pages = "545--546",
month = dec,
year = "1979",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Schlageter:1978:PSD}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1979-4-4/p545-bernstein/p545-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1979-4-4/p545-bernstein/",
acknowledgement = ack-nhfb,
annote = "The results of Schlageter are in error.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "Information Systems --- Database Management (H.2)",
}
@Article{Rothnie:1980:ISD,
author = "James B. {Rothnie, Jr.} and Philip A. Bernstein and S.
Fox and N. Goodman and M. Hammer and T. A. Landers and
C. Reeve and David W. Shipman and E. Wong",
title = "Introduction to a System for Distributed Databases
({SDD-1})",
journal = j-TODS,
volume = "5",
number = "1",
pages = "1--17",
month = mar,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-1/p1-rothnie/p1-rothnie.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-1/p1-rothnie/",
abstract = "The declining cost of computer hardware and the
increasing data processing needs of geographically
dispersed organizations have led to substantial
interest in distributed data management. SDD-1 is a
distributed database management system currently being
developed by Computer Corporation of America. Users
interact with SDD-1 precisely as if it were a
nondistributed database system because SDD-1 handles
all issues arising from the distribution of data. These
issues include distributed concurrency control,
distributed query processing, resiliency to component
failure, and distributed directory management. This
paper presents an overview of the SDD-1 design and its
solutions to the above problems.\par
This paper is the first of a series of companion papers
on SDD-1 (Bernstein and Shipman [2], Bernstein et al.
[4], and Hammer and Shipman [14]).",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; data base systems; database
reliability; distributed database system; query
processing; relational data model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Relational databases}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Concurrency}; Information Systems --- Database
Management --- Systems (H.2.4): {\bf Query
processing}",
}
@Article{Bernstein:1980:CCS,
author = "Philip A. Bernstein and David W. Shipman and James B.
{Rothnie, Jr.}",
title = "Concurrency Control in a System for Distributed
Databases ({SDD-1})",
journal = j-TODS,
volume = "5",
number = "1",
pages = "18--51",
month = mar,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-1/p18-bernstein/p18-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-1/p18-bernstein/",
abstract = "This paper presents the concurrency control strategy
of SDD-1. SDD-1, a System for Distributed Databases, is
a prototype distributed database system being developed
by Computer Corporation of America. In SDD-1, portions
of data distributed throughout a network may be
replicated at multiple sites. The SDD-1 concurrency
control guarantees database consistency in the face of
such distribution and replication.\par
This paper is one of a series of companion papers on
SDD-1 [4, 10, 12, 21].",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; conflict graph; data base
systems; distributed database system; serializability;
synchronization; timestamps",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Distributed databases}",
}
@Article{Bernstein:1980:CCC,
author = "Philip A. Bernstein and David W. Shipman",
title = "Correctness of Concurrency Control Mechanisms in a
System for Distributed Databases ({SDD-1})",
journal = j-TODS,
volume = "5",
number = "1",
pages = "52--68",
month = mar,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-1/p52-bernstein/p52-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-1/p52-bernstein/",
abstract = "This paper presents a formal analysis of the
concurrency control strategy of SDD-1. SDD-1, a System
for Distributed Databases, is a prototype distributed
database system being developed by Computer Corporation
of America. In SDD-1, portions of data distributed
throughout a network may be replicated at multiple
sites. The SDD-1 concurrency control guarantees
database consistency in the face of such distribution
and replication.\par
This paper is one of a series of companion papers on
SDD-1 [2, 8].",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conflict graph; correctness of concurrency control;
data base systems; distributed database system;
serializability theory",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Concurrency}",
}
@Article{Gopalakrishna:1980:PEA,
author = "V. Gopalakrishna and C. E. {Veni Madhavan}",
title = "Performance Evaluation of Attribute-Based Tree
Organization",
journal = j-TODS,
volume = "5",
number = "1",
pages = "69--87",
month = mar,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-1/p69-gopalakrishna/p69-gopalakrishna.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-1/p69-gopalakrishna/",
abstract = "A modified version of the multiple attribute tree
(MAT) database organization, which uses a compact
directory, is discussed. An efficient algorithm to
process the directory for carrying out the node
searches is presented. Statistical procedures are
developed to estimate the number of nodes searched and
the number of data blocks retrieved for most general
and complex queries. The performance of inverted file
and modified MAT organizations are compared using six
real-life databases and four types of query
complexities. Careful tradeoffs are established in
terms of storage and access times for directory and
data, query complexities, and database
characteristics.",
acknowledgement = ack-nhfb,
annote = "A version of the multiple attribute tree (MAT)
database organization. Statistical procedures are
developed to estimate the number of nodes searched and
the number of data blocks retrieved. The performance of
inverted file and modified MAT organizations are
compared.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access time; average retrieval time per query; data
base systems; database organization; database
performance; directory search time; modified multiple
attribute tree; query complexity; secondary index
organization",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3)",
}
@Article{Denning:1980:FPF,
author = "Dorothy E. Denning and Jan Schl{\"o}rer",
title = "Fast Procedure for Finding a Tracker in a Statistical
Database",
journal = j-TODS,
volume = "5",
number = "1",
pages = "88--102",
month = mar,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-1/p88-denning/p88-denning.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-1/p88-denning/",
abstract = "To avoid trivial compromises, most on-line statistical
databases refuse to answer queries for statistics about
small subgroups. Previous research discovered a
powerful snooping tool, the tracker, with which the
answers to these unanswerable queries are easily
calculated. However, the extent of this threat was not
clear, for no one had shown that finding a tracker is
guaranteed to be easy.\par
This paper gives a simple algorithm for finding a
tracker when the maximum number of identical records is
not too large. The number of queries required to find a
tracker is at most {$ O(\log_2 S) $} queries, where
{$S$} is the number of distinct records possible.
Experimental results show that the procedure often
finds a tracker with just a few queries. The threat
posed by trackers is therefore considerable.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; data base systems; data security;
database security; statistical database; tracker",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Menasce:1980:LPR,
author = "Daniel A. Menasc{\'e} and Gerald J. Popek and Richard
R. Muntz",
title = "A Locking Protocol for Resource Coordination in
Distributed Databases",
journal = j-TODS,
volume = "5",
number = "2",
pages = "103--138",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p103-menasce/p103-menasce.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p103-menasce/",
abstract = "A locking protocol to coordinate access to a
distributed database and to maintain system consistency
throughout normal and abnormal conditions is presented.
The proposed protocol is robust in the face of crashes
of any participating site, as well as communication
failures. Recovery from any number of failures during
normal operation or any of the recovery stages is
supported. Recovery is done in such a way that maximum
forward progress is achieved by the recovery
procedures. Integration of virtually any locking
discipline including predicate lock methods is
permitted by this protocol. The locking algorithm
operates, and operates correctly, when the network is
partitioned, either intentionally or by failure of
communication lines. Each partition is able to continue
with work local to it, and operation merges gracefully
when the partitions are reconnected.\par
A subroutine of the protocol, that assures reliable
communication among sites, is shown to have better
performance than two-phase commit methods. For many
topologies of interest, the delay introduced by the
overall protocol is not a direct function of the size
of the network. The communications cost is shown to
grow in a relatively slow, linear fashion with the
number of sites participating in the transaction. An
informal proof of the correctness of the algorithm is
also presented in this paper.\par
The algorithm has as its core a centralized locking
protocol with distributed recovery procedures. A
centralized controller with local appendages at each
site coordinates all resource control, with requests
initiated by application programs at any site. However,
no site experiences undue load. Recovery is broken down
into three disjoint mechanisms: for single node
recovery, merge of partitions, and reconstruction of
the centralized controller and tables. The disjointness
of the mechanisms contributes to comprehensibility and
ease of proof.\par
The paper concludes with a proposal for an extension
aimed at optimizing operation of the algorithm to adapt
to highly skewed distributions of activity. The
extension applies nicely to interconnected computer
networks.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; consistency; crash recovery; distributed
databases; locking protocol",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Distributed databases}",
}
@Article{Bayer:1980:PRD,
author = "R. Bayer and H. Heller and A. Reiser",
title = "Parallelism and Recovery in Database Systems",
journal = j-TODS,
volume = "5",
number = "2",
pages = "139--156",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p139-bayer/p139-bayer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p139-bayer/",
abstract = "In this paper a new method to increase parallelism in
database systems is described. Use is made of the fact
that for recovery reasons, we often have two values for
one object in the database--the new one and the old
one. Introduced and discussed in detail is a certain
scheme by which readers and writers may work
simultaneously on the same object. It is proved that
transactions executed according to this scheme have the
correct effect; i.e., consistency is preserved. Several
variations of the basic scheme which are suitable
depending on the degree of parallelism required, are
described.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; consistency; data base systems; deadlock;
integrity; recovery; synchronization; transaction; two
phase locking",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart};
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Deadlock avoidance};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Concurrency}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Transaction processing}",
}
@Article{Navathe:1980:SAD,
author = "Shamkant B. Navathe",
title = "Schema Analysis for Database Restructuring",
journal = j-TODS,
volume = "5",
number = "2",
pages = "157--184",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Proceedings of the Third
Conference on Very Large Databases, Morgan Kaufman
pubs. (Los Altos CA), 1977.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p157-navathe/p157-navathe.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p157-navathe/",
abstract = "The problem of generalized restructuring of databases
has been addressed with two limitations: first, it is
assumed that the restructuring user is able to describe
the source and target databases in terms of the
implicit data model of a particular methodology;
second, the restructuring user is faced with the task
of judging the scope and applicability of the defined
types of restructuring to his database implementation
and then of actually specifying his restructuring needs
by translating them into the restructuring operations
on a foreign data model. A certain amount of analysis
of the logical and physical structure of databases must
be performed, and the basic ingredients for such an
analysis are developed here. The distinction between
hierarchical and nonhierarchical data relationships is
discussed, and a classification for database schemata
is proposed. Examples are given to illustrate how these
schemata arise in the conventional hierarchical and
network systems. Application of the schema analysis
methodology to restructuring specification is also
discussed. An example is presented to illustrate the
different implications of restructuring three seemingly
identical database structures.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; data model; data relationships;
data semantics; data structure; database; database
design; database management systems; database
restructuring; graphical representation of data;
schema; stored data",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Schema and subschema}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Data models}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Mylopoulos:1980:LFD,
author = "John Mylopoulos and Philip A. Bernstein and Harry K.
T. Wong",
title = "A Language Facility for Designing Database-Intensive
Applications",
journal = j-TODS,
volume = "5",
number = "2",
pages = "185--207",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib; Object/Nierstrasz.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p185-mylopoulos/p185-mylopoulos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p185-mylopoulos/",
abstract = "TAXIS, a language for the design of interactive
information systems (e.g., credit card verification,
student-course registration, and airline reservations)
is described. TAXIS offers (relational) database
management facilities, a means of specifying semantic
integrity constraints, and an exception-handling
mechanism, integrated into a single language through
the concepts of {\em class, property}, and the {\em
IS-A\/} (generalization) {\em relationship}. A
description of the main constructs of TAXIS is included
and their usefulness illustrated with examples.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data type; applications programming;
exception handling; information system; relational data
model; semantic network",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Information Systems
--- Database Management --- Languages (H.2.3)",
}
@Article{Lozinskii:1980:CRR,
author = "Eliezer L. Lozinskii",
title = "Construction of Relations in Relational Databases",
journal = j-TODS,
volume = "5",
number = "2",
pages = "208--224",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p208-lozinskii/p208-lozinskii.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p208-lozinskii/",
abstract = "Using a nonprocedural language for query formulation
requires certain automatization of a query answering
process. Given a query for creation of a new relation,
the problem is to find an efficient procedure which
produces this relation from a given relational
database. The author concentrates upon sequences of
join operations which losslessly produce a relation
required by a query. A new property of such sequences
is analyzed which provides a basis for the presented
algorithms that construct an efficient join procedure.
The algorithms have polynomial complexity. A modified
AND\slash OR graph is used for the display of a given
set of dependencies and a collection of relations
representing a database.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; AND/OR graphs; data base systems; lossless
joins; query answering; relational databases",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Stonebraker:1980:RDS,
author = "Michael Stonebraker",
title = "Retrospection on a Database System",
journal = j-TODS,
volume = "5",
number = "2",
pages = "225--240",
month = jun,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-2/p225-stonebraker/p225-stonebraker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-2/p225-stonebraker/",
abstract = "This paper describes the implementation history of the
INGRES database system. It focuses on mistakes that
were made in progress rather than on eventual
corrections. Some attention is also given to the role
of structured design in a database system
implementation and to the problem of supporting
nontrivial users. Lastly, miscellaneous impressions of
UNIX, the PDP-11, and data models are given.",
acknowledgement = ack-nhfb,
annote = "The implementation history of the INGRES database
system. The role of structured design in a database
system implementation, impressions of UNIX, the PDP-11,
and data models are given.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency; data base systems, history evaluation,
Ingres, TODS; integrity; nonprocedural languages;
protection; recovery; relational databases",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Relational
databases}; Information Systems --- Database Management
--- Physical Design (H.2.2): {\bf Recovery and
restart}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Concurrency}",
}
@Article{Beeri:1980:MPF,
author = "Catriel Beeri",
title = "On the Membership Problem for Functional and
Multivalued Dependencies in Relational Databases",
journal = j-TODS,
volume = "5",
number = "3",
pages = "241--259",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p241-beeri/p241-beeri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p241-beeri/",
abstract = "The problem of whether a given dependency in a
database relation can be derived from a given set of
dependencies is investigated. We show that the problem
can be decided in polynomial time when the given set
consists of either multivalued dependencies only or of
both functional and multivalued dependencies and the
given dependency is also either a functional or a
multivalued dependency. These results hold when the
derivations are restricted not to use the
complementation rule.",
acknowledgement = ack-nhfb,
annote = "The problem of whether a given dependency in a
database relation can be derived from a given set of
dependencies is investigated. We show that the problem
can be decided in polynomial time when the given set
consists of either multivalued dependencies only or of
both functional and multivalued dependencies and the
given dependency is also either a functional or a
multivalued dependency. These results hold when the
derivations are restricted not to use the
complementation rule.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; functional dependency; inference
rule; membership; multivalued dependency; relations",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Klug:1980:CCR,
author = "A. Klug",
title = "Calculating Constraints on Relational Expressions",
journal = j-TODS,
volume = "5",
number = "3",
pages = "260--290",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p260-klug/p260-klug.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p260-klug/",
abstract = "This paper deals with the problem of determining which
of a certain class of constraints hold on a given
relational algebra expression where the base relations
come from a given schema. The class of constraints
includes functional dependencies, equality of domains,
and constancy of domains. The relational algebra
consists of projection, selection, restriction, cross
product, union, and difference. The problem as given is
undecidable, but if set difference is removed from the
algebra, there is a solution. Operators specifying a
closure function (similar to functional dependency
closure on one relation) are defined; these will
generate exactly the set of constraints valid on the
given relational algebra expression. We prove that the
operators are sound and complete.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "completeness; constraints; data base systems;
derivation rules; functional dependencies; Views",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Denning:1980:SSD,
author = "Dorothy E. Denning",
title = "Secure Statistical Databases with Random Sample
Queries",
journal = j-TODS,
volume = "5",
number = "3",
pages = "291--315",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p291-denning/p291-denning.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p291-denning/",
abstract = "A new inference control, called random sample queries,
is proposed for safeguarding confidential data in
on-line statistical databases. The random sample
queries control deals directly with the basic principle
of compromise by making it impossible for a questioner
to control precisely the formation of query sets.
Queries for relative frequencies and averages are
computed using random samples drawn from the query
sets. The sampling strategy permits the release of
accurate and timely statistics and can be implemented
at very low cost. Analysis shows the relative error in
the statistics decreases as the query set size
increases; in contrast, the effort required to
compromise increases with the query set size due to
large absolute errors. Experiments performed on a
simulated database support the analysis.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; data base systems; database security;
disclosure controls; sampling; statistical database",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Query processing};
Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Beck:1980:SMS,
author = "Leland L. Beck",
title = "A security mechanism for statistical database",
journal = j-TODS,
volume = "5",
number = "3",
pages = "316--338",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p316-beck/p316-beck.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p316-beck/",
abstract = "The problem of user inference in statistical databases
is discussed and illustrated with several examples. It
is assumed that the database allows ``total'',
``average'', ``count'', and ``percentile'' queries; a
query may refer to any arbitrary subset of the
database. Methods for protecting the security of such a
database are considered; it is shown that any scheme
which gives ``statistically correct'' answers is
vulnerable to penetration. A precise definition of
compromisability (in a statistical sense) is given. A
general model of user inference is proposed; two
special cases of this model appear to contain all
previously published strategies for compromising a
statistical database. A method for protecting the
security of such a statistical database against these
types of user inference is presented and discussed. It
is shown that the number of queries required to
compromise the database can be made arbitrarily large
by accepting moderate increases in the variance of
responses to queries. A numerical example is presented
to illustrate the application of the techniques
discussed.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromisability; data base systems; data security;
database inference; privacy protection; statistical
databases; statistical queries",
subject = "Information Systems --- Database Management ---
General (H.2.0): {\bf Security, integrity, and
protection**}; Information Systems --- Database
Management --- Systems (H.2.4): {\bf Query processing};
Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}",
}
@Article{Lee:1980:QTF,
author = "D. T. Lee and C. K. Wong",
title = "Quintary Trees: a File Structure for Multidimensional
Database Systems",
journal = j-TODS,
volume = "5",
number = "3",
pages = "339--353",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Graphics/siggraph/80.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p339-lee/p339-lee.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p339-lee/",
abstract = "A file structure is presented that was designed for a
database system in which four types of retrieval
requests (queries) are allowed: exact match, partial
match, range, and partial range queries. Outlines are
sketched for inserting and deleting records that
require O(k plus (log N)**k) time, on the average. This
structure achieves faster response time than previously
known structures (for many of the queries) at the cost
of extra storage.",
acknowledgement = ack-nhfb,
annote = "Four types of retrieval (queries) are allowed: exact
match, partial match, range, and partial range queries.
Faster response time at the cost of extra storage.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; data processing --- data
structures; database system; exact match queries; file
maintenance; information retrieval; key;
multidimensional space; queries; range search; search",
subject = "Data --- Data Structures (E.1): {\bf Trees};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}; Information Systems
--- Information Storage and Retrieval --- Information
Storage (H.3.2): {\bf File organization}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3)",
}
@Article{Kung:1980:CMB,
author = "H. T. Kung and Philip L. Lehman",
title = "Concurrent Manipulation of Binary Search Trees",
journal = j-TODS,
volume = "5",
number = "3",
pages = "354--382",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-3/p354-kung/p354-kung.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-3/p354-kung/",
abstract = "The concurrent manipulation of a binary search tree is
considered in this paper. The systems presented can
support any number of concurrent processes which
perform searching, insertion, deletion, and rotation
(reorganization) on the tree, but allow any process to
lock only a constant number of nodes at any time. Also,
in the systems, searches are essentially never blocked.
The concurrency control techniques introduced in the
paper include the use of special nodes and pointers to
redirect searches, and the use of copies of sections of
the tree to introduce many changes simultaneously and
therefore avoid unpredictable interleaving. Methods
developed in this paper may provide new insights into
other problems in the area of concurrent database
manipulation.",
acknowledgement = ack-nhfb,
annote = "Operations on tries are defined so that concurrency of
access is possible while the number of locked nodes is
minimal.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "binary search trees; concurrency controls; concurrent
algorithm; consistency; correctness; data processing;
data structures; databases; locking protocols",
subject = "Data --- Data Structures (E.1): {\bf Trees};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Concurrency}",
}
@Article{Denning:1980:CLQ,
author = "D. E. Denning",
title = "Corrigenda on Linear Queries in Statistical
Databases",
journal = j-TODS,
volume = "5",
number = "3",
pages = "383--383",
month = sep,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
annote = "refers to Schwartz 1979 TODS.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hsiao:1980:TFT,
author = "David K. Hsiao",
title = "{TODS} --- the first three years {(1976\&ndash1978)}",
journal = j-TODS,
volume = "5",
number = "4",
pages = "385--403",
month = dec,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-4/p385-hsiao/p385-hsiao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-4/p385-hsiao/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "General Literature --- General (A.0)",
}
@Article{Armstrong:1980:DFD,
author = "W. W. Armstrong and C. Delobel",
title = "Decompositions and Functional Dependencies in
Relations",
journal = j-TODS,
volume = "5",
number = "4",
pages = "404--430",
month = dec,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-4/p404-armstrong/p404-armstrong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-4/p404-armstrong/",
abstract = "A general study is made of two basic integrity
constraints on relations: functional and multivalued
dependencies. The latter are studied via an equivalent
concept: decompositions. A model is constructed for any
possible combination of functional dependencies and
decompositions. The model embodies some decompositions
as unions of relations having different schemata of
functional dependencies. This suggests a new, stronger
integrity constraint, the degenerate decomposition.
More generally, the theory demonstrates the importance
of using the union operation in database design and of
allowing different schemata on the operands of a union.
Techniques based on the union lead to a method for
solving the problem of membership of a decomposition in
the closure of a given set of functional dependencies
and decompositions. The concept of antiroot is
introduced as a tool for describing families of
decompositions, and its fundamental importance for
database design is indicated.",
acknowledgement = ack-nhfb,
annote = "A general study is made of two basic integrity
constrains, functional and multivalued dependencies,
via an equivalent concept: decompositions.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; decomposition; functional
dependency; integrity constraint; multivalued
dependency; relational database",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases}",
}
@Article{Hammer:1980:RMS,
author = "Michael Hammer and David Shipman",
title = "Reliability Mechanisms for {SDD-1}: a System for
Distributed Databases",
journal = j-TODS,
volume = "5",
number = "4",
pages = "431--466",
month = dec,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-4/p431-hammer/p431-hammer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-4/p431-hammer/",
abstract = "This paper presents the reliability mechanisms of
SDD-1, a prototype distributed database system being
developed by the Computer Corporation of America.
Reliability algorithms in SDD-1 center around the
concept of the Reliable Network (RelNet). The RelNet is
a communications medium incorporating facilities for
site status monitoring, event timestamping, multiply
buffered message delivery, and the atomic control of
distributed transactions.\par
This paper is one of a series of companion papers on
SDD-1 [3, 4, 6, 13].",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "atomicity; data base systems; distributed databases;
recovery; reliability",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart}",
}
@Article{Schloer:1980:SSD,
author = "Jan Schl{\"o}er",
title = "Security of statistical databases: multidimensional
transformation",
journal = j-TODS,
volume = "5",
number = "4",
pages = "467--492",
month = dec,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1980-5-4/p467-schler/",
abstract = "Statistical evaluation of databases which contain
personal records may entail risks for the
confidentiality of the individual records. The risk has
increased with the availability of flexible interactive
evaluation programs which permit the use of trackers,
the most dangerous class of snooping tools known. A
class of trackers, called union trackers, is described.
They permit reconstruction of the entire database
without supplementary knowledge and include the general
tracker recently described as a special case. For many
real statistical databases the overwhelming majority of
definable sets of records will form trackers. For such
databases a random search for a tracker is likely to
succeed rapidly. Individual trackers are redefined and
counted and their cardinalities are investigated. If
there are $n$ records in the database, then most
individual trackers employ innocent cardinalities near
$ n / 3 $, making them difficult to detect. Disclosure
with trackers usually requires little effort per
retrieved data element.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; database security; security;
statistical database; tracker",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Database Management
--- Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
xxtitle = "Disclosure from Statistical Databases: Quantitative
Aspects of Trackers",
}
@Article{Herot:1980:SMD,
author = "Christopher F. Herot",
title = "Spatial Management of Data",
journal = j-TODS,
volume = "5",
number = "4",
pages = "493--513",
month = dec,
year = "1980",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
Graphics/imager/imager.80.bib;
Graphics/siggraph/80.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1980-5-4/p493-herot/p493-herot.pdf;
http://www.acm.org/pubs/citations/journals/tods/1980-5-4/p493-herot/",
abstract = "Spatial data management is a technique for organizing
and retrieving information by positioning it in a
graphical data space (GDS). This graphical data space
is viewed through a color raster-scan display which
enables users to traverse the GDS surface or zoom into
the image to obtain greater detail. In contrast to
conventional database management systems, in which
users access data by asking questions in a formal query
language, a spatial data management system (SDMS)
presents the information graphically in a form that
seems to encourage browsing and to require less prior
knowledge of the contents and organization of the
database.\par
This paper presents an overview of the SDMS concept and
describes its implementation in a prototype system for
retrieving information from both a symbolic database
management system and an optical videodisk.",
acknowledgement = ack-nhfb,
annote = "Organizing and retrieving information by positioning
it in a graphical data space viewed through a color
display. An overview of the SDMS concept and describes
its implementation in a prototype system.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer graphics; database query languages;
graphical/programming language, query language,
Man-Machine Communications interaction, data base
systems; graphics languages; man-machine interaction",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Spatial databases
and GIS}; Information Systems --- Database Management
--- Languages (H.2.3): {\bf Query languages};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}",
}
@Article{Zaniolo:1981:DRD,
author = "Carlo Zaniolo and Michel A. Melkanoff",
title = "On the Design of Relational Database Schemata",
journal = j-TODS,
volume = "6",
number = "1",
pages = "1--47",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15 (68H05)",
MRnumber = "82b:68019",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p1-zaniolo/p1-zaniolo.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p1-zaniolo/",
abstract = "The purpose of this paper is to present a new approach
to the conceptual design of relational databases based
on the complete relatability conditions (CRCs).\par
It is shown that current database design methodology
based upon the elimination of anomalies is not
adequate. In contradistinction, the CRCs are shown to
provide a powerful criticism for decomposition. A
decomposition algorithm is presented which (1) permits
decomposition of complex relations into simple,
well-defined primitives, (2) preserves all the original
information, and (3) minimizes redundancy.\par
The paper gives a complete derivation of the CRCs,
beginning with a unified treatment of functional and
multivalued dependencies, and introduces the concept of
elementary functional dependencies and multiple
elementary multivalued dependencies. Admissibility of
covers and validation of results are also discussed,
and it is shown how these concepts may be used to
improve the design of 3NF schemata. Finally, a
convenient graphical representation is proposed, and
several examples are described in detail to illustrate
the method.",
acknowledgement = ack-nhfb,
annote = "The conceptual design of relational databases based on
the complete reliability conditions (CRCs). A unified
treatment of functional and multivalued dependencies.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; decomposition; functional
dependencies; minimal covers; multivalued dependencies;
relational databases; schema design",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Schema and subschema}",
}
@Article{Lien:1981:HSR,
author = "Y. Edmund Lien",
title = "Hierarchical Schemata for Relational Databases",
journal = j-TODS,
volume = "6",
number = "1",
pages = "48--69",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15 (68H05)",
MRnumber = "82b:68015",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p48-lien/p48-lien.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p48-lien/",
abstract = "Most database design methods for the relational model
produce a flat database, that is, a family of relations
with no explicit interrelational connections. The user
of a flat database is likely to be unaware of certain
interrelational semantics. In contrast, the
entity-relationship model provides schema graphs as a
description of the database, as well as for navigating
the database. Nevertheless, the user of an
entity-relationship database may still commit semantic
errors, such as performing a lossy join. This paper
proposes a nonflat, or hierarchical, view of relational
databases. Relations are grouped together to form {\em
relation hierarchies\/} in which lossless joins are
explicitly shown whereas lossy joins are excluded.
Relation hierarchies resemble the schema graphs in the
entity-relationship model.\par
An approach to the design of relation hierarchies is
outlined in the context of data dependencies and
relational decomposition. The approach consists of two
steps; each is described as an algorithm. Algorithm DEC
decomposes a given universal relation according to a
given set of data dependencies and produces a set of
nondecomposable relation schemes. This algorithm
differs from its predecessors in that it produces no
redundant relation schemes. Algorithm RH further
structures the relation schemes produced by Algorithm
DEC into a hierarchical schema. These algorithms can be
useful software tools for database designers.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database design; lossless join;
multivalued dependency; relation normalization",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Schema and subschema}",
}
@Article{Chamberlin:1981:SRT,
author = "D. D. Chamberlin and M. M. Astrahan and W. F. King and
R. A. Lorie and J. W. Mehl and T. G. Price and M.
Schkolnick and P. Griffiths Selinger and D. R. Slutz
and B. W. Wade and R. A. Yost",
title = "Support for Repetitive Transactions and Ad Hoc Queries
in {System R}",
journal = j-TODS,
volume = "6",
number = "1",
pages = "70--94",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: IBM Research Report
RJ2551(33151), May. 1979.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p70-chamberlin/p70-chamberlin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p70-chamberlin/",
abstract = "System R supports a high-level relational user
language called SQL which may be used by ad hoc users
at terminals or as an embedded data sublanguage in PL/I
or COBOL. Host-language programs with embedded SQL
statements are processed by the System R precompiler
which replaces the SQL statements by calls to a
machine-language access module. The precompilation
approach removes much of the work of parsing, name
binding, and access path selection from the path of a
running program, enabling highly efficient support for
repetitive transactions. Ad hoc queries are processed
by a similar approach of name binding and access path
selection which takes place on-line when the query is
specified. By providing a flexible spectrum of binding
times, System R permits transaction-oriented programs
and ad hoc query users to share a database without loss
of efficiency.\par
System R is an experimental database management system
designed and built by members of the IBM San Jose
Research Laboratory as part of a research program on
the relational model of data. This paper describes the
architecture of System R, and gives some preliminary
measurements of system performance in both the ad hoc
query and the ``canned program'' environments.",
acknowledgement = ack-nhfb,
annote = "Embedded SQL statements are processed by the System R
precompiler enabling highly efficient support for
repetitive transactions. Ad hoc query is specified. By
providing a flexible spectrum of binding times. System
R permits transaction-oriented programs and ad hoc
query users to share a database without loss of
efficiency.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compilation; data base systems, TODS ad-hoc relation
database IBM San Jose; performance measurements; query
languages; relational database systems; transaction
processing",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf System R}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Schlorer:1981:SSD,
author = "Jan Schl{\"o}rer",
title = "Security of Statistical Databases: Multidimensional
Transformation",
journal = j-TODS,
volume = "6",
number = "1",
pages = "95--112",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15",
MRnumber = "82b:68018",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p95-schlorer/p95-schlorer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p95-schlorer/",
abstract = "The concept of multidimensional transformation of
statistical databases is described. A given set of
statistical output may be compatible with more than one
statistical database. A transformed database $ D' $ is
a database which (1) differs from the original database
$D$ in its record content, for (2) produces, within
certain limits, the same statistical output as the
original database. For a transformable database $D$
there are two options: One may physically transform $D$
into a suitable database $ D' $, or one may release
only that output which will not permit the users to
decide whether it comes from $D$ or $ D' $. The second
way is, of course, the easier one. Basic structural
requirements for transformable statistical databases
are investigated. Advantages, drawbacks, and open
questions are discussed.",
acknowledgement = ack-nhfb,
annote = "A transformed database differs from the original
database in its record content but produces within
certain limits the same statistical output.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "confidentiality; data base systems; data processing
--- security of data; database; database security;
matrices; security; statistical database",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}",
}
@Article{Chin:1981:SDD,
author = "Francis Y. Chin and Gultekin {\"O}zsoyo{\u{g}}lu",
title = "Statistical Database Design",
journal = j-TODS,
volume = "6",
number = "1",
pages = "113--139",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p113-chin/p113-chin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p113-chin/",
abstract = "The security problem of a statistical database is to
limit the use of the database so that no sequence of
statistical queries is sufficient to deduce
confidential or private information. In this paper it
is suggested that the problem be investigated at the
conceptual data model level. The design of a
statistical database should utilize a statistical
security management facility to enforce the security
constraints at the conceptual model level. Information
revealed to users is well defined in the sense that it
can at most be reduced to nondecomposable information
involving a group of individuals. In addition, the
design also takes into consideration means of storing
the query information for auditing purposes, changes in
the database, users' knowledge, and some security
measures.",
acknowledgement = ack-nhfb,
annote = "Limit the use of the database so that no sequence of
statistical queries is sufficient to deduce
confidential information at the conceptual data model
level.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromisability; conceptual databases model; data
base systems; data processing --- security of data;
database design; protection; security; statistical
database",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}",
}
@Article{Shipman:1981:FDM,
author = "David W. Shipman",
title = "The Functional Data Model and the Data Language
{DAPLEX}",
journal = j-TODS,
volume = "6",
number = "1",
pages = "140--173",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/bibdb.bib;
Database/Graefe.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/Functional.bib; Misc/is.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p140-shipman/p140-shipman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p140-shipman/",
abstract = "DAPLEX is a database language which incorporates:
\par
a formulation of data in terms of entities;\par
a functional representation for both actual and virtual
data relationships;\par
a rich collection of language constructs for expressing
entity selection criteria;\par
a notion of subtype/supertype relationships among
entity types.\par
This paper presents and motivates the DAPLEX language
and the underlying data model on which it is based.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data base systems;
database; functional data model; language",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf DAPLEX}; Information Systems
--- Database Management --- Languages (H.2.3)",
}
@Article{Rosenberg:1981:TSO,
author = "Arnold L. Rosenberg and Lawrence Snyder",
title = "Time- and Space-Optimality in {B-Trees}",
journal = j-TODS,
volume = "6",
number = "1",
pages = "174--193",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15 (68E10)",
MRnumber = "82m:68048",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p174-rosenberg/p174-rosenberg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p174-rosenberg/",
abstract = "A B-tree is {\em compact\/} if it is minimal in number
of nodes, hence has optimal space utilization, among
equally capacious B-trees of the same order. The space
utilization of compact B-trees is analyzed and compared
with that of noncompact B-trees and with
(node)-visit-optimal B-trees, which minimize the
expected number of nodes visited per key access.
Compact B-trees can be as much as a {\em factor\/} of
2.5 more space efficient than visit-optimal B-trees;
and the node-visit cost of a compact tree is never more
than 1 + the node-visit cost of an optimal tree. The
utility of initializing a B-tree to be compact (which
initialization can be done in time linear in the number
of keys if the keys are presorted) is demonstrated by
comparing the space utilization of a compact tree that
has been augmented by random insertions with that of a
tree that has been grown entirely by random insertions.
Even after increasing the number of keys by a modest
amount, the effects of compact initialization are still
felt. Once the tree has grown so large that these
effects are no longer discernible, the tree can be
expeditiously compacted in place using an algorithm
presented here; and the benefits of compactness
resume.",
acknowledgement = ack-nhfb,
annote = "A Btree is compact if it is minimal in number of
nodes. Compact Btree initialization can be done in time
linear in the number of keys if the keys are presorted.
Study indicates that space-optimal trees are nearly
time optimal, but time-optimal trees are nearly space
pessimal.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "2,3-tree; B-tree; bushy B-tree; compact B-tree; data
processing; node-visit cost; space utilization",
subject = "Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Trees}",
}
@Article{Scholl:1981:NFO,
author = "Michel Scholl",
title = "New File Organizations Based on Dynamic Hashing",
journal = j-TODS,
volume = "6",
number = "1",
pages = "194--211",
month = mar,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15",
MRnumber = "82c:68016",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-1/p194-scholl/p194-scholl.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-1/p194-scholl/",
abstract = "New file organizations based on hashing and suitable
for data whose volume may vary rapidly recently
appeared in the literature. In the three schemes which
have been independently proposed, rehashing is avoided,
storage space is dynamically adjusted to the number of
records actually stored, and there are no overflow
records. Two of these techniques employ an index to the
data file. Retrieval is fast and storage utilization is
low.\par
In order to increase storage utilization, we introduce
two schemes based on a similar idea and analyze the
performance of the second scheme. Both techniques use
an index of much smaller size. In both schemes,
overflow records are accepted. The price which has to
be paid for the improvement in storage utilization is a
slight access cost degradation.",
acknowledgement = ack-nhfb,
annote = "In the three schemes which proposed, rehashing is
avoided, storage space is dynamically adjusted to the
number of records actually stored, and there are no
overflow records. Two of these techniques employ an
index to the data file.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; data structure; dynamic hashing; file
organization; hashing; linear splitting",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Kung:1981:OMC,
author = "H. T. Kung and John T. Robinson",
title = "On Optimistic Methods for Concurrency Control",
journal = j-TODS,
volume = "6",
number = "2",
pages = "213--226",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Compiler/garbage.collection.bib;
Compiler/Heaps.bib; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/misc.1.bib; Misc/real.time.bib;
Object/Nierstrasz.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p213-kung/p213-kung.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p213-kung/",
abstract = "Most current approaches to concurrency control in
database systems rely on locking of data objects as a
control mechanism. In this paper, two families of
nonlocking concurrency controls are presented. The
methods used are ``optimistic'' in the sense that they
rely mainly on transaction backup as a control
mechanism, ``hoping'' that conflicts between
transactions will not occur. Applications for which
these methods should be more efficient than locking are
discussed.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency controls; data base systems, concurrency
other; databases; transaction processing",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}",
}
@Article{Boral:1981:PAS,
author = "Haran Boral and David J. DeWitt",
title = "Processor Allocation Strategies for Multiprocessor
Database Machines",
journal = j-TODS,
volume = "6",
number = "2",
pages = "227--254",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p227-boral/p227-boral.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p227-boral/",
abstract = "In this paper four alternative strategies for
assigning processors to queries in multiprocessor
database machines are described and evaluated. The
results demonstrate that SIMD database machines are
indeed a poor design when their performance is compared
with that of the three MIMD strategies presented.
\par
Also introduced is the application of data-flow machine
techniques to the processing of relational algebra
queries. A strategy that employs data-flow techniques
is shown to be superior to the other strategies
described by several experiments. Furthermore, if the
data-flow query processing strategy is employed, the
results indicate that a two-level storage hierarchy (in
which relations are paged between a shared data cache
and mass storage) does not have a significant impact on
performance.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative processors; back-end computers; computer
architecture; data base systems, Direct TODS; data-flow
computers; database machines; database management;
parallel processors; processor scheduling",
subject = "Information Systems --- Database Management ---
Database Machines (H.2.6); Information Systems ---
Database Management (H.2)",
}
@Article{Su:1981:TDT,
author = "Stanley Y. W. Su and Herman Lam and Der Her Lo",
title = "Transformation of Data Traversals and Operations in
Application Programs to Account for Semantic Changes of
Databases",
journal = j-TODS,
volume = "6",
number = "2",
pages = "255--294",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p255-su/p255-su.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p255-su/",
abstract = "This paper addresses the problem of application
program conversion to account for changes in database
semantics that result in changes in the schema and
database contents. With the observation that the
existing data models can be viewed as alternative ways
of modeling the same database semantics, a methodology
of application program analysis and conversion based on
an existing-DBMS-model-and schema-independent
representation of both the database and programs is
presented. In this methodology, the source and target
databases are described in terms of the association
types of a semantic association model. The structural
properties, the integrity constraints, and the
operational characteristics (storage operation
behaviors) of the association types are more explicitly
defined to reveal the semantics that is generally
hidden in application programs. The explicit
descriptions of the source and target databases are
used as the basis for program analysis and conversion.
Application programs are described in terms of a small
number of ``access patterns'' which define the data
traversals and operations of the programs. In addition
to the methodology, this paper (1) describes a model of
a generalized application program conversion system
that serves as a framework for research, (2) presents
an analysis of access patterns that serve as the
primitives for program description, (3) delineates some
meaningful semantic changes to databases and their
corresponding transformation rules for program
conversion, (4) illustrates the application of these
rules to two different approaches to program conversion
problems, and (5) reports on the development effort
undertaken at the University of Florida.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access pattern; application program conversion; data
base systems; database changes; semantic data model;
transformation rules",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8); Information Systems ---
Database Management --- Physical Design (H.2.2): {\bf
Access methods}; Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Data
models}",
}
@Article{Clemons:1981:DES,
author = "Eric K. Clemons",
title = "Design of an External Schema Facility to Define and
Process Recursive Structures",
journal = j-TODS,
volume = "6",
number = "2",
pages = "295--311",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p295-clemons/p295-clemons.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p295-clemons/",
abstract = "The role of the external schema is to support user
views of data and thus to provide programmers with
easier data access. This author believes that an
external schema facility is best based on hierarchies,
both simple and recursive. After a brief introduction
to an external schema facility to support simple
hierarchical user views, the requirements for a
facility for recursive hierarchies are listed and the
necessary extensions to the external schema definition
language are offered.\par
Functions that must be provided for generality in
definition are node specification and node control.
Tree traversal functions must be provided for
processing. Definitions of each and examples of use are
presented.",
acknowledgement = ack-nhfb,
annote = "[Ahad,Yao,Choi87] A.2.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "ANSI SPARC architectures; data base systems; external
schemata; recursive data structures; user views",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Schema and subschema}",
}
@Article{Davida:1981:DES,
author = "George I. Davida and David L. Wells and John B. Kam",
title = "A Database Encryption System with Subkeys",
journal = j-TODS,
volume = "6",
number = "2",
pages = "312--328",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15",
MRnumber = "82f:68020",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p312-davida/p312-davida.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p312-davida/",
abstract = "A new cryptosystem that is suitable for database
encryption is presented. The system has the important
property of having subkeys that allow the encryption
and decryption of fields within a record. The system is
based on the Chinese Remainder Theorem.",
acknowledgement = ack-nhfb,
annote = "Subkeys allow the encryption and decryption of fields
within a record. The system is based on the Chinese
Remainder Theorem.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "codes, symbolic; data base systems; data security;
databases; decryption; encryption; subkeys",
subject = "Data --- Data Encryption (E.3)",
}
@Article{Ling:1981:ITN,
author = "Tok Wang Ling and Frank W. Tompa and Tiko Kameda",
title = "An Improved Third Normal Form for Relational
Databases",
journal = j-TODS,
volume = "6",
number = "2",
pages = "329--346",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15",
MRnumber = "82f:68024",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p329-ling/p329-ling.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p329-ling/",
abstract = "In this paper, we show that some Codd third normal
form relations may contain ``superfluous'' attributes
because the definitions of transitive dependency and
prime attribute are inadequate when applied to sets of
relations. To correct this, an improved third normal
form is defined and an algorithm is given to construct
a set of relations from a given set of functional
dependencies in such a way that the superfluous
attributes are guaranteed to be removed. This new
normal form is compared with other existing definitions
of third normal form, and the deletion normalization
method proposed is shown to subsume the decomposition
method of normalization.",
acknowledgement = ack-nhfb,
annote = "An improved third normal form is defined and an
algorithm is given to construct a set of relations from
a given set of functional dependencies in such a way
that the superfluous attributes are guaranteed to be
removed.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "covering; data base systems; database design;
functional dependency; normalization; prime attribute;
reconstructibility; relational schema; third normal
form; transitive dependency",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Schema and subschema}",
}
@Article{McLean:1981:CSC,
author = "Gordon {McLean, Jr.}",
title = "Comments on {SDD-1} Concurrency Control Mechanisms",
journal = j-TODS,
volume = "6",
number = "2",
pages = "347--350",
month = jun,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-2/p347-mclean/p347-mclean.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-2/p347-mclean/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}",
}
@Article{Hammer:1981:DDS,
author = "Michael Hammer and Dennis Mc Leod",
title = "Database Description with {SDM}: a Semantic Database
Model",
journal = j-TODS,
volume = "6",
number = "3",
pages = "351--386",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/bibdb.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Reprinted in \cite{Stonebraker:1988:RDS}. Also
published in \cite{Zdonik:1990:ROO}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p351-hammer/p351-hammer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p351-hammer/",
abstract = "SDM is a high-level semantics-based database
description and structuring formalism (database model)
for databases. This database model is designed to
capture more of the meaning of an application
environment than is possible with contemporary database
models. An SDM specification describes a database in
terms of the kinds of entities that exist in the
application environment, the classifications and
groupings of those entities, and the structural
interconnections among them. SDM provides a collection
of high-level modeling primitives to capture the
semantics of an application environment. By
accommodating derived information in a database
structural specification, SDM allows the same
information to be viewed in several ways; this makes it
possible to directly accommodate the variety of needs
and processing requirements typically present in
database applications. The design of the present SDM is
based on our experience in using a preliminary version
of it.\par
SDM is designed to enhance the effectiveness and
usability of database systems. An SDM database
description can serve as a formal specification and
documentation tool for a database; it can provide a
basis for supporting a variety of powerful user
interface facilities, it can serve as a conceptual
database model in the database design process; and, it
can be used as the database model for a new kind of
database management system.",
acknowledgement = ack-nhfb,
annote = "SDM is a high-level semantics-based database model, to
capture the meaning of an application environment. One
of the papers usually referred to when discussing
semantic data models. Describes a model which permits a
lot of flexibility and expressiveness, and is
consequently difficult to implement. Advantage is that
it can be used as a specification and documentation
tool. Good introduction, giving an overview of (some?,
most?, all?) problems in semantic data models. The
section describing SDM DDL is a bit too detailed (one
needs to pick up the essential concepts like
subclassing, and redundancy in model (which may be
necessary to make the model easier to use)). Some
discussion of inheritance is also present. Nothing much
is said in the final discussion. Reasonable paper. To
benefit, one needs to be careful not to get lost in the
details. A detailed description of the semantic data
model.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database definition; database
management; database modeling; database models;
database semantics; logical database design",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}",
}
@Article{Fagin:1981:NFR,
author = "Ronald Fagin",
title = "A Normal Form for Relational Databases That is Based
on Domains and Keys",
journal = j-TODS,
volume = "6",
number = "3",
pages = "387--415",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Compiler/prog.lang.theory.bib;
Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p387-fagin/p387-fagin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p387-fagin/",
abstract = "The new normal form for relational databases, called
domain-key normal form (DK\slash NF), is defined. Also,
formal definitions of insertion anomaly and deletion
anomaly are presented. It is shown that a schema is in
DK\slash NF if and only if it has no insertion or
deletion anomalies. Unlike previously defined normal
forms, DK\slash NF is not defined in terms of
traditional dependencies (functional, multivalued, or
join). Instead, it is defined in terms of the more
primitive concepts of domain and key, along with the
general concept of a ``constraint''. It is considered
how the definitions of traditional normal forms might
be modified by taking into consideration, for the first
time, the combinatorial consequences of bounded domain
sizes. It is shown that after this modification, these
traditional normal forms are all implied by DK\slash
NF. In particular, if all domains are infinite, then
these traditional normal forms are all implied by
DK\slash NF.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "anomaly; complexity; data base systems; database
design; DK/NF; domain-key normal form; functional
dependency; join dependency; multivalued dependency;
normalization; relational database",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Normal forms}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Relational databases}",
}
@Article{Hong:1981:AHS,
author = "Y. C. Hong and Stanley Y. W. Su",
title = "Associative Hardware and Software Techniques for
Integrity Control",
journal = j-TODS,
volume = "6",
number = "3",
pages = "416--440",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p416-hong/p416-hong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p416-hong/",
abstract = "This paper presents the integrity control mechanism of
the associative processing system, CASSM. The mechanism
takes advantage of the associative techniques, such as
content and context addressing, tagging and marking
data, parallel processing, automatic triggering of
integrity control procedures, etc., for integrity
control and as a result offers three significant
advantages: (1) The problem of staging data in a main
memory for integrity checking can be eliminated because
database storage operations are verified at the place
where the data are stored. (2) The backout or merging
procedures are relatively easy and inexpensive in the
associative system because modified copies can be
substituted for the originals or may be discarded by
merely changing their associated tags. (3) The database
management system software is simplified because
database integrity functions are handled by the
associative processing system to which a mainframe
computer is a front-end computer.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "assertion and trigger; associative techniques;
cellular-logic devices; data base systems; database
integrity; database management; integrity control;
integrity control, SYWSu hardware support relational
database machine TODS",
subject = "Information Systems --- Database Management ---
General (H.2.0): {\bf Security, integrity, and
protection**}",
}
@Article{March:1981:FMS,
author = "Salvatore T. March and Dennis G. Severance and Michael
Wilens",
title = "Frame Memory: a Storage Architecture to Support Rapid
Design and Implementation of Efficient Databases",
journal = j-TODS,
volume = "6",
number = "3",
pages = "441--463",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p441-march/p441-march.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p441-march/",
abstract = "Frame memory is a virtual view of secondary storage
that can be implemented with reasonable overhead to
support database record storage and accessing
requirements. Frame memory is designed so that its
operating characteristics can be easily manipulated by
either designers or design algorithms, while
performance effects of such changes can be accurately
predicted. Automated design procedures exist to
generate and evaluate alternative database designs
built upon frame memory, and the existence of these
procedures establishes frames as an attractive memory
management architecture for future database management
systems.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "analytic modeling; data base systems; database design
system; database machine; hardware support; TODS;
virtual secondary storage",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2); Software ---
Operating Systems --- Storage Management (D.4.2): {\bf
Secondary storage}",
}
@Article{vandeRiet:1981:HLP,
author = "Reind P. {van de Riet} and Anthony I. Wasserman and
Martin L. Kersten and Wiebren {de Jonge}",
title = "High-Level Programming Features for Improving the
Efficiency of a Relational Database System",
journal = j-TODS,
volume = "6",
number = "3",
pages = "464--485",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: UCSF, Lab. of Med. Inf. Science,
Tech. Rpt. 44, Feb. 1980.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p464-van_de_riet/p464-van_de_riet.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p464-van_de_riet/",
abstract = "This paper discusses some high-level language
programming constructs that can be used to manipulate
the relations of a relational database system
efficiently. Three different constructs are described:
(1) tuple identifiers that directly reference tuples of
a relation; (2) cursors that may iterate over the
tuples of a relation; and (3) markings, a form of
temporary relation consisting of a set of tuple
identifiers. In each case, attention is given to
syntactic, semantic, and implementation considerations.
\par
The use of these features is first presented within the
context of the programming language PLAIN, and it is
then shown how these features could be used more
generally to provide database manipulation capabilities
in a high-level programming language. Consideration is
also given to issues of programming methodology, with
an important goal being the achievement of a balance
between the enforcement of good programming practices
and the ability to write efficient programs.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "markings; PLAIN; programming languages; programming
methodology; relational algebra; relational database
management",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Database (persistent)
programming languages}",
}
@Article{Culik:1981:DMT,
author = "K. {Culik II} and Th. Ottmann and D. Wood",
title = "Dense multiway trees",
journal = j-TODS,
volume = "6",
number = "3",
pages = "486--512",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15 (05C05)",
MRnumber = "82m:68038",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p486-culic/",
abstract = "B-trees of order $m$ are a ``balanced'' class of
$m$-ary trees, which have applications in the areas of
file organization. In fact, they have been the only
choice when balanced multiway trees are required.
Although they have very simple insertion and deletion
algorithms, their storage utilization, that is, the
number of keys per page or node, is at worst 50
percent. In the present paper we investigate a new
class of balanced $m$-ary trees, the dense multiway
trees, and compare their storage utilization with that
of B-trees of order $m$. \par
Surprisingly, we are able to demonstrate that weakly
dense multiway trees have an $ (l o g_2 N) $ insertion
algorithm. We also show that inserting $ m h - 1 $ keys
in ascending order into an initially empty dense
multiway tree yields the complete $m$-ary tree of
height $h$, and that at intermediate steps in the
insertion sequence the intermediate trees can also be
considered to be as dense as possible. Furthermore, an
analysis of the limiting dynamic behavior of the dense
$m$-ary trees under insertion shows that the average
storage utilization tends to 1; that is, the trees
become as dense as possible. This motivates the use of
the term ``dense.''",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "B-trees; balanced trees; dense trees; multiway trees;
search trees; storage utilization",
subject = "Data --- Data Structures (E.1): {\bf Trees}",
}
@Article{Comer:1981:AHF,
author = "Douglas Comer",
title = "Analysis of a Heuristic for Full Trie Minimization",
journal = j-TODS,
volume = "6",
number = "3",
pages = "513--537",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-3/p513-comer/p513-comer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-3/p513-comer/",
abstract = "A trie is a distributed-key search tree in which
records from a file correspond to leaves in the tree.
Retrieval consists of following a path from one root to
a leaf, where the choice of edge at each node is
determined by attribute values of the key. For full
tries, those in which all leaves lie at the same depth,
the problem of finding an ordering of attributes which
yields a minimum size trie is NP-complete.\par
This paper considers a ``greedy'' heuristic for
constructing low-cost tries. It presents simulation
experiments which show that the greedy method tends to
produce tries with small size, and analysis leading to
a worst case bound on approximations produced by the
heuristic. It also shows a class of files for which the
greedy method may perform badly, producing tries of
high cost.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; heuristic; trie index; trie size",
subject = "Computing Methodologies --- Artificial Intelligence
--- Problem Solving, Control Methods, and Search
(I.2.8): {\bf Heuristic methods}",
}
@Article{Kent:1981:CAU,
author = "W. Kent",
title = "Consequences of Assuming a Universal Relation",
journal = j-TODS,
volume = "6",
number = "4",
pages = "539--556",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See remark \cite{Ullman:1983:KCA}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p539-kent/p539-kent.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p539-kent/",
abstract = "Although central to the current direction of
dependency theory, the assumption of a universal
relation is incompatible with some aspects of
relational database theory and practice. Furthermore,
the universal relation is itself ill defined in some
important ways. And, under the universal relation
assumption, the decomposition approach to database
design becomes virtually indistinguishable from the
synthetic approach.",
acknowledgement = ack-nhfb,
annote = "The assumption of a universal relation is incompatible
with some aspects of relational database theory and
practice. Under the universal relation assumption, the
decomposition approach to database design becomes
virtually indistinguishable from the synthetic
approach.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database design; dependency theory;
rational database; relational theory; universal
relation",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Models and Principles ---
Systems and Information Theory (H.1.1); Information
Systems --- Database Management --- Logical Design
(H.2.1)",
}
@Article{Bancilhon:1981:USR,
author = "F. B. Bancilhon and N. Spyratos",
title = "Update Semantics of Relational Views",
journal = j-TODS,
volume = "6",
number = "4",
pages = "557--575",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See comment \cite{Keller:1987:CBS}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p557-bancilhon/p557-bancilhon.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p557-bancilhon/",
abstract = "A database view is a portion of the data structured in
a way suitable to a specific application. Updates on
views must be translated into updates on the underlying
database. This paper studies the translation process in
the relational model.\par
The procedure is as follows: first, a ``complete'' set
of updates is defined such that\par
together with every update the set contains a
``return'' update, that is, one that brings the view
back to the original state;\par
given two updates in the set, their composition is also
in the set.\par
To translate a complete set, we define a mapping called
a ``translator,'' that associates with each view update
a unique database update called a ``translation.'' The
constraint on a translation is to take the database to
a state mapping onto the updated view. The constraint
on the translator is to be a morphism.\par
We propose a method for defining translators. Together
with the user-defined view, we define a
``complementary'' view such that the database could be
computed from the view and its complement. We show that
a view can have many different complements and that the
choice of a complement determines an update policy.
Thus, we fix a view complement and we define the
translation of a given view update in such a way that
the complement remains invariant (``translation under
constant complement''). The main result of the paper
states that, given a complete set $U$ of view updates,
$U$ has a translator if and only if $U$ is translatable
under constant complement.",
acknowledgement = ack-nhfb,
annote = "A mapping called a ``translator'', associates with
each view update a unique database update. A method for
defining translators with the user-defined view, define
a ``complementary'' view such that the database could
be computed from the view and its complement. We define
the translation of a given view update in such a way
that the complement remains invariant. Aplies to
Universal relations.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual model; data base systems; data model; data
semantics; database view; relation; relational model
database; update translation; view updating",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Theory of
Computation --- Logics and Meanings of Programs ---
Semantics of Programming Languages (F.3.2)",
}
@Article{Baroody:1981:OOA,
author = "A. James {Baroody, Jr.} and David J. DeWitt",
title = "An Object-Oriented Approach to Database System
Implementation",
journal = j-TODS,
volume = "6",
number = "4",
pages = "576--601",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Object/Nierstrasz.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p576-baroody/p576-baroody.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p576-baroody/",
abstract = "This paper examines object-oriented programming as an
implementation technique for database systems. The
object-oriented approach encapsulates the
representations of database entities and relationships
with the procedures that manipulate them. To achieve
this, we first define abstractions of the modeling
constructs of the data model that describe their common
properties and behavior. Then we represent the entity
types and relationship types in the conceptual schema
and the internal schema by objects that are instances
of these abstractions. The generic procedures (data
manipulation routines) that comprise the user interface
can now be implemented as calls to the procedures
associated with these objects.\par
A generic procedure model of database implementation
techniques is presented and discussed. Several current
database system implementation techniques are
illustrated as examples of this model, followed by a
critical analysis of our implementation technique based
on the use of objects. We demonstrate that the
object-oriented approach has advantages of data
independence, run-time efficiency due to eliminating
access to system descriptors, and support for low-level
views.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming, olit-db casais; data base
systems; data independence; data manipulation routines;
database systems; high-level languages; object-oriented
programming; procedural binding",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Object-oriented databases};
Computer Systems Organization --- Computer System
Implementation (C.5); Information Systems --- Database
Management --- Languages (H.2.3)",
}
@Article{Bernstein:1981:QPS,
author = "Philip A. Bernstein and Nathan Goodman and Eugene Wong
and Christopher L. Reeve and James B. {Rothnie, Jr.}",
title = "Query Processing in a System for Distributed Databases
({SDD-1})",
journal = j-TODS,
volume = "6",
number = "4",
pages = "602--625",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p602-bernstein/p602-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p602-bernstein/",
abstract = "This paper describes the techniques used to optimize
relational queries in the SDD-1 distributed database
system. Queries are submitted to SDD-1 in a high-level
procedural language called Datalanguage. Optimization
begins by translating each Datalanguage query into a
relational calculus form called an {\em envelope},
which is essentially an aggregate-free QUEL query. This
paper is primarily concerned with the optimization of
envelopes.\par
Envelopes are processed in two phases. The first phase
executes relational operations at various sites of the
distributed database in order to delimit a subset of
the database that contains all data relevant to the
envelope. This subset is called a {\em reduction\/} of
the database. The second phase transmits the reduction
to one designated site, and the query is executed
locally at that site.\par
The critical optimization problem is to perform the
reduction phase efficiently. Success depends on
designing a good repertoire of operators to use during
this phase, and an effective algorithm for deciding
which of these operators to use in processing a given
envelope against a given database. The principal
reduction operator that we employ is called a {\em
semijoin}. In this paper we define the semijoin
operator, explain why semijoin is an effective
reduction operator, and present an algorithm that
constructs a cost-effective program of semijoins, given
an envelope and a database.",
acknowledgement = ack-nhfb,
annote = "Techniques to optimize relational queries in the SDD-1
distributed database system. First phase executes
relational operations at various sites to delimit a
subset called a reduction. The second phase transmits
the reduction to one designated site. The principal
reduction operator, introduced here, is called a
semijoin.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- subroutines; data base
systems; distributed databases; query optimization;
query processing; query processing, TODS semijoins
semi-join join; relational databases; semijoins",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Distributed databases}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Welty:1981:HFC,
author = "Charles Welty and David W. Stemple",
title = "Human Factors Comparison of a Procedural and a
Nonprocedural Query Language",
journal = j-TODS,
volume = "6",
number = "4",
pages = "626--649",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p626-welty/p626-welty.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p626-welty/",
abstract = "Two experiments testing the ability of subjects to
write queries in two different query languages were
run. The two languages, SQL and TABLET, differ
primarily in their procedurality; both languages use
the relational data model, and their Halstead levels
are similar. Constructs in the languages which do not
affect their procedurality are identical. The two
languages were learned by the experimental subjects
almost exclusively from manuals presenting the same
examples and problems ordered identically for both
languages. The results of the experiments show that
subjects using the more procedural language wrote
difficult queries better than subjects using the less
procedural language. The results of the experiments are
also used to compare corresponding constructs in the
two languages and to recommend improvements for these
constructs.",
acknowledgement = ack-nhfb,
annote = "SQL and TABLET. The results show that subjects using
the more procedural language wrote difficult queries
better than subjects using the less procedural
language.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; database systems; human factors;
procedural and nonprocedural languages; query
languages",
subject = "Information Systems --- Models and Principles ---
User/Machine Systems (H.1.2): {\bf Human factors};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Systems (H.2.4)",
}
@Article{Lehman:1981:ELC,
author = "Philip L. Lehman and S. Bing Yao",
title = "Efficient Locking for Concurrent Operations on
{B-Trees}",
journal = j-TODS,
volume = "6",
number = "4",
pages = "650--670",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p650-lehman/p650-lehman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p650-lehman/",
abstract = "The B-tree and its variants have been found to be
highly useful (both theoretically and in practice) for
storing large amounts of information, especially on
secondary storage devices. We examine the problem of
overcoming the inherent difficulty of concurrent
operations on such structures, using a practical
storage model. A single additional ``link'' pointer in
each node allows a process to easily recover from tree
modifications performed by other concurrent processes.
Our solution compares favorably with earlier solutions
in that the locking scheme is simpler (no read-locks
are used) and only a (small) constant number of nodes
are locked by any update process at any given time. An
informal correctness proof for our system is given.",
acknowledgement = ack-nhfb,
annote = "A single additional `link' pointer in each node allows
a process to easily recover from tree modifications
performed by other concurrent processes. No read-locks
are used only a (small) constant number of nodes are
locked by any update process at any given time.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "B-tree; concurrenct algorithms; concurrency controls;
consistency; correctness; data processing; data
structures; database; index organizations; locking
protocols; multiway search trees",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}; Mathematics of
Computing --- Discrete Mathematics --- Graph Theory
(G.2.2): {\bf Trees}",
}
@Article{Larson:1981:AIS,
author = "Per-{\AA}ke Larson",
title = "Analysis of Index-Sequential Files with Overflow
Chaining",
journal = j-TODS,
volume = "6",
number = "4",
pages = "671--680",
month = dec,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68B15 (68H05)",
MRnumber = "82m:68044",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1981-6-4/p671-larson/p671-larson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1981-6-4/p671-larson/",
abstract = "The gradual performance deterioration caused by
deletions from and insertions into an index-sequential
file after loading is analyzed. The model developed
assumes that overflow records are handled by chaining.
Formulas for computing the expected number of overflow
records and the expected number of additional accesses
caused by the overflow records for both successful and
unsuccessful searches are derived.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "analysis of algorithms; analytic model; data
processing, TODS ISAM; file organization; file
structure; index sequential files; indexed sequential
access method; ISAM; overflow; overflow chaining;
overflow handling; performance analysis",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Information Systems --- Database
Management --- Physical Design (H.2.2): {\bf Access
methods}",
}
@Article{Comer:1981:EKD,
author = "D. Comer",
title = "Extended {K-d} Tree Database Organization: a Dynamic
Multiattribute File Corresponds to Leaves in the Tree",
journal = j-TODS,
volume = "6",
number = "3",
pages = "??--??",
month = sep,
year = "1981",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:49:00 1996",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
annote = "This paper considers a `greedy' heuristic for
constructing low-cost trees.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Zaniolo:1982:DRN,
author = "C. Zaniolo",
title = "Database Relations with Null Values",
journal = j-TODS,
volume = "1",
number = "1",
pages = "??--??",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:48:57 1996",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
annote = "a three-valued logic: TRUE, FALSE, UNKNOWN",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Katz:1982:DCD,
author = "R. H. Katz and E. Wong",
title = "Decompiling {CODASYL DML} into Relational Queries",
journal = j-TODS,
volume = "7",
number = "1",
pages = "1--23",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-1/p1-katz/p1-katz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-1/p1-katz/",
abstract = "A ``decompilation'' algorithm is developed to
transform a program written with the procedural
operations of CODASYL DML into one which interacts with
a relational system via a nonprocedural query
specification. An Access Path Model is introduced to
interpret the semantic accesses performed by the
program. Data flow analysis is used to determine how
FIND operations implement semantic accesses. A sequence
of these is mapped into a relational query and embedded
into the original program. The class of programs for
which the algorithm succeeds is characterized.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems; decompilation; semantic data
models",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Relational databases};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data manipulation languages
(DML)}; Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Heterogeneous
Databases (H.2.5): {\bf Program translation**}",
}
@Article{Zaniolo:1982:FAD,
author = "Carlo Zaniolo and Michel A. Melkanoff",
title = "A Formal Approach to the Definition and the Design of
Conceptual Schemata for Database Systems",
journal = j-TODS,
volume = "7",
number = "1",
pages = "24--59",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-1/p24-zaniolo/p24-zaniolo.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-1/p24-zaniolo/",
abstract = "A formal approach is proposed to the definition and
the design of conceptual database diagrams to be used
as conceptual schemata in a system featuring a
multilevel schema architecture, and as an aid for the
design of other forms of schemata. We consider E-R
(entity-relationship) diagrams, and we introduce a new
representation called {\em CAZ\/}-graphs. A rigorous
connection is established between these diagrams and
some formal constraints used to describe relationships
in the framework of the relational data model. These
include functional and multivalued dependencies of
database relations. The basis for our schemata is a
combined representation for two fundamental structures
underlying every relation: the first defined by its
minimal atomic decompositions, the second by its
elementary functional dependencies.\par
The interaction between these two structures is
explored, and we show that, jointly, they can represent
a wide spectrum of database relationships, of which the
well-known one-to-one, one-to-many, and many-to-many
associations constitute only a small subset. It is
suggested that a main objective in conceptual schema
design is to ensure a complete representation of these
two structures. A procedure is presented to design
schemata which obtain this objective while eliminating
redundancy. A simple correspondence between the
topological properties of these schemata and the
structure of multivalued dependencies of the original
relation is established. Various applications are
discussed and a number of illustrative examples are
given.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems, logical design TODS",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Data
models}; Information Systems --- Database Management
--- Logical Design (H.2.1): {\bf Schema and
subschema}",
}
@Article{Batory:1982:OFD,
author = "D. S. Batory",
title = "Optimal File Designs and Reorganization Points",
journal = j-TODS,
volume = "7",
number = "1",
pages = "60--81",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: University of Toronto,
TR-CSRG-110, 1980.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-1/p60-batory/p60-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-1/p60-batory/",
abstract = "A model for studying the combined problems of file
design and file reorganization is presented. New
modeling techniques for predicting the performance
evolution of files and for finding optimal
reorganization points for files are introduced.
Applications of the model to hash-based and
indexed-sequential files reveal important relationships
between initial loading factors and reorganization
frequency. A practical file design strategy, based on
these relationships, is proposed.",
acknowledgement = ack-nhfb,
annote = "Applications of the model to hash-based and
indexed-sequential files reveal important relationships
between initial loading factors and reorganization
frequency.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; file design; file reorganization",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Physical Design (H.2.2)",
}
@Article{Du:1982:DAC,
author = "H. C. Du and J. S. Sobolewski",
title = "Disk Allocation for {Cartesian} Product Files on
Multiple-Disk Systems",
journal = j-TODS,
volume = "7",
number = "1",
pages = "82--101",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-1/p82-du/p82-du.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-1/p82-du/",
abstract = "Cartesian product files have recently been shown to
exhibit attractive properties for partial match
queries. This paper considers the file allocation
problem for Cartesian product files, which can be
stated as follows: Given a $k$-attribute Cartesian
product file and an $m$-disk system, allocate buckets
among the $m$ disks in such a way that, for all
possible partial match queries, the concurrency of disk
accesses is maximized. The Disk Modulo (DM) allocation
method is described first, and it is shown to be strict
optimal under many conditions commonly occurring in
practice, including all possible partial match queries
when the number of disks is 2 or 3. It is also shown
that although it has good performance, the DM
allocation method is not strict optimal for all
possible partial match queries when the number of disks
is greater than 3. The General Disk Modulo (GDM)
allocation method is then described, and a sufficient
but not necessary condition for strict optimality of
the GDM method for all partial match queries and any
number of disks is then derived. Simulation studies
comparing the DM and random allocation methods in terms
of the average number of disk accesses, in response to
various classes of partial match queries, show the
former to be significantly more effective even when the
number of disks is greater than 3, that is, even in
cases where the DM method is not strict optimal. The
results that have been derived formally and shown by
simulation can be used for more effective design of
optimal file systems for partial match queries. When
considering multiple-disk systems with independent
access paths, it is important to ensure that similar
records are clustered into the same or similar buckets,
while similar buckets should be dispersed uniformly
among the disks.",
acknowledgement = ack-nhfb,
annote = "For partial match queries. Allocate buckets among the
m disks in such a way that, for all possible partial
match queries, the concurrency of disk accesses is
maximized.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Cartesian product files; data processing",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2); Information Systems ---
Information Storage and Retrieval --- Information
Storage (H.3.2): {\bf File organization}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}; Information Systems --- Database Management
--- Systems (H.2.4)",
}
@Article{Dahl:1982:DSD,
author = "Ver{\'o}nica Dahl",
title = "On Database Systems Development through Logic",
journal = j-TODS,
volume = "7",
number = "1",
pages = "102--123",
month = mar,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05 (03B99)",
MRnumber = "83f:68112",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-1/p102-dahl/p102-dahl.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-1/p102-dahl/",
abstract = "The use of logic as a single tool for formalizing and
implementing different aspects of database systems in a
uniform manner is discussed. The discussion focuses on
relational databases with deductive capabilities and
very high-level querying and defining features. The
computational interpretation of logic is briefly
reviewed, and then several pros and cons concerning the
description of data, programs, queries, and language
parser in terms of logic programs are examined. The
inadequacies are discussed, and it is shown that they
can be overcome by the introduction of convenient
extensions into logic programming. Finally, an
experimental database query system with a natural
language front end, implemented in PROLOG, is presented
as an illustration of these concepts. A description of
the latter from the user's point of view and a sample
consultation session in Spanish are included.",
acknowledgement = ack-nhfb,
annote = "The use of logic as a single tool for relational
databases with deductive capabilities and very
high-level querying and defining features. Inadequacies
are discussed, and overcome by extensions into logic
programming. An experimental database query system with
a natural language front end, implemented in PROLOG, is
presented.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems, TODS relational database; rational
database",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Theory of Computation --- Mathematical
Logic and Formal Languages --- Mathematical Logic
(F.4.1): {\bf Logic and constraint programming};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Relational databases}; Information Systems ---
Database Management --- Languages (H.2.3): {\bf
Prolog}",
}
@Article{Addis:1982:RBL,
author = "T. R. Addis",
title = "A Relation-Based Language Interpreter for a Content
Addressable File Store",
journal = j-TODS,
volume = "7",
number = "2",
pages = "125--163",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p125-addis/p125-addis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p125-addis/",
abstract = "The combination of the Content Addressable File Store
(CAFS \footnote{CAFS is a registered trademark of
International Computers Limited}) and an extension of
relational analysis is described. This combination
allows a simple and compact implementation of a
database query and update language (FIDL). The language
has one of the important properties of a ``natural''
language interface by using a ``world model'' derived
from the relational analysis. The interpreter (FLIN)
takes full advantage of the CAFS by employing a unique
database storage technique which results in a fast
response to both queries and updates.",
acknowledgement = ack-nhfb,
annote = "ICL CAFS is used.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer operating systems --- program Interpreters,
hardware support database machine CAFS TODS; content
addressing; data base systems",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Database Machines
(H.2.6)",
}
@Article{Buneman:1982:ITD,
author = "Peter Buneman and Robert E. Frankel and Rishiyur
Nikhil",
title = "An Implementation Technique for Database Query
Languages",
journal = j-TODS,
volume = "7",
number = "2",
pages = "164--186",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/Functional.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p164-buneman/p164-buneman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p164-buneman/",
abstract = "Structured query languages, such as those available
for relational databases, are becoming increasingly
desirable for all database management systems. Such
languages are applicative: there is no need for an
assignment or update statement. A new technique is
described that allows for the implementation of
applicative query languages against most commonly used
database systems. The technique involves ``lazy''
evaluation and has a number of advantages over existing
methods: it allows queries and functions of arbitrary
complexity to be constructed; it reduces the use of
secondary storage; it provides a simple control
structure through which interfaces to other programs
may be constructed; and the implementation, including
the database interface, is quite compact. Although the
technique is presented for a specific functional
programming system and for a CODASYL DBMS, it is
general and may be used for other query languages and
database systems.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "applicative programming; coroutines; database
interfaces; functional, data base systems; lazy
evaluation; query languages; TODS functional FQL
applicative programming lazy evaluation",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Software --- Programming Languages ---
Language Classifications (D.3.2): {\bf Applicative
(functional) languages}; Information Systems ---
Database Management --- Languages (H.2.3): {\bf Query
languages}",
}
@Article{Obermarck:1982:DDD,
author = "Ron Obermarck",
title = "Distributed Deadlock Detection Algorithm",
journal = j-TODS,
volume = "7",
number = "2",
pages = "187--208",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/misc.1.bib; Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p187-obermarck/p187-obermarck.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p187-obermarck/",
abstract = "We propose an algorithm for detecting deadlocks among
transactions running concurrently in a distributed
processing network (i.e., a distributed database
system). The proposed algorithm is a distributed
deadlock detection algorithm. A proof of the
correctness of the distributed portion of the algorithm
is given, followed by an example of the algorithm in
operation. The performance characteristics of the
algorithm are also presented.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming; data base systems; deadlock
detection",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}; Software ---
Operating Systems --- Process Management (D.4.1): {\bf
Deadlocks}; Software --- Operating Systems ---
Organization and Design (D.4.7): {\bf Distributed
systems}",
}
@Article{Garcia-Molina:1982:ROT,
author = "H{\'e}ctor Garc{\'\i}a-Molina and Gio Wiederhold",
title = "Read-Only Transactions in a Distributed Database",
journal = j-TODS,
volume = "7",
number = "2",
pages = "209--234",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p209-garcia-molina/p209-garcia-molina.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p209-garcia-molina/",
abstract = "A read-only transaction or query is a transaction
which does not modify any data. Read-only transactions
could be processed with general transaction processing
algorithms, but in many cases it is more efficient to
process read-only transactions with special algorithms
which take advantage of the knowledge that the
transaction only reads. This paper defines the various
consistency and currency requirements that read-only
transactions may have. The processing of the different
classes of read-only transactions in a distributed
database is discussed. The concept of {$R$} insularity
is introduced to characterize both the read-only and
update algorithms. Several simple update and read-only
transaction processing algorithms are presented to
illustrate how the query requirements and the update
algorithms affect the read-only transaction processing
algorithms.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; consistency; currency; data base
systems, TODS R insularity; query; R insularity;
read-only transaction; schedule; serializability;
transaction; transaction processing algorithm",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Query processing};
Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}",
}
@Article{Shneiderman:1982:AAR,
author = "Ben Shneiderman and Glenn Thomas",
title = "An Architecture for Automatic Relational Database
System Conversion",
journal = j-TODS,
volume = "7",
number = "2",
pages = "235--257",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p235-shneiderman/p235-shneiderman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p235-shneiderman/",
abstract = "Changes in requirements for database systems
necessitate schema restructuring, database translation,
and application or query program conversion. An
alternative to the lengthy manual revision process is
proposed by offering a set of 15 transformations keyed
to the relational model of data and the relational
algebra. Motivations, examples, and detailed
descriptions are provided.",
acknowledgement = ack-nhfb,
annote = "Alterations to the logical structure of a DB may
necessitate changes at three levels: (1) stored
database, (2) schema definition, and (3) application
programs or queries. Each transformation is assessed on
three features: (1) information preservation (data are
not destroyed, only their logical format is altered);
(2) data dependence (a data dependent transformation is
one in which the stored DB must be checked to determine
whether it is consistent with the logical format of the
target system); and (3) program dependence (a program
dependent transformation is one in which the
application programs must be checked to determine
whether the transformation is permissible). At every
stage the DB is kept in fourth normal form. The 15
transformations are divided into five groups. The first
group includes simple alterations, such as changing the
name of an attribute or relation (CHANGE NAME), or
adding or deleting attributes or relations (ADD/DELETE
ATTRIBUTES, INTRODUCE/SEPARATE). The role played by
keys in the relational model is clearly critical, and
particular care must be taken when transformations
involving these keys are being carried out. The second
group of transformations concerns the effect of adding
attributes to or deleting attributes from keys
(PROMOTE/DEMOTE). The third and fourth sets of
transformations are provided for the combining and
dividing of relations. (COMPOSE/DECOMPOSE,
PARTITION/MERGE). The final group of transformations is
concerned with functional dependencies",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "automatic conversion; data base systems; database
systems; relational model; transformations",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Schema and subschema};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data manipulation languages
(DML)}; Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5): {\bf Program
translation**}",
}
@Article{Roussopoulos:1982:VIR,
author = "Nicholas Roussopoulos",
title = "View Indexing in Relational Databases",
journal = j-TODS,
volume = "7",
number = "2",
pages = "258--290",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p258-roussopoulos/p258-roussopoulos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p258-roussopoulos/",
abstract = "The design and maintenance of a useful database system
require efficient optimization of the logical access
paths which demonstrate repetitive usage patterns.
Views (classes of queries given by a query model) are
an appropriate intermediate logical representation for
databases. Frequently accessed views of databases need
to be supported by indexing to enhance retrieval. This
paper investigates the problem of selecting an optimal
index set of views and describes an efficient algorithm
for this selection.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data base systems, views precomputation index
selection TODS index selection; index selection",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2); Information Systems ---
Database Management --- Systems (H.2.4): {\bf Query
processing}",
}
@Article{Jacobs:1982:IRL,
author = "Barry E. Jacobs and Alan R. Aronson and Anthony C.
Klug",
title = "On Interpretations of Relational Languages and
Solutions to the Implied Constraint Problem",
journal = j-TODS,
volume = "7",
number = "2",
pages = "291--315",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-2/p291-jacobs/p291-jacobs.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-2/p291-jacobs/",
abstract = "The interconnection between conceptual and external
levels of a relational database is made precise in
terms of the notion of ``interpretation'' between
first-order languages. This is then used to obtain a
methodology for discovering constraints at the external
level that are ``implied'' by constraints at the
conceptual level and by conceptual-to-external
mappings. It is also seen that these concepts are
important in other database issues, namely, automatic
program conversion, database design, and compile-time
error checking of embedded database languages. Although
this study deals exclusively with the relational
approach, it also discusses how these ideas can be
extended to hierarchical and network databases.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "constraints; data base systems; program conversion;
relational database",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Schema and subschema}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Data manipulation languages (DML)}",
}
@Article{Chamberlin:1982:HFC,
author = "Donald D. Chamberlin",
title = "On ``Human Factors Comparison of a Procedural and a
Nonprocedural Query Language''",
journal = j-TODS,
volume = "7",
number = "2",
pages = "316--317",
month = jun,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:45:59 1996",
bibsource = "Database/Graefe.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "TODS technical correspondence",
}
@Article{Traiger:1982:TCD,
author = "Irving L. Traiger and Jim Gray and Cesare A. Galtieri
and Bruce G. Lindsay",
title = "Transactions and Consistency in Distributed Database
Systems",
journal = j-TODS,
volume = "7",
number = "3",
pages = "323--342",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p323-traiger/p323-traiger.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p323-traiger/",
abstract = "The concepts of transaction and of data consistency
are defined for a distributed system. The cases of
partitioned data, where fragments of a file are stored
at multiple nodes, and replicated data, where a file is
replicated at several nodes, are discussed. It is
argued that the distribution and replication of data
should be transparent to the programs which use the
data. That is, the programming interface should provide
location transparency, replica transparency,
concurrency transparency, and failure transparency.
Techniques for providing such transparencies are
abstracted and discussed.\par
By extending the notions of system schedule and system
clock to handle multiple nodes, it is shown that a
distributed system can be modeled as a single
sequential execution sequence. This model is then used
to discuss simple techniques for implementing the
various forms of transparency.",
acknowledgement = ack-nhfb,
annote = "This paper is a easy-to-read introduction to required
transparency in distributed database systems. 4
transparencies are chosen and explained here, namely
location transparency, replication transparency,
concurrency transparency, and failure transparency. The
transaction model adapted by the paper is fully
synchronous and 2 phase protocol is used to implement
concurrency transparency. The paper proves that if all
transaction executions are two-phase, any legal
execution of the transactions by a distributed system
will be equivalent to some serial execution of the
transactions by a system consisting of a single node
under the assumption that updates are synchronous. The
paper introduces special node-associated clock to prove
it. The paper also gives simple explanation about a
protocol to implement failure transparency using logs
and two-phase commit protocol.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; data partitioning; data
replication; recovery; TODS data replication, data
partitioning",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}",
}
@Article{Fagin:1982:SUR,
author = "Ronald Fagin and Alberto O. Mendelzon and Jeffrey D.
Ullman",
title = "A Simplified Universal Relation Assumption and its
Properties",
journal = j-TODS,
volume = "7",
number = "3",
pages = "343--360",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05 (68B15)",
MRnumber = "83k:68100",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/bibdb.bib; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p343-fagin/p343-fagin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p343-fagin/",
abstract = "One problem concerning the universal relation
assumption is the inability of known methods to obtain
a database scheme design in the general case, where the
real-world constraints are given by a set of
dependencies that includes embedded multivalued
dependencies. We propose a simpler method of describing
the real world, where constraints are given by
functional dependencies and a single join dependency.
The relationship between this method of defining the
real world and the classical methods is exposed. We
characterize in terms of hypergraphs those multivalued
dependencies that are the consequence of a given join
dependency. Also characterized in terms of hypergraphs
are those join dependencies that are equivalent to a
set of multivalued dependencies.",
acknowledgement = ack-nhfb,
annote = "Constraints are functional dependencies and a single
join dependency.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "acyclic; database scheme; hypergraph; join dependency;
multivalued dependency; relational database",
subject = "Theory of Computation --- Mathematical Logic and
Formal Languages --- Mathematical Logic (F.4.1);
Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Graph algorithms};
Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Trees}; Information Systems
--- Database Management --- Logical Design (H.2.1):
{\bf Normal forms}; Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Schema and
subschema}; Information Systems --- Information Storage
and Retrieval --- Information Search and Retrieval
(H.3.3): {\bf Query formulation}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Relational databases}",
}
@Article{Klug:1982:DVD,
author = "Anthony Klug and Rod Price",
title = "Determining {View} dependencies using tableaux",
journal = j-TODS,
volume = "7",
number = "3",
pages = "361--380",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05",
MRnumber = "83k:68103",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p361-klug/p361-klug.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p361-klug/",
abstract = "A relational database models some part of the real
world by a set of relations and a set of constraints.
The constraints model properties of the stored
information and must be maintained true at all times.
For views defined over physically stored (base)
relations, this is done by determining whether the view
constraints are logical consequences of base relation
constraints. A technique for determining such valid
view constraints is presented in this paper. A
generalization of the tableau chase is used. The idea
of the method is to generate a tableau for the
expression whose summary violates the test constraints
in a ``canonical'' way. The chase then tries to remove
this violation.\par
It is also shown how this method has applications to
schema design. Relations not in normal form or having
other deficiencies can be replaced by normal form
projections without losing the ability to represent all
constraint information.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "chase; dependencies; rational algebra; relational
model; tableaux; views TODS",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Schema and subschema}",
}
@Article{Dayal:1982:CTU,
author = "Umeshwar Dayal and Philip A. Bernstein",
title = "On the Correct Translation of Update Operations on
Relational Views",
journal = j-TODS,
volume = "7",
number = "3",
pages = "381--416",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05",
MRnumber = "83k:68099",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p381-dayal/p381-dayal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p381-dayal/",
abstract = "Most relational database systems provide a facility
for supporting user views. Permitting this level of
abstraction has the danger, however, that update
requests issued by a user within the context of his
view may not translate correctly into equivalent
updates on the underlying database. The purpose of this
paper is to formalize the notion of update translation
and derive conditions under which translation
procedures will produce correct translations of view
updates.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "external schemata; relational databases; schema
mapping; update translation; user views",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Schema and subschema};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data manipulation languages
(DML)}; Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Database
Management --- Heterogeneous Databases (H.2.5): {\bf
Program translation**}; Computing Methodologies ---
Artificial Intelligence --- Automatic Programming
(I.2.2): {\bf Program transformation}",
}
@Article{Griffith:1982:TPR,
author = "Robert L. Griffith",
title = "Three Principles of Representation for Semantic
Networks",
journal = j-TODS,
volume = "7",
number = "3",
pages = "417--442",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p417-griffith/p417-griffith.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p417-griffith/",
abstract = "Semantic networks are so intuitive and easy to use
that they are often employed without much thought as to
the phenomenon of semantic nets themselves. Since they
are becoming more and more a tool of artificial
intelligence and now database technology, it is
appropriate to focus on the principles of semantic
nets. Such focus finds a harmonious and consistent base
which can increase the semantic quality and usefulness
of such nets. Three rules of representation are
presented which achieve greater conceptual simplicity
for users, simplifications in semantic net
implementations and maintenance, and greater
consistency across semantic net applications. These
rules, applied to elements of the net itself, reveal
how fundamental structures should be organized, and
show that the common labeled-edge semantic net can be
derived from a more primitive structure involving only
nodes and membership relationships (and special nodes
which represent names). Also, the correlation between
binary and $n$-ary relations is presented.",
acknowledgement = ack-nhfb,
annote = "Semantic networks are employed without much thought.
They are becoming a tool of artificial intelligences
and database technology, principles of semantic nets.
Three rules of representation are presented. The common
labeled-edge semantic net can be derived from a more
primitive structure involving only nodes and membership
relationships.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "Data --- Data Structures (E.1): {\bf Graphs and
networks}; Computing Methodologies --- Artificial
Intelligence --- Knowledge Representation Formalisms
and Methods (I.2.4): {\bf Semantic networks}",
}
@Article{Kim:1982:OSL,
author = "Won Kim",
title = "On Optimizing an {SQL-like} Nested Query",
journal = j-TODS,
volume = "7",
number = "3",
pages = "443--469",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p443-kim/p443-kim.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p443-kim/",
abstract = "SQL is a high-level nonprocedural data language which
has received wide recognition in relational databases.
One of the most interesting features of SQL is the
nesting of query blocks to an arbitrary depth. An
SQL-like query nested to an arbitrary depth is shown to
be composed of five basic types of nesting. Four of
them have not been well understood and more work needs
to be done to improve their execution efficiency.
Algorithms are developed that transform queries
involving these basic types of nesting into
semantically equivalent queries that are amenable to
efficient processing by existing query-processing
subsystems. These algorithms are then combined into a
coherent strategy for processing a general nested query
of arbitrary complexity.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregate function; divide; join; nested query;
predicate; relational database; SQL queries TODS",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}",
}
@Article{Wong:1982:SAI,
author = "Eugene Wong",
title = "A Statistical Approach to Incomplete Information in
Database Systems",
journal = j-TODS,
volume = "7",
number = "3",
pages = "470--488",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05",
MRnumber = "83k:68108",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/bibdb.bib; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p470-wong/p470-wong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p470-wong/",
abstract = "There are numerous situations in which a database
cannot provide a precise answer to some of the
questions that are posed. Sources of imprecision vary
and include examples such as recording errors,
incompatible scaling, and obsolete data. In many such
situations, considerable prior information concerning
the imprecision exists and can be exploited to provide
valuable information for queries to which no exact
answer can be given. The objective of this paper is to
provide a framework for doing so.",
acknowledgement = ack-nhfb,
annote = "Sources of imprecision include recording errors,
incompatible scaling, and obsolete data. In many
situations considerable prior information concerning
the imprecision exists and can be exploited. This paper
provides a framework. Null values.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "incomplete information; missing values; null values;
TODS null values",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Schema and subschema}",
}
@Article{Zaniolo:1982:NNF,
author = "Carlo Zaniolo",
title = "A New Normal Form for the Design of Relational
Database Schemata",
journal = j-TODS,
volume = "7",
number = "3",
pages = "489--499",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05 (68B15)",
MRnumber = "83k:68109",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p489-zaniolo/p489-zaniolo.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p489-zaniolo/",
abstract = "This paper addresses the problem of database schema
design in the framework of the relational data model
and functional dependencies. It suggests that both
Third Normal Form (3NF) and Boyce-Codd Normal Form
(BCNF) supply an inadequate basis for relational schema
design. The main problem with 3NF is that it is too
forgiving and does not enforce the separation principle
as strictly as it should. On the other hand, BCNF is
incompatible with the principle of representation and
prone to computational complexity. Thus a new normal
form, which lies between these two and captures the
salient qualities of both is proposed. The new normal
form is stricter than 3NF, but it is still compatible
with the representation principle. First a simpler
definition of 3NF is derived, and the analogy of this
new definition to the definition of BCNF is noted. This
analogy is used to derive the new normal form. Finally,
it is proved that Bernstein's algorithm for schema
design synthesizes schemata that are already in the new
normal form.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database schema; functional dependencies; relational
model",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Normal forms}",
}
@Article{Lam:1982:CSA,
author = "K. Lam and C. T. Yu",
title = "A Clustered Search Algorithm Incorporating Arbitrary
Term Dependencies",
journal = j-TODS,
volume = "7",
number = "3",
pages = "500--508",
month = sep,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68H05",
MRnumber = "83k:68104",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/bibdb.bib; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-3/p500-lam/p500-lam.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-3/p500-lam/",
abstract = "The documents in a database are organized into
clusters, where each cluster contains similar documents
and a representative of these documents. A user query
is compared with all the representatives of the
clusters, and on the basis of such comparisons, those
clusters having many {\em close neighbors\/} with
respect to the query are selected for searching. This
paper presents an estimation of the number of close
neighbors in a cluster in relation to the given query.
The estimation takes into consideration the
dependencies between terms. It is demonstrated by
experiments that the estimate is accurate and the time
to generate the estimate is small.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Bahadur-Lazarsfeld expansion; clustered search; CTYU
TODS; generating polynomial; term dependencies",
subject = "Theory of Computation --- Analysis of Algorithms and
Problem Complexity --- General (F.2.0); Mathematics of
Computing --- Discrete Mathematics --- Combinatorics
(G.2.1): {\bf Combinatorial algorithms}; Information
Systems --- Information Storage and Retrieval ---
Information Storage (H.3.2): {\bf File organization};
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Clustering}; Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3): {\bf Retrieval models}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}",
}
@Article{Batory:1982:UMP,
author = "D. S. Batory and C. C. Gotlieb",
title = "A Unifying Model of Physical Databases",
journal = j-TODS,
volume = "7",
number = "4",
pages = "509--539",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p509-batory/p509-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p509-batory/",
abstract = "A unifying model for the study of database performance
is proposed. Applications of the model are shown to
relate and extend important work concerning batched
searching, transposed files, index selection, dynamic
hash-based files, generalized access path structures,
differential files, network databases, and multifile
query processing.",
acknowledgement = ack-nhfb,
annote = "See also \cite{Piwowarski:1985:CBS}.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, TODS decomposition; decomposition;
linksets; simple files; unifying model",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2)",
}
@Article{Aghili:1982:PGD,
author = "Houtan Aghili and Dennis G. Severance",
title = "Practical Guide to the Design of Differential Files
for Recovery of On-Line Databases",
journal = j-TODS,
volume = "7",
number = "4",
pages = "540--565",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p540-aghili/p540-aghili.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p540-aghili/",
abstract = "The concept of a differential file has previously been
proposed as an efficient means of collecting database
updates for on-line systems. This paper studies the
problem of database backup and recovery for such
systems, and presents an analytic model of their
operation. Five key design decisions are identified and
an optimization procedure for each is developed. A
design algorithm that quickly provides parameters for a
near-optimal differential file architecture is
provided.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backup and recovery; data processing; database
maintenance; database systems; differential files;
hashing functions; numerical methods; optimization;
reorganization",
subject = "Data --- Data Storage Representations (E.2);
Mathematics of Computing --- Numerical Analysis (G.1);
Information Systems --- Database Management ---
Physical Design (H.2.2); Information Systems ---
Database Management --- Database Administration
(H.2.7)",
}
@Article{Larson:1982:PAL,
author = "Per-{\AA}ke Larson",
title = "Performance Analysis of Linear Hashing with Partial
Expansions",
journal = j-TODS,
volume = "7",
number = "4",
pages = "566--587",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p566-larson/p566-larson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p566-larson/",
abstract = "Linear hashing with partial expansions is a new file
organization primarily intended for files which grow
and shrink dynamically. This paper presents a
mathematical analysis of the expected performance of
the new scheme. The following performance measures are
considered: length of successful and unsuccessful
searches, accesses required to insert or delete a
record, and the size of the overflow area. The
performance is cyclical. For all performance measures,
the necessary formulas are derived for computing the
expected performance at any point of a cycle and the
average over a cycle. Furthermore, the expected worst
case in connection with searching is analyzed. The
overall performance depends on several file parameters.
The numerical results show that for many realistic
parameter combinations the performance is expected to
be extremely good. Even the longest search is expected
to be of quite reasonable length.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "dynamic hashing schemes; extendible hashing; hashing;
linear hashing; TODS dynamic hashing, extendible
hashing, TODS dynamic hashing, extendible hashing, data
processing",
subject = "Theory of Computation --- Analysis of Algorithms and
Problem Complexity --- Nonnumerical Algorithms and
Problems (F.2.2): {\bf Sorting and searching};
Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Babb:1982:JNF,
author = "E. Babb",
title = "Joined Normal Form: a Storage Encoding for Relational
Databases",
journal = j-TODS,
volume = "7",
number = "4",
pages = "588--614",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p588-babb/p588-babb.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p588-babb/",
abstract = "A new on-line query language and storage structure for
a database machine is presented. By including a
mathematical model in the interpreter the query
language has been substantially simplified so that no
reference to relation names is necessary. By storing
the model as a single joined normal form (JNF) file, it
has been possible to exploit the powerful search
capability of the Content Addressable File Store (CAFS;
CAFS is a registered trademark of International
Computers Limited) database machine.",
acknowledgement = ack-nhfb,
annote = "prejoining for CAFS.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CAFS; content addressing hardware; database systems;
functional dependencies; implication network; joined
normal form; joins; mathematical model; network;
queries; relational database; storage encoding tags;
storage encoding, TODS CAFS, third normal form; third
normal form; updates",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Query languages}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process}",
}
@Article{Heyman:1982:MMD,
author = "Daniel P. Heyman",
title = "Mathematical Models of Database Degradation",
journal = j-TODS,
volume = "7",
number = "4",
pages = "615--631",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p615-heyman/p615-heyman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p615-heyman/",
abstract = "As data are updated, the initial physical structure of
a database is changed and retrieval of specific pieces
of data becomes more time consuming. This phenomenon is
called database degradation. In this paper two models
of database degradation are described. Each model
refers to a different aspect of the problem.\par
It is assumed that transactions are statistically
independent and either add, delete, or update data. The
first model examines the time during which a block of
data is filling up. The second model examines the
overflows from a block of data, which essentially
describes the buildup of disorganization. Analytical
results are obtained for both models. In addition,
several numerical examples are presented which show
that the mean number of overflows grows approximately
linearly with time. This approximation is used to
devise a simple formula for the optimal time to
reorganize a stochastically growing database.",
acknowledgement = ack-nhfb,
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data overflows; database degradation, TODS data
overflows; database systems; file organization;
mathematical models",
subject = "Computer Systems Organization --- Performance of
Systems (C.4): {\bf Modeling techniques}; Information
Systems --- Database Management --- Database
Administration (H.2.7): {\bf Logging and recovery}",
}
@Article{Korth:1982:DFU,
author = "Henry F. Korth",
title = "Deadlock Freedom Using Edge Locks",
journal = j-TODS,
volume = "7",
number = "4",
pages = "632--652",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p632-korth/p632-korth.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p632-korth/",
abstract = "We define a series of locking protocols for database
systems that all have three main features: freedom from
deadlock, multiple granularity, and support for general
collections of locking primitives. A rooted directed
acyclic graph is used to represent multiple
granularities, as in System R. Deadlock freedom is
guaranteed by extending the System R protocol to
require locks on edges of the graph in addition to the
locks required on nodes.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; database systems; locking;
serializability",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Transaction processing}",
}
@Article{Goodman:1982:TQS,
author = "Nathan Goodman and Oded Shmueli",
title = "Tree Queries: a Simple Class of Relational Queries",
journal = j-TODS,
volume = "7",
number = "4",
pages = "653--677",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p653-goodman/p653-goodman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p653-goodman/",
abstract = "One can partition the class of relational database
schemas into tree schemas and cyclic schemas. (These
are called acyclic hypergraphs and cyclic hypergraphs
elsewhere in the literature.) This partition has
interesting implications in query processing,
dependency theory, and graph theory.\par
The tree/cyclic partitioning of database schemas
originated with a similar partition of equijoin
queries. Given an arbitrary equijoin query one can
obtain an equivalent query that calculates the natural
join of all relations in (an efficiently) derived
database; such a query is called a natural join (NJ)
query. If the derived database is a tree schema the
original query is said to be a tree query, and
otherwise a cyclic query.\par
In this paper we analyze query processing consequences
of the tree/cyclic partitioning. We are able to argue,
qualitatively, that queries which imply a tree schema
are easier to process than those implying a cyclic
schema. Our results also extend the study of the
semijoin operator.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "acyclic schemes; cyclic schemas; database systems;
join; semijoin; tree queries; tree schemas",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}",
}
@Article{Kerschberg:1982:QOS,
author = "Larry Kerschberg and Peter D. Ting and S. Bing Yao",
title = "Query Optimization in Star Computer Networks",
journal = j-TODS,
volume = "7",
number = "4",
pages = "678--711",
month = dec,
year = "1982",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1982-7-4/p678-kerschberg/p678-kerschberg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1982-7-4/p678-kerschberg/",
abstract = "Query processing is investigated for relational
databases distributed over several computers organized
in a star network. Minimal response-time processing
strategies are presented for queries involving the
select, project, and join commands. These strategies
depend on system parameters such as communication costs
and different machine processing speeds; database
parameters such as relation cardinality and file size;
and query parameters such as estimates of the size and
number of tuples in the result relation. The optimal
strategies specify relation preparation processes, the
shipping strategy, serial or parallel processing, and,
where applicable, the site of join filtering and
merging. Strategies for optimizing select and join
queries have been implemented and tested.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer networks; database systems; query
optimization; relational database system; star computer
network",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed applications}; Computer
Systems Organization --- Computer-Communication
Networks --- Distributed Systems (C.2.4): {\bf
Distributed databases}; Computer Systems Organization
--- Performance of Systems (C.4): {\bf Design studies};
Computer Systems Organization --- Performance of
Systems (C.4): {\bf Modeling techniques}; Software ---
Operating Systems --- File Systems Management (D.4.3):
{\bf Distributed file systems}; Software --- Operating
Systems --- Organization and Design (D.4.7): {\bf
Distributed systems}; Information Systems --- Database
Management --- Physical Design (H.2.2): {\bf Access
methods}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Distributed databases}",
}
@Article{Maier:1983:MOS,
author = "David Maier and Jeffrey D. Ullman",
title = "Maximal Objects and the Semantics of Universal
Relation Databases",
journal = j-TODS,
volume = "8",
number = "1",
pages = "1--14",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
note = "Also published in/as: SUNY, Stony Brook, CS, TR
80/016, 1980.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p1-maier/p1-maier.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p1-maier/",
abstract = "The universal relation concept is intended to provide
the database user with a simplified model in which he
can compose queries without regard to the underlying
structure of the relations in the database. Frequently,
the lossless join criterion provides the query
interpreter with the clue needed to interpret the query
as the user intended. However, some examples exist
where interpretation by the lossless-join rule runs
contrary to our intuition. To handle some of these
cases, we propose a concept called {\em maximal
objects}, which modifies the universal relation concept
in exactly those situations where it appears to go awry
--- when the underlying relational structure has
``cycles.'' We offer examples of how the maximal object
concept provides intuitively correct interpretations.
We also consider how one might construct maximal
objects mechanically from purely syntactic structural
information --- the relation schemes and functional
dependencies --- about the database.",
acknowledgement = ack-nhfb,
annote = "A universal relation is represented by a hypergraph.
If the hypergraph is cyclic, some queries can be
evaluated in different ways; restricting navigation to
few acyclic components (maximal objects) gives
intuitively correct answers.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "acyclic hypergraph; database systems; relational
database; universal relation",
subject = "Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Path and circuit problems};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Data models}; Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Data description languages (DDL)}; Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Data manipulation languages (DML)}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf Query
processing}",
}
@Article{Haskin:1983:OCH,
author = "Roger L. Haskin and Lee A. Hollaar",
title = "Operational Characteristics of a Hardware-Based
Pattern Matcher",
journal = j-TODS,
volume = "8",
number = "1",
pages = "15--40",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p15-haskin/p15-haskin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p15-haskin/",
abstract = "The design and operation of a new class of
hardware-based pattern matchers, such as would be used
in a backended database processor in a full-text or
other retrieval system, is presented. This recognizer
is based on a unique implementation technique for
finite state automata consisting of partitioning the
state table among a number of simple digital machines.
It avoids the problems generally associated with
implementing finite state machines, such as large state
table memories, complex control mechanisms, and state
encodings. Because it consists primarily of memory,
with its high regularity and density, needs only
limited static interconnections, and operates at a
relatively low speed, it can be easily constructed
using integrated circuit techniques.\par
After a brief discussion of other pattern-matching
hardware, the structure and operation of the
partitioned finite state automaton is given, along with
a simplified discussion of how the state tables are
partitioned. The expected performance of the resulting
system and the state table partitioning programs is
then discussed.",
acknowledgement = ack-nhfb,
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backend processors; computer system architecture;
database systems; finite state automata; full text
retrieval systems; information science; text
searching",
subject = "Hardware --- Logic Design --- Design Styles (B.6.1):
{\bf Cellular arrays and automata}; Hardware ---
Integrated Circuits --- Types and Design Styles
(B.7.1): {\bf Algorithms implemented in hardware};
Information Systems --- Database Management ---
Database Machines (H.2.6); Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process}",
}
@Article{Sicherman:1983:AQR,
author = "George L. Sicherman and Wiebren {De Jonge} and Reind
P. {Van De Riet}",
title = "Answering Queries without Revealing Secrets",
journal = j-TODS,
volume = "8",
number = "1",
pages = "41--59",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Also published in/as: reprinted in deJonge thesis,
Jun. 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p41-sicherman/p41-sicherman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p41-sicherman/",
abstract = "Question-answering systems must often keep certain
information secret. This can be accomplished, for
example, by sometimes refusing to answer a query. Here
the danger of revealing a secret by refusing to answer
a query is investigated. First several criteria that
can be used to decide whether or not to answer a query
are developed. First several criteria that can be used
to decide whether or not to answer a query are
developed. Then it is shown which of these criteria are
safe if the questioner knows nothing at all about what
is kept secret. Furthermore, it is proved that one of
these criteria is safe even if the user of the system
knows which information is to be kept secret.",
acknowledgement = ack-nhfb,
acmcrnumber = "8404-296",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, statistical security TODS; keeping
secrets; refusal to answer; strategy",
subject = "Information Systems --- Models and Principles ---
Systems and Information Theory (H.1.1): {\bf Value of
information}; Information Systems --- Models and
Principles --- User/Machine Systems (H.1.2);
Information Systems --- Information Storage and
Retrieval --- Systems and Software (H.3.4): {\bf
Current awareness systems (selective dissemination of
information--SDI)**}; Information Systems ---
Information Storage and Retrieval --- Systems and
Software (H.3.4): {\bf Question-answering (fact
retrieval) systems**}; Computing Methodologies ---
Artificial Intelligence --- Deduction and Theorem
Proving (I.2.3): {\bf Answer/reason extraction}",
}
@Article{deJonge:1983:CSD,
author = "Wiebren de Jonge",
title = "Compromising Statistical Databases Responding to
Queries About Means",
journal = j-TODS,
volume = "8",
number = "1",
pages = "60--80",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Also published in/as: reprinted in Jun. 1985 thesis",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p60-de_jonge/p60-de_jonge.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p60-de_jonge/",
abstract = "This paper describes how to compromise a statistical
database which only answers queries about arithmetic
means for query sets whose cardinality falls in the
range $ [k, N - k] $, for some $k$ greater than $0$,
where $N$ greater than equivalent to $ 2 k $ is the
number of records in the database. The compromise is
shown to be easy and to require only a little
preknowledge; knowing the cardinality of just one
nonempty query set is usually sufficient.\par
This means that not only count and sum queries, but
also queries for arithmetic means can be extremely
dangerous for the security of a statistical database,
and that this threat must be taken into account
explicitly by protective measures. This seems quite
important from a practical standpoint: while arithmetic
means were known for some time to be not altogether
harmless, the (perhaps surprising) extent of the threat
is now shown.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compromise; database security; database systems;
security TODS; statistical databases",
subject = "Information Systems --- Models and Principles ---
Systems and Information Theory (H.1.1): {\bf Value of
information}; Information Systems --- Models and
Principles --- User/Machine Systems (H.1.2);
Information Systems --- Information Storage and
Retrieval --- Systems and Software (H.3.4): {\bf
Question-answering (fact retrieval) systems**}",
}
@Article{Graham:1983:FD,
author = "Marc H. Graham",
title = "Functions in Databases",
journal = j-TODS,
volume = "8",
number = "1",
pages = "81--109",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "85a:68036",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p81-graham/p81-graham.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p81-graham/",
abstract = "We discuss the objectives of including functional
dependencies in the definition of a relational
database. We find two distinct objectives. The
appearance of a dependency in the definition of a
database indicates that the states of the database are
to encode a function. A method based on the chase of
calculating the function encoded by a particular state
is given and compared to methods utilizing derivations
of the dependency. A test for deciding whether the
states of a schema may encode a nonempty function is
presented as is a characterization of the class of
schemas which are capable of encoding nonempty
functions for all the dependencies in the definition.
This class is the class of dependency preserving
schemas as defined by Beeri et al. and is strictly
larger than the class presented by Bernstein.\par
The second objective of including a functional
dependency in the definition of a database is that the
dependency be capable of constraining the states of the
database; that is, capable of uncovering input errors
made by the users. We show that this capability is
weaker than the first objective; thus, even
dependencies whose functions are everywhere empty may
still act as constraints. Bounds on the requirements
for a dependency to act as a constraint are derived.
\par
These results are founded on the notion of a weak
instance for a database state, which replaces the
universal relation instance assumption and is both
intuitively and computationally more nearly
acceptable.",
acknowledgement = ack-nhfb,
annote = "Method based on the chase of calculating the function
is given; the dependency should constrain the states of
the database; many algorithms.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "functional dependencies; tableaux; TODS functional
dependencies, tableaux, database systems",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Normal forms}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Schema and subschema}",
}
@Article{Katz:1983:RCG,
author = "R. H. Katz and E. Wong",
title = "Resolving Conflicts in Global Storage Design Through
Replication",
journal = j-TODS,
volume = "8",
number = "1",
pages = "110--135",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p110-katz/p110-katz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p110-katz/",
abstract = "We present a conceptual framework in which a
database's intra- and interrecord set access
requirements are specified as a constrained assignment
of abstract characteristics (``evaluated,''
``indexed,'' ``clustered,'' ``well-placed'') to logical
access paths. We derive a physical schema by choosing
an available storage structure that most closely
provides the desired access characteristics. We use
explicit replication of schema objects to reduce the
access cost along certain paths, and analyze the
trade-offs between increased update overhead and
improved retrieval access. Finally, we given an
algorithm to select storage structures for a CODASYL 78
DBTG schema, given its access requirements
specification.",
acknowledgement = ack-nhfb,
annote = "Access path data model deduced from the
Entity-Relationship Model. Each function is augmented
with access characteristics, evaluated, indexed,
clustered, and well-placed.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access path selection; database systems, TODS
functional data model; functional data model; storage
structure choice",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Physical Design
(H.2.2): {\bf Access methods}",
}
@Article{Lomet:1983:BIE,
author = "David B. Lomet",
title = "Bounded Index Exponential Hashing",
journal = j-TODS,
volume = "8",
number = "1",
pages = "136--165",
month = mar,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-1/p136-lomet/p136-lomet.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-1/p136-lomet/",
abstract = "Bounded index exponential hashing, a new form of
extendible hashing, is described. It has the important
advantages over most of the other extendible hashing
variants of both (i) providing random access to any
record of a file in close to one disk access and (ii)
having performance which does not vary with file size.
It is straightforward to implement and demands only a
fixed and specifiable amount of main storage to achieve
this performance. Its underlying physical disk storage
is readily managed and record overflow is handled so as
to insure that unsuccessful searches never take more
than two accesses. The method's ability to access data
in close to a single disk access makes it possible to
organize a database, in which files have a primary key
and multiple secondary keys, such that the result is a
significant performance advantage over existing
organizations.",
acknowledgement = ack-nhfb,
classification = "722",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing, TODS extendible hashing; extendible
hasing; tree index methods",
subject = "Software --- Operating Systems --- File Systems
Management (D.4.3): {\bf File organization}; Data ---
Data Storage Representations (E.2): {\bf Hash-table
representations}; Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2):
{\bf File organization}",
}
@Article{Stonebraker:1983:PER,
author = "Michael Stonebraker and John Woodfill and Jeff
Ranstrom and Marguerite Murphy and Marc Meyer and Eric
Allman",
title = "Performance Enhancements to a Relational Database
System",
journal = j-TODS,
volume = "8",
number = "2",
pages = "167--185",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-2/p167-stonebraker/p167-stonebraker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-2/p167-stonebraker/",
abstract = "In this paper we examine four performance enhancements
to a database management system: dynamic compilation,
microcoded routines, a special-purpose file system, and
a special-purpose operating system. All were examined
in the context of the INGRES database management
system. Benchmark timings that are included suggest the
attractiveness of dynamic compilation and a
special-purpose file system. Microcode and a
special-purpose operating system are analyzed and
appear to be of more limited utility in the INGRES
context.",
acknowledgement = ack-nhfb,
annote = "Estimates are given for compilation, micro-coding, a
file system which supports locality, and a specialized
operating system for INGRES.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "compiled query languages; database performance;
database systems, TODS dynamic compilation microcode
special purpose file operating system; file systems for
databases; microcode",
subject = "Information Systems --- Database Management ---
General (H.2.0); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Query processing};
Information Systems --- Database Management ---
Database Machines (H.2.6)",
}
@Article{Garcia-Molina:1983:USK,
author = "H{\'e}ctor Garc{\'\i}a-Molina",
title = "Using Semantic Knowledge for Transaction Processing in
a Distributed Database",
journal = j-TODS,
volume = "8",
number = "2",
pages = "186--213",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-2/p186-garcia-molina/p186-garcia-molina.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-2/p186-garcia-molina/",
abstract = "This paper investigates how the semantic knowledge of
an application can be used in a distributed database to
process transactions efficiently and to avoid some of
the delays associated with failures. The main idea is
to allow nonserializable schedules which preserve
consistency and which are acceptable to the system
users. To produce such schedules, the transaction
processing mechanism receives semantic information from
the users in the form of transaction semantic types, a
division of transactions into steps, compatibility
sets, and countersteps. Using these notions, we propose
a mechanism which allows users to exploit their
semantic knowledge in an organized fashion. The
strengths and weaknesses of this approach are
discussed.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; consistency; database systems;
locking; schedule; semantic knowledge;
serializability",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}; Information
Systems --- Database Management --- Systems (H.2.4);
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}",
}
@Article{Clifford:1983:FST,
author = "James Clifford and David S. Warren",
title = "Formal Semantics for Time in Databases",
journal = j-TODS,
volume = "8",
number = "2",
pages = "214--254",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/ai.misc.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-2/p214-clifford/p214-clifford.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-2/p214-clifford/",
abstract = "The concept of a historical database is introduced as
a tool for modeling the dynamic nature of some part of
the real world. Just as first-order logic has been
shown to be a useful formalism for expressing and
understanding the underlying semantics of the
relational database model, intensional logic is
presented as an analogous formalism for expressing and
understanding the temporal semantics involved in a
historical database. The various components of the
relational model, as extended to include historical
relations, are discussed in terms of the model theory
for the logic IL//s, a variation of the logic IL
formulated by Richard Montague. The modal concepts of
intensional and extensional data constraints and
queries are introduced and contrasted. Finally, the
potential application of these ideas to the problem of
natural language database querying is discussed.",
acknowledgement = ack-nhfb,
annote = "all timeslices are represented. No inference needed.
Storage could be huge. Uses term historical db versus
temporal db. Intensional Montague logic. Two
timestamps: `state' and `exist'",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; entity-relationship model;
historical databases; intensional logic; relational
database; temporal semantics",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}",
}
@Article{Bitton:1983:DRE,
author = "Dina Bitton and David J. DeWitt",
title = "Duplicate Record Elimination in Large Data Files",
journal = j-TODS,
volume = "8",
number = "2",
pages = "255--265",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-2/p255-bitton/p255-bitton.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-2/p255-bitton/",
abstract = "The issue of duplicate elimination for large data
files in which many occurrences of the same record may
appear is addressed. A comprehensive cost analysis of
the duplicate elimination operation is presented. This
analysis is based on a combinatorial model developed
for estimating the size of intermediate runs produced
by a modified merge-sort procedure. The performance of
this modified merge-sort procedure is demonstrated to
be significantly superior to the standard duplicate
elimination technique of sorting followed by a
sequential pass to locate duplicate records. The
results can also be used to provide critical input to a
query optimizer in a relational database system.",
acknowledgement = ack-nhfb,
annote = "use a modified sort-merge.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, early aggregation TODS; duplicate
elimination; projection operator; sorting",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}",
}
@Article{Sagiv:1983:CGC,
author = "Yehoshua Sagiv",
title = "A Characterization of Globally Consistent Databases
and Their Correct Access Paths",
journal = j-TODS,
volume = "8",
number = "2",
pages = "266--286",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/prolog.1.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-2/p266-sagiv/p266-sagiv.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-2/p266-sagiv/",
abstract = "The representative instance is proposed as a
representation of the data stored in a database whose
relations are not the projections of a universal
instance. Database schemes are characterized for which
local consistency implies global consistency. (Local
consistency means that each relation satisfies its own
functional dependencies; global consistency means that
the representative instance satisfies all the
functional dependencies). A method of efficiently
computing projections of the representative instance is
given, provided that local consistency implies global
consistency. Throughout, it is assumed that a cover of
the functional dependencies is embodied in the database
scheme in the form of keys.",
acknowledgement = ack-nhfb,
annote = "Inter-relational consistency based on FD's",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "chase; database systems, TODS chase, universal
relation scheme, extension join, relational algebra;
extension join; functional dependency; null value;
prolog; relational algebra; relational database;
representative instance; universal relation scheme",
subject = "Theory of Computation --- Mathematical Logic and
Formal Languages --- Mathematical Logic (F.4.1);
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Normal forms}; Information Systems
--- Database Management --- Logical Design (H.2.1):
{\bf Schema and subschema}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Query formulation}",
}
@Article{Ullman:1983:CTJ,
author = "Jeffrey D. Ullman",
title = "Corrigendum: The Theory of Joins in Relational
Databases",
journal = j-TODS,
volume = "8",
number = "2",
pages = "287--287",
month = jun,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Graefe.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Aho:1979:TJR}.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cardenas:1983:PRA,
author = "Alfonso F. Cardenas and Farid Alavian and Algirdas
Avizienis",
title = "Performance of Recovery Architectures in Parallel
Associative Database Processors",
journal = j-TODS,
volume = "8",
number = "3",
pages = "291--323",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p291-cardenas/p291-cardenas.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p291-cardenas/",
abstract = "The need for robust recovery facilities in modern
database management systems is quite well known.
Various authors have addressed recovery facilities and
specific techniques, but none have delved into the
problem of recovery in database machines. In this
paper, the types of undesirable events that occur in a
database environment are classified and the necessary
recovery information, with subsequent actions to
recover the correct state of the database, is
summarized. A model of the ``processor-per-track''
class of parallel associative database processor is
presented. Three different types of recovery mechanisms
that may be considered for parallel associative
database processors are identified. For each
architecture, both the workload imposed by the recovery
mechanisms on the execution of database operations
(i.e., retrieve, modify, delete, and insert) and the
workload involved in the recovery actions (i.e.,
rollback, restart, restore, and reconstruct) are
analyzed. The performance of the three architectures is
quantitatively compared. This comparison is made in
terms of the number of extra revolutions of the
database area required to process a transaction versus
the number of records affected by a transaction. A
variety of different design parameters of the database
processor, of the database, and of a mix of transaction
types (modify, insert, and delete) are considered. A
large number of combinations is selected and the
effects of the parameters on the extra processing time
are identified.",
acknowledgement = ack-nhfb,
annote = "three methods of recovery in logic-per-track
processors are analyzed.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative database processors; database systems,
hardware support machine TODS",
subject = "Computer Systems Organization --- Performance of
Systems (C.4): {\bf Performance attributes};
Information Systems --- Database Management ---
Database Machines (H.2.6); Information Systems ---
Database Management --- Database Administration
(H.2.7): {\bf Logging and recovery}",
}
@Article{Bitton:1983:PAE,
author = "Dina Bitton and Haran Boral and David J. DeWitt and W.
Kevin Wilkinson",
title = "Parallel Algorithms for the Execution of Relational
Database Operations",
journal = j-TODS,
volume = "8",
number = "3",
pages = "324--353",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p324-bitton/p324-bitton.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p324-bitton/",
abstract = "This paper presents and analyzes algorithms for
parallel processing of relational database operations
in a general multiprocessor framework. To analyze
alternative algorithms, we introduce an analysis
methodology which incorporates I/O, CPU, and message
costs and which can be adjusted to fit different
multiprocessor architectures. Algorithms are presented
and analyzed for sorting, projection, and join
operations. While some of these algorithms have been
presented and analyzed previously, we have generalized
each in order to handle the case where the number of
pages is significantly larger than the number of
processors. In addition, we present and analyze
algorithms for the parallel execution of update and
aggregate operations.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregate operations; database machines; database
systems; join operation; parallel processing;
projection operator; sorting",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Database Machines
(H.2.6)",
}
@Article{Eager:1983:ARD,
author = "Derek L. Eager and Kenneth C. Sevcik",
title = "Achieving Robustness in Distributed Database Systems",
journal = j-TODS,
volume = "8",
number = "3",
pages = "354--381",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p354-eager/p354-eager.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p354-eager/",
abstract = "The problem of concurrency control in distributed
database systems in which site and communication link
failures may occur is considered. The possible range of
failures is not restricted; in particular, failures may
induce an arbitrary network partitioning. It is
desirable to attain a high ``level of robustness'' in
such a system; that is, these failures should have only
a small impact on system operation.\par
A level of robustness termed {\em maximal partial
operability\/} is identified. Under our models of
concurrency control and robustness, this robustness
level is the highest level attainable without
significantly degrading performance.\par
A basis for the implementation of maximal partial
operability is presented. To illustrate its use, it is
applied to a distributed locking concurrency control
method and to a method that utilizes timestamps. When
no failures are present, the robustness modifications
for these methods induce no significant additional
overhead.",
acknowledgement = ack-nhfb,
annote = "Three phases: 1. read and write to a private
workspace, 2. indicate intention to commit, restart, or
abort, 3. if verified complete actual transaction.
Intention to update from phase 2 is withdrawn if abort
or restart is the end result of phase 2. Two versions
are presented, either the data are transmitted in phase
3, or, if handled as phase 2 of two-phase commit
protocol, the data are held in secure storage from
phase 2 to phase 3. In case of partitioning, voting
(ref. Gifford) is used, but to prevent broad lockouts,
those transactions which cannot update all copies must
post this failure at a quorum of nodes, so that
successor transactions can test that they do not
conflict, and do not enter phase 3. Dangling precommits
may be resolved by checking other nodes in the
partition. On re-establishing the net, acyclicness is
created by possibly restarting transactions which led
to a cycle in the combined schedule.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; database systems; network
partitioning; robustness; serializability",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2); Information Systems ---
Database Management --- Systems (H.2.4); Information
Systems --- Database Management --- Database
Administration (H.2.7)",
}
@Article{Trueblood:1983:MMM,
author = "Robert P. Trueblood and H. Rex Hartson and Johannes J.
Martin",
title = "{MULTISAFE} --- {A} Modular Multiprocessing Approach
to Secure Database Management",
journal = j-TODS,
volume = "8",
number = "3",
pages = "382--409",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p382-trueblood/p382-trueblood.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p382-trueblood/",
abstract = "This paper describes the configuration and intermodule
communication of a MULTImodule system for supporting
Secure Authorization with Full Enforcement (MULTISAFE)
for database management. A modular architecture is
described which provides secure, controlled access to
shared data in a multiuser environment, with low
performance penalties, even for complex protection
policies. The primary mechanisms are structured and
verifiable. The entire approach is immediately
extendible to distributed protection of distributed
data. The system includes a user and applications
module (UAM), a data storage and retrieval module
(SRM), and a protection and security module (PSM). The
control of intermodule communication is based on a data
abstraction approach, initially described in terms of
function invocations. An implementation within a formal
message system is then described. The discussion of
function invocations begins with the single terminal
case and extends to the multiterminal case. Some
physical implementation aspects are also discussed, and
some examples of message sequences are given.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data types; access control; back-end
database; database systems; intermodule communication;
secure database; TODS",
subject = "Computer Systems Organization --- Processor
Architectures --- Multiple Data Stream Architectures
(Multiprocessors) (C.1.2); Software --- Operating
Systems --- Storage Management (D.4.2); Software ---
Operating Systems --- Security and Protection (D.4.6);
Information Systems --- Database Management (H.2);
Information Systems --- Database Management --- Systems
(H.2.4); Information Systems --- Database Management
--- Database Machines (H.2.6)",
}
@Article{Ito:1983:HFO,
author = "Tetsuro Ito and Makoto Kizawa",
title = "Hierarchical File Organization and its Application to
Similar-String Matching",
journal = j-TODS,
volume = "8",
number = "3",
pages = "410--433",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/spell.bib;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
https://www.math.utah.edu/pub/tex/bib/unix.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p410-ito/p410-ito.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p410-ito/",
abstract = "The automatic correction of misspelled inputs is
discussed from a viewpoint of similar-string matching.
First a hierarchical file organization based on a
linear ordering of records is presented for retrieving
records highly similar to any input query. Then the
spelling problem is attacked by constructing a
hierarchical file for a set of strings in a dictionary
of English words. The spelling correction steps proceed
as follows: (1) find one of the best-match strings
which are most similar to a query, (2) expand the
search area for obtaining the good-match strings, and
(3) interrupt the file search as soon as the required
string is displayed. Computational experiments verify
the performance of the proposed methods for
similar-string matching under the UNIX time-sharing
system.",
acknowledgement = ack-nhfb,
annote = "A spelling checker to provide possible correct
spellings for all possible words. Results are quite
sketchy",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "best match; data processing, algorithms;
experimentation; file organization; good match;
hierarchical clustering; linear ordering; measurement;
office automation; performance; similar-string;
similarity; spelling correction; text editor; theory;
verification",
review = "ACM CR 8408-0665",
subject = "I.2 Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Natural Language Processing \\ I.5.4 Computing
Methodologies, PATTERN RECOGNITION, Applications, Text
processing \\ E.5 Data, FILES, Organization/structure
\\ H.3.2 Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Storage, File organization \\
H.3.3 Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Search
process \\ H.3.3 Information Systems, INFORMATION
STORAGE AND RETRIEVAL, Information Search and
Retrieval, Selection process \\ H.4 Information
Systems, INFORMATION SYSTEMS APPLICATIONS, Office
Automation",
}
@Article{Kolodner:1983:IRS,
author = "Janet L. Kolodner",
title = "Indexing and Retrieval Strategies for Natural Language
Fact Retrieval",
journal = j-TODS,
volume = "8",
number = "3",
pages = "434--464",
month = sep,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/ai.misc.bib; Compendex database;
Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-3/p434-kolodner/p434-kolodner.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-3/p434-kolodner/",
abstract = "Researchers in artificial intelligence have recently
become interested in natural language fact retrieval;
currently, their research is at a point where it can
begin contributing to the field of Information
Retrieval. In this paper, strategies for a natural
language fact retrieval system are mapped out, and
approaches to many of the organization and retrieval
problems are presented. The CYRUS system, which keeps
track of important people and is queried in English, is
presented and used to illustrate those solutions.",
acknowledgement = ack-nhfb,
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "artificial intelligence; conceptual memory; database
retrieval; fact retrieval; information science; natural
language processing; question answering",
subject = "Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1);
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Computing Methodologies --- Artificial Intelligence ---
Knowledge Representation Formalisms and Methods
(I.2.4)",
}
@Article{Bernstein:1983:MCC,
author = "Philip A. Bernstein and Nathan Goodman",
title = "Multiversion Concurrency Control --- Theory and
Algorithms",
journal = j-TODS,
volume = "8",
number = "4",
pages = "465--483",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86m:68025",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/Discrete.event.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p465-bernstein/p465-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p465-bernstein/",
abstract = "Concurrency control is the activity of synchronizing
operations issued by concurrently executing programs on
a shared database. The goal is to produce an execution
that has the same effect as a serial (noninterleaved)
one. In a multiversion database system, each write on a
data item produces a new copy (or {\em version\/}) of
that data item. This paper presents a theory for
analyzing the correctness of concurrency control
algorithms for multiversion database systems. We use
the theory to analyze some new algorithms and some
previously published ones.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- Algorithms; database systems;
transaction processing",
subject = "Information Systems --- Database Management ---
Systems (H.2.4)",
}
@Article{Lynch:1983:MAN,
author = "Nancy A. Lynch",
title = "Multilevel Atomicity --- {A} New Correctness Criterion
for Database Concurrency Control",
journal = j-TODS,
volume = "8",
number = "4",
pages = "484--502",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86j:68022",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p484-lynch/p484-lynch.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p484-lynch/",
abstract = "{\em Multilevel atomicity}, a new correctness criteria
for database concurrency control, is defined. It
weakens the usual notion of serializability by
permitting controlled interleaving among transactions.
It appears to be especially suitable for applications
in which the set of transactions has a natural
hierarchical structure based on the hierarchical
structure of an organization. A characterization for
multilevel atomicity, in terms of the absence of cycles
in a dependency relation among transaction steps, is
given. Some remarks are made concerning
implementation.",
acknowledgement = ack-nhfb,
annote = "A weaker level of concurrency control than transaction
serializability, a generalization of Garc{\'\i}a-Molina
[1981].",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "atomicity; breakpoint; database systems; transaction",
subject = "Software --- Programming Languages --- Language
Constructs and Features (D.3.3): {\bf Concurrent
programming structures}",
}
@Article{Hecht:1983:SMF,
author = "Matthew S. Hecht and John D. Gabbe",
title = "Shadowed Management of Free Disk Pages with a Linked
List",
journal = j-TODS,
volume = "8",
number = "4",
pages = "503--514",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p503-hecht/p503-hecht.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p503-hecht/",
abstract = "We describe and prove correct a programming technique
using a linked list of pages for managing the free disk
pages of a file system where shadowing is the recovery
technique. Our technique requires a window of only two
pages of main memory for accessing and maintaining the
free list, and avoids wholesale copying of free-list
pages during a {\em checkpoint\/} or {\em recover\/}
operation.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "checkpoint; computer operating systems; computer
programming; database systems; dynamic storage
allocation; file system; recovery; shadowing; storage
management",
subject = "Software --- Operating Systems --- Storage Management
(D.4.2): {\bf Allocation/deallocation strategies};
Software --- Operating Systems --- Reliability (D.4.5):
{\bf Checkpoint/restart}",
}
@Article{Malhotra:1983:EIA,
author = "A. Malhotra and H. M. Markowitz and D. P. Pazel",
title = "{EAS-E}: An Integrated Approach to Application
Development",
journal = j-TODS,
volume = "8",
number = "4",
pages = "515--542",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p515-malhotra/p515-malhotra.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p515-malhotra/",
abstract = "{\em EAS-E\/} (pronounced EASY) is an experimental
programming language integrated with a database
management system now running on VM/370 at the IBM
Thomas J. Watson Research Center. The EAS-E programming
language is built around the entity, attribute, and set
({\em EAS\/}) view of application development. It
provides a means for translating operations on EAS
structures directly into executable code. EAS-E
commands have an English-like syntax, and thus EAS-E
programs are easy to read and understand. EAS-E
programs are also more compact than equivalent programs
in other database languages.\par
The EAS-E database management system allows many users
simultaneous access to the database. It supports
locking and deadlock detection and is capable of
efficiently supporting network databases of various
sizes including very large databases, consisting of
several millions of entities stored on multiple DASD
extends. Also available is a nonprocedural facility
that allows a user to browse and update the database
without writing programs.",
acknowledgement = ack-nhfb,
annote = "ER model based tool",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database systems, TODS
E/R model; entity relationship model",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data description languages
(DDL)}; Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data manipulation languages
(DML)}; Information Systems --- Database Management ---
Systems (H.2.4); Software --- Software Engineering ---
Programming Environments (D.2.6)",
}
@Article{Moran:1983:CDO,
author = "Shlomo Moran",
title = "On the Complexity of Designing Optimal Partial-Match
Retrieval Systems",
journal = j-TODS,
volume = "8",
number = "4",
pages = "543--551",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (68P10)",
MRnumber = "86j:68024",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Graphics/siggraph/83.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p543-moran/p543-moran.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p543-moran/",
abstract = "We consider the problem of designing an information
retrieval system on which partial match queries have to
be answered. Each record in the system consists of a
list of {\em attributes}, and a partial match query
specifies the values of some of the attributes. The
records are stored in {\em buckets\/} in a secondary
memory, and in order to answer a partial match query
all the buckets that may contain a record satisfying
the specifications of that query must be retrieved. The
bucket in which a given record is stored is found by a
multiple key hashing function, which maps each
attribute to a string of a fixed number of bits. The
address of that bucket is then represented by the
string obtained by concatenating the strings on which
the various attributes were mapped. A partial match
query may specify only part of the bits in the string
representing the address, and the larger the number of
bits specified, the smaller the number of buckets that
have to be retrieved in order to answer the query.
\par
The optimization problem considered in this paper is
that of deciding to how many bits each attribute should
be mapped by the bashing function above, so that the
expected number of buckets retrieved per query is
minimized. Efficient solutions for special cases of
this problem have been obtained in [1], [12], and [14].
It is shown that in general the problem is NP-hard, and
that if $P$ NP, it is also not fully approximable. Two
heuristic algorithms for the problem are also given and
compared.",
acknowledgement = ack-nhfb,
annote = "Optimal variable bit lengths of hashstrings, it is
NP-hard.",
classification = "723; 901; 922",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximation algorithms; computer programming ---
algorithms; file organization; hashing; information
science; NP-hard problems; optimization, TODS hashing,
searching; partial match retrieval; searching",
oldlabel = "geom-947",
review = "ACM CR 8411-0954",
subject = "Theory of Computation --- Analysis of Algorithms and
Problem Complexity --- Nonnumerical Algorithms and
Problems (F.2.2); Information Systems --- Information
Storage and Retrieval --- Information Search and
Retrieval (H.3.3)",
}
@Article{Ramamohanarao:1983:PMR,
author = "K. Ramamohanarao and John W. Lloyd and James A. Thom",
title = "Partial-Match Retrieval using Hashing and
Descriptors",
journal = j-TODS,
volume = "8",
number = "4",
pages = "552--576",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "794 538",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Graphics/siggraph/83.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p552-ramamohanarao/p552-ramamohanarao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p552-ramamohanarao/",
abstract = "This paper studies a partial-match retrieval scheme
based on hash functions and descriptors. The emphasis
is placed on showing how the use of a descriptor file
can improve the performance of the scheme. Records in
the file are given addresses according to hash
functions for each field in the record. Furthermore,
each page of the file has associated with it a
descriptor, which is a fixed-length bit string,
determined by the records actually present in the page.
Before a page is accessed to see if it contains records
in the answer to a query, the descriptor for the page
is checked. This check may show that no relevant
records are on the page and, hence, that the page does
not have to be accessed. The method is shown to have a
very substantial performance advantage over pure
hashing schemes, when some fields in the records have
large key spaces. A mathematical model of the scheme,
plus an algorithm for optimizing performance, is
given.",
acknowledgement = ack-nhfb,
classification = "723; 901; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- Algorithms; DATA PROCESSING
--- File Organization; descriptors; dynamic file;
hashing; information science; MATHEMATICAL MODELS;
OPTIMIZATION; optimization; partial-match retrieval",
oldlabel = "geom-948",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Access methods};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}",
}
@Article{Ceri:1983:CQE,
author = "S. Ceri and G. Pelagatti",
title = "Correctness of Query Execution Strategies in
Distributed Databases",
journal = j-TODS,
volume = "8",
number = "4",
pages = "577--607",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p577-ceri/p577-ceri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p577-ceri/",
abstract = "A major requirement of a Distributed DataBase
Management System (DDBMS) is to enable users to write
queries as though the database were not distributed
(distribution transparency). The DDBMS transforms the
user's queries into execution strategies, that is,
sequences of operations on the various nodes of the
network and of transmissions between them. An execution
strategy on a distributed database is correct if it
returns the same result as if the query were applied to
a nondistributed database.\par
This paper analyzes the correctness problem for query
execution strategies. A formal model, called
Multirelational Algebra, is used as a unifying
framework for this purpose. The problem of proving the
correctness of execution strategies is reduced to the
problem of proving the equivalence of two expressions
of Multirelational Algebra. A set of theorems on
equivalence is given in order to facilitate this task.
\par
The proposed approach can be used also for the
generation of correct execution strategies, because it
defines the rules which allow the transformation of a
correct strategy into an equivalent one. This paper
does not deal with the problem of evaluating equivalent
strategies, and therefore is not in itself a proposal
for a query optimizer for distributed databases.
However, it constitutes a theoretical foundation for
the design of such optimizers.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "correctness of database access; database systems;
distributed database access; read-only transactions;
relational algebra",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Distributed Systems
(C.2.4): {\bf Distributed databases}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Query languages}; Information Systems --- Database
Management --- Systems (H.2.4); Information Systems ---
Database Management --- Systems (H.2.4): {\bf Query
processing}",
}
@Article{Biskup:1983:FCR,
author = "Joachim Biskup",
title = "A Foundation of {Codd}'s Relational Maybe Operators",
journal = j-TODS,
volume = "8",
number = "4",
pages = "608--636",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (03B70)",
MRnumber = "86j:68019",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p608-biskup/p608-biskup.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p608-biskup/",
abstract = "Database relations which possibly contain maybe-tuples
and null values of type ``value at present unknown''
are studied. Maybe-tuples and null values are formally
interpreted by our notion of {\em representation},
which uses classical notions of predicate logic,
elaborates Codd's proposal of maybe-tuples, and adopts
Reiter's concept of a closed world. Precise notions of
{\em information content\/} and {\em redundancy},
associated with our notion of representation, are
investigated. {\em Extensions of the relational
algebra\/} to relations with maybe-tuples and null
values are proposed. Our extensions are essentially
Codd's, with some modifications. It is proved that
these extensions have natural properties which are
formally stated as being {\em adequate\/} and {\em
restricted}.\par
By the treatment of difference and division, our formal
framework can be used even for operations that require
``negative information.'' Finally, extensions of {\em
update operations\/} are discussed.",
acknowledgement = ack-nhfb,
annote = "Join, Project, Select, Union, Difference is defined
for nulls which are not labeled, results include Maybe.
Division does not work. Update is discussed.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "closed world assumption; database systems; information
content; maybe-tuple; negative information; null value;
open word assumption; redundancy; relational algebra;
relational database; representation",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Query processing}; Computing Methodologies ---
Artificial Intelligence --- Knowledge Representation
Formalisms and Methods (I.2.4): {\bf Predicate logic}",
}
@Article{Ullman:1983:KCA,
author = "Jeffrey D. Ullman",
title = "On {Kent}'s {``Consequences of assuming a universal
relation''} ({Technical} correspondence)",
journal = j-TODS,
volume = "8",
number = "4",
pages = "637--643",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/database.bib; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Kent:1981:CAU}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p637-ullman/p637-ullman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p637-ullman/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "TODS technical correspondence",
subject = "Information Systems --- Database Management ---
General (H.2.0)",
}
@Article{Kent:1983:URR,
author = "William Kent",
title = "The universal relation revisited (technical
correspondence)",
journal = j-TODS,
volume = "8",
number = "4",
pages = "644--648",
month = dec,
year = "1983",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/database.bib; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1983-8-4/p644-kent/p644-kent.pdf;
http://www.acm.org/pubs/citations/journals/tods/1983-8-4/p644-kent/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "TODS technical correspondence",
subject = "Information Systems --- Database Management ---
General (H.2.0)",
}
@Article{Kaplan:1984:DPN,
author = "S. Jerrold Kaplan",
title = "Designing a Portable Natural Language Database Query
System",
journal = j-TODS,
volume = "9",
number = "1",
pages = "1--19",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/ai.misc.bib; Compendex database;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p1-kaplan/p1-kaplan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p1-kaplan/",
abstract = "One barrier to the acceptance of natural language
database query systems is the substantial installation
effort required for each new database. Much of this
effort involves the encoding of semantic knowledge for
the domain of discourse, necessary to correctly
interpret and respond to natural language questions.
For such systems to be practical, techniques must be
developed to increase their portability to new domains.
\par
This paper discusses several issues involving the
portability of natural language interfaces to database
systems, and presents the approach taken in {\em
CO-OP\/} -- a natural language database query system
that provides cooperative responses to English
questions and operates with a typical CODA-SYL database
system. {\em CO-OP\/} derives its domain-specific
knowledge from a {\em lexicon\/} (the list of words
known to the system) and the information already
present in the structure and content of the underlying
database. Experience with the implementation suggests
that strategies that are not directly derivative of
cognitive or linguistic models may nonetheless play an
important role in the development of practical natural
language systems.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems",
}
@Article{Reiss:1984:PDS,
author = "Steven P. Reiss",
title = "Practical Data-Swapping: The First Steps",
journal = j-TODS,
volume = "9",
number = "1",
pages = "20--37",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p20-reiss/p20-reiss.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p20-reiss/",
abstract = "The problem of statistical database confidentiality in
releasing microdata is addressed through the use of
approximate data-swapping. Here, a portion of the
microdata is replaced with a database that has been
selected with approximately the same statistics. The
result guarantees the confidentiality of the original
data, while providing microdata with accurate
statistics. Methods for achieving such transformations
are considered and analyzed through simulation.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, TODS statistical databases",
subject = "Data --- Coding and Information Theory (E.4): {\bf
Nonsecret encoding schemes**}; Information Systems ---
Models and Principles --- Systems and Information
Theory (H.1.1): {\bf Value of information}; Information
Systems --- Information Storage and Retrieval ---
Online Information Services (H.3.5): {\bf Data
sharing}",
}
@Article{Nievergelt:1984:GFA,
author = "J. Nievergelt and Hans Hinterberger and Kenneth C.
Sevcik",
title = "The Grid File: An Adaptable, Symmetric Multikey File
Structure",
journal = j-TODS,
volume = "9",
number = "1",
pages = "38--71",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p38-nievergelt/p38-nievergelt.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p38-nievergelt/",
abstract = "Traditional file structures that provide multikey
access to records, for example, inverted files, are
extensions of file structures originally designed for
single-key access. They manifest various deficiencies
in particular for multikey access to highly dynamic
files. We study the dynamic aspects of file structures
that treat all keys symmetrically, that is, file
structures which avoid the distinction between primary
and secondary keys. We start from a bitmap approach and
treat the problem of file design as one of data
compression of a large sparse matrix. This leads to the
notions of a {\em grid partition\/} of the search space
and of a {\em grid directory}, which are the keys to a
dynamic file structure called the {\em grid file}. This
file system adapts gracefully to its contents under
insertions and deletions, and thus achieves an upper
bound of two disk accesses for single record retrieval;
it also handles range queries and partially specified
queries efficiently. We discuss in detail the design
decisions that led to the grid file, present simulation
results of its behavior, and compare it to other
multikey access file structures.",
acknowledgement = ack-nhfb,
annote = "Grid files use a vector of hash-keys, partition the
result into clusters, and store the clusters into
blocks. Two accesses are used for retrieval. Update may
be more costly. Access structures fit in core?",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing, TODS multidimensional hashing,
multidimensional hashing",
review = "ACM CR 8411-0931",
}
@Article{Buchanan:1984:DMS,
author = "Jack R. Buchanan and Richard D. Fennell and Hanan
Samet",
title = "A Database Management System for the {Federal
Courts}",
journal = j-TODS,
volume = "9",
number = "1",
pages = "72--88",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p72-buchanan/p72-buchanan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p72-buchanan/",
abstract = "A judicial systems laboratory has been established and
several large-scale information management systems
projects have been undertaken within the Federal
Judicial Center in Washington, D.C. The newness of the
court application area, together with the experimental
nature of the initial prototypes, required that the
system building tools be as flexible and efficient as
possible for effective software design and development.
The size of the databases, the expected transaction
volumes, and the long-term value of the court records
required a data manipulation system capable of
providing high performance and integrity. The resulting
design criteria, the programming capabilities
developed, and their use in system construction are
described herein. This database programming facility
has been especially designed as a technical management
tool for the database administrator, while providing
the applications programmer with a flexible database
software interface for high productivity.
\par
Specifically, a network-type database management system
using SAIL as the data manipulation host language is
described. Generic data manipulation verb formats using
SAIL's macro facilities and dynamic data structuring
facilities allowing in-core database representations
have been developed to achieve a level of flexibility
not usually attained in conventional database
systems.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, TODS SAIL, network model",
}
@Article{Papadimitriou:1984:CCM,
author = "Christos H. Papadimitriou and Paris C. Kanellakis",
title = "On Concurrency Control by Multiple Versions",
journal = j-TODS,
volume = "9",
number = "1",
pages = "89--99",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p89-papadimitriou/p89-papadimitriou.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p89-papadimitriou/",
abstract = "We examine the problem of concurrency control when the
database management system supports multiple versions
of the data. We characterize the limit of the
parallelism achievable by the multiversion approach and
demonstrate the resulting space-parallelism
trade-off.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems",
}
@Article{Shultz:1984:RTA,
author = "Roger K. Shultz and Roy J. Zingg",
title = "Response Time Analysis of Multiprocessor Computers for
Database Support",
journal = j-TODS,
volume = "9",
number = "1",
pages = "100--132",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p100-shultz/p100-shultz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p100-shultz/",
abstract = "Comparison of three multiprocessor computer
architectures for database support is made possible
through evaluation of response time expressions. These
expressions are derived by parameterizing algorithms
performed by each machine to execute a relational
algebra query. Parameters represent properties of the
database and components of the machines. Studies of
particular parameter values exhibit response times for
conventional machine technology, for low selectivity,
high duplicate occurrence, and parallel disk access,
increasing the number of processors, and improving
communication and processing technology.",
acknowledgement = ack-nhfb,
annote = "analyzes DIRECT, HYPERTREE, and REPT, their own
proposal.",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "COMPUTER SYSTEMS, DIGITAL --- multiprocessing, TODS
relational model, relational queries, direct,
hypertree, rept; database systems",
}
@Article{Valduriez:1984:JSA,
author = "Patrick Valduriez and Georges Gardarin",
title = "Join and Semijoin Algorithms for a Multiprocessor
Database Machine",
journal = j-TODS,
volume = "9",
number = "1",
pages = "133--161",
month = mar,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-1/p133-valduriez/p133-valduriez.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-1/p133-valduriez/",
abstract = "This paper presents and analyzes algorithms for
computing joins and semijoins of relations in a
multiprocessor database machine. First, a model of the
multiprocessor architecture is described, incorporating
parameters defining I/O, CPU, and message transmission
times that permit calculation of the execution times of
these algorithms. Then, three join algorithms are
presented and compared. It is shown that, for a given
configuration, each algorithm has an application domain
defined by the characteristics of the operand and
result relations. Since a semijoin operator is useful
for decreasing I/O and transmission times in a
multiprocessor system, we present and compare two
equi-semijoin algorithms and one non-equi-semijoin
algorithm. The execution times of these algorithms are
generally linearly proportional to the size of the
operand and result relations, and inversely
proportional to the number of processors. We then
compare a method which consists of joining two
relations to a method whereby one joins their
semijoins. Finally, it is shown that the latter method,
using semijoins, is generally better. The various
algorithms presented are implemented in the SABRE
database system; an evaluation model selects the best
algorithm for performing a join according to the
results presented here. A first version of the SABRE
system is currently operational at INRIA.",
acknowledgement = ack-nhfb,
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "COMPUTER SYSTEMS, DIGITAL --- Multiprocessing;
database systems",
}
@Article{Christodoulakis:1984:ICA,
author = "S. Christodoulakis",
title = "Implications of Certain Assumptions in Database
Performance Evaluation",
journal = j-TODS,
volume = "9",
number = "2",
pages = "163--186",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86k:68011",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p163-christodoulakis/p163-christodoulakis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p163-christodoulakis/",
abstract = "The assumptions of uniformity and independence of
attribute values in a file, uniformity of queries,
constant number of records per block, and random
placement of qualifying records among the blocks of a
file are frequently used in database performance
evaluation studies. In this paper we show that these
assumptions often result in predicting only an upper
bound of the expected system cost. We then discuss the
implications of nonrandom placement, nonuniformity, and
dependencies of attribute values on database design and
database performance evaluation.",
acknowledgement = ack-nhfb,
annote = "After a somewhat cursory reading of the paper --- A
few comments: A. Uniform distributions, particularly
for parallel machines, may imply uniform distribution
of work over the machines --- thus giving an upper
bound for speedup --- thus a uniform distribution is an
optimistic assumption. B. For uniprocessor systems --
the assumption of a uniform dist. is optimistic when:
1. hashing --- fewer collisions, shorter lists at
collisions should be expected from a uniform
distribution. 2. trees --- more balancing costs may be
incurred for non-uniform distributions. 3. searching
--- for example, a binary search on a non-uniform could
cost significantly more. 4. sorting --- I suspect that
uniform distributions are optimal for some sorting
methods, although I haven't looked at this in any
detail.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, selectivity cost estimation approx
TODS",
}
@Article{Effelsberg:1984:LIP,
author = "Wolfgang Effelsberg and Mary E. S. Loomis",
title = "Logical, Internal, and Physical Reference Behavior in
{CODASYL} Database Systems",
journal = j-TODS,
volume = "9",
number = "2",
pages = "187--213",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p187-effelsberg/p187-effelsberg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p187-effelsberg/",
abstract = "This work investigates one aspect of the performance
of CODASYL database systems: the data reference
behavior. We introduce a model of database traversals
at three levels: the logical, internal, and physical
levels. The mapping between the logical and internal
levels is defined by the internal schema, whereas the
mapping between the internal and the physical levels
depends on cluster properties of the database. Our
model explains the physical reference behavior for a
given sequence of DML statements at the logical level.
\par
Software has been implemented to monitor references in
two selected CODASYL DBMS applications. In a series of
experiments the physical reference behavior was
observed for varying internal schemas and cluster
properties of the database. The measurements were
limited to retrieval transactions, so that a variety of
queries could be analyzed for the same well-known state
of the database. Also, all databases were relatively
small in order to allow fast reloading with varying
internal schema parameters. In all cases, the database
transactions showed less locality of reference than do
programs under virtual memory operating systems; some
databases showed no locality at all. No evidence of
physical sequentiality was found. This suggests that
standard page replacement strategies are not optimal
for CODASYL database buffer management; instead,
replacement decisions in a database buffer should be
based on specific knowledge available from higher
system layers.",
acknowledgement = ack-nhfb,
acmcrnumber = "8506 0534",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems, TODS buffer management",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Computer Systems Organization ---
Performance of Systems (C.4): {\bf Measurement
techniques}; Software --- Operating Systems --- Storage
Management (D.4.2): {\bf Storage hierarchies}; Software
--- Operating Systems --- Performance (D.4.8): {\bf
Measurements}; Software --- Operating Systems ---
Performance (D.4.8): {\bf Modeling and prediction};
Information Systems --- Database Management ---
Physical Design (H.2.2); Information Systems ---
Database Management --- Logical Design (H.2.1)",
}
@Article{Kim:1984:PPR,
author = "Won Kim and Daniel Gajski and David J. Kuck",
title = "A Parallel Pipelined Relational Query Processor",
journal = j-TODS,
volume = "9",
number = "2",
pages = "214--242",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p214-kim/p214-kim.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p214-kim/",
abstract = "This paper presents the design of a relational query
processor. The query processor consists of only four
processing PIPEs and a number of random-access memory
modules. Each PIPE processes tuples of relations in a
bit-serial, tuple-parallel manner for each of the
primitive database operations which comprise a complex
relational query. The design of the query processor
meets three major objectives: the query processor must
be manufacturable using existing and near-term LSI
(VLSI) technology; it must support in a uniform manner
both the numeric and nonnumeric processing requirements
a high-level user interface like SQL presents; and it
must support the query-processing strategy derived in
the query optimizer to satisfy certain system-wide
performance optimality criteria.",
acknowledgement = ack-nhfb,
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer architecture; database systems; pipeline
processing; relational query processor, hardware
support database machine TODS",
subject = "Computer Systems Organization --- Processor
Architectures --- Other Architecture Styles (C.1.3):
{\bf High-level language architectures**}; Information
Systems --- Database Management --- Database Machines
(H.2.6)",
}
@Article{Al-Suwaiyel:1984:ATC,
author = "M. Al-Suwaiyel and E. Horowitz",
title = "Algorithms for Trie Compaction",
journal = j-TODS,
volume = "9",
number = "2",
pages = "243--263",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P05",
MRnumber = "794 541",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p243-ai-suwaiyel/",
abstract = "The trie data structure has many properties which make
it especially attractive for representing large files
of data. These properties include fast retrieval time,
quick unsuccessful search determination, and finding
the longest match to a given identifier. The main
drawback is the space requirement. In this paper the
concept of trie compaction is formalized. An exact
algorithm for optimal trie compaction and three
algorithms for approximate trie compaction are given,
and an analysis of the three algorithms is done. The
analyses indicate that for actual tries, reductions of
around 70 percent in the space required by the
uncompacted trie can be expected. The quality of the
compaction is shown to be insensitive to the number of
nodes, while a more relevant parameter is the alphabet
size of the key.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing",
subject = "Data --- Data Structures (E.1); Data --- Data Storage
Representations (E.2); Data --- Coding and Information
Theory (E.4): {\bf Data compaction and compression};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2); Theory of
Computation --- Analysis of Algorithms and Problem
Complexity --- Nonnumerical Algorithms and Problems
(F.2.2)",
}
@Article{Mendelzon:1984:DST,
author = "Alberto O. Mendelzon",
title = "Database States and Their Tableaux",
journal = j-TODS,
volume = "9",
number = "2",
pages = "264--282",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "794 542",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p264-mendelzon/p264-mendelzon.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p264-mendelzon/",
abstract = "Recent work considers a database state to satisfy a
set of dependencies if there exists a satisfying
universal relation whose projections contain each of
the relations in the state. Such relations are called
{\em weak instances\/} for the state. We propose the
set of all weak instances for a state as an embodiment
of the information represented by the state. We
characterize states that have the same set of weak
instances by the equivalence of their associated
tableaux. We apply this notion to the comparison of
database schemes and characterize all pairs of schemes
such that for every legal state of one of them there
exists an equivalent legal state of the other one. We
use this approach to provide a new characterization of
Boyce-Codd Normal Form relation schemes.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "TODS weak instance assumption, database systems",
}
@Article{Maier:1984:FUR,
author = "David Maier and Jeffrey D. Ullman and Moshe Y. Vardi",
title = "On the Foundations of the Universal Relation Model",
journal = j-TODS,
volume = "9",
number = "2",
pages = "283--308",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86m:68031",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p283-maier/p283-maier.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p283-maier/",
abstract = "Two fundamentally different approaches to the
universal relation model have been taken. According to
the first approach, the user's view of the database is
a universal relation or many universal relations, about
which the user poses queries. The second approach sees
the model as having query-processing capabilities that
relieve the user of the need to specify the logical
access path. Thus, while the first approach gives a
denotational semantics to query answering, the second
approach gives it an operational semantics. The authors
investigate the relationship between these two
approaches.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Query languages}; Computing Methodologies ---
Artificial Intelligence --- Deduction and Theorem
Proving (I.2.3); Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Normal
forms}; Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}",
}
@Article{Katsuno:1984:ECF,
author = "Hirofumi Katsuno",
title = "An Extension of Conflict-free Multi-valued Dependency
Sets",
journal = j-TODS,
volume = "9",
number = "2",
pages = "309--326",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86m:68029",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-2/p309-katsuno/p309-katsuno.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-2/p309-katsuno/",
abstract = "Several researchers (Beeri, Bernstein, Chiu, Fagin,
Goodman, Maier, Mendelzon, Ullman, and Yannakakis) have
introduced a special class of database schemes, called
{\em acyclic\/} or {\em tree\/} schemes. Beeri et al.
have shown that an acyclic join dependency, naturally
defined by an acyclic database scheme, has several
desirable properties, and that an acyclic join
dependency is equivalent to a conflict-free set of
multivalued dependencies. However, since their results
are confined to multivalued and join dependencies, it
is not clear whether we can handle functional
dependencies independently of other dependencies.
\par
In the present paper we define an extension of a
conflict-free set, called an {\em extended
conflict-free set}, including multivalued dependencies
and functional dependencies, and show the following two
properties of an extended conflict-free set:\par
There are three equivalent definitions of an extended
conflict-free set. One of them is defined as a set
including an acyclic joint dependency and a set of
functional dependencies such that the left and right
sides of each functional dependency are included in one
of the attribute sets that construct the acyclic join
dependency.\par
For a relation scheme with an extended conflict-free
set, there is a decomposition into third normal form
with a lossless join and preservation of
dependencies.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Schema and subschema};
Information Systems --- Database Management --- Logical
Design (H.2.1): {\bf Normal forms}",
}
@Article{Korth:1984:SUD,
author = "Henry F. Korth and Gabriel M. Kuper and Joan
Feigenbaum and Allen {Van Gelder} and Jeffrey D.
Ullman",
title = "{System/U}: a Database System Based on the Universal
Relation Assumption",
journal = j-TODS,
volume = "9",
number = "3",
pages = "331--347",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p331-korth/p331-korth.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p331-korth/",
abstract = "System/U is a universal relation database system under
development at Stanford University which uses the
language C on UNIX. The system is intended to test the
use of the universal view, in which the entire database
is seen as one relation. This paper describes the
theory behind System/U, in particular the theory of
maximal objects and the connection between a set of
attributes. We also describe the implementation of the
DDL (Data Description Language) and the DML (Data
Manipulation Language), and discuss in detail how the
DDL finds maximal objects and how the DML determines
the connection between the attributes that appear in a
query.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database systems;
RELATIONAL DATABASE; SYSTEM/U; UNIVERSAL RELATION",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Data description languages (DDL)}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Data manipulation languages (DML)}; Information
Systems --- Database Management --- Physical Design
(H.2.2): {\bf Access methods}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf Query
processing}; Mathematics of Computing --- Discrete
Mathematics --- Graph Theory (G.2.2): {\bf Path and
circuit problems}",
}
@Article{Wald:1984:RQI,
author = "Joseph A. Wald and Paul G. Sorenson",
title = "Resolving the Query Inference Problem Using {Steiner}
Trees",
journal = j-TODS,
volume = "9",
number = "3",
pages = "348--368",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Graphics/siggraph/86.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p348-wald/p348-wald.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p348-wald/",
abstract = "The query inference problem is to translate a sentence
of a query language into an unambiguous representation
of a query. A query is represented as an expression
over a set of query trees. A metric is introduced for
measuring the complexity of a query and also a proposal
that a sentence be translated into the least complex
query which `satisfies' the sentence. This method of
query inference can be used to resolve ambiguous
sentences and leads to easier formulation of
sentences.",
acknowledgement = ack-nhfb,
annote = "MDCST resolves queries over attributes using a schema
tree.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; query inference problem; Steiner
trees, TODS E/R model",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Transaction processing}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Query formulation};
Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Graph algorithms};
Mathematics of Computing --- Discrete Mathematics ---
Graph Theory (G.2.2): {\bf Trees}; Information Systems
--- Database Management --- Languages (H.2.3): {\bf
Query languages}",
}
@Article{Ramamohanarao:1984:RLH,
author = "K. Ramamohanarao and R. Sacks-Davis",
title = "Recursive Linear Hashing",
journal = j-TODS,
volume = "9",
number = "3",
pages = "369--391",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "794 545",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p369-ramamohanarao/p369-ramamohanarao.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p369-ramamohanarao/",
abstract = "A modification of linear hashing is proposed for which
the conventional use of overflow records is avoided.
Furthermore, an implementation of linear hashing is
presented for which the amount of physical storage
claimed is only fractionally more than the minimum
required. This implementation uses a fixed amount of
in-core space. Simulation results are given which
indicate that even for storage utilizations approaching
95 percent, the average successful search cost for this
method is close to one disk access.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "COMPUTER SIMULATION; data processing; DYNAMIC FILES;
LINEAR HASHING",
subject = "Data --- Data Storage Representations (E.2): {\bf
Hash-table representations}; Software --- Operating
Systems --- File Systems Management (D.4.3): {\bf File
organization}; Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2):
{\bf File organization}; Computing Methodologies ---
Simulation and Modeling --- Applications (I.6.3);
Software --- Operating Systems --- Storage Management
(D.4.2): {\bf Secondary storage}",
}
@Article{Cooper:1984:ATU,
author = "Robert B. Cooper and Martin K. Solomon",
title = "The Average Time Until Bucket Overflow",
journal = j-TODS,
volume = "9",
number = "3",
pages = "392--408",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p392-cooper/p392-cooper.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p392-cooper/",
abstract = "It is common for file structures to be divided into
equal-length partitions, called buckets, into which
records arrive for insertion and from which records are
physically deleted. We give a simple algorithm which
permits calculation of the average time until overflow
for a bucket of capacity $n$ records, assuming that
record insertions and deletions can be modeled as a
stochastic process in the usual manner of queueing
theory. We present some numerical examples, from which
we make some general observations about the
relationships among insertion and deletion rates,
bucket capacity, initial fill, and average time until
overflow. In particular, we observe that it makes sense
to define the {\em stable point\/} as the product of
the arrival rate and the average residence time of the
records; then a bucket tends to fill up to its stable
point quickly, in an amount of time almost independent
of the stable point, but the average time until
overflow increases rapidly with the difference between
the bucket capacity and the stable point.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "BUCKET OVERFLOW; data processing",
}
@Article{March:1984:SER,
author = "Salvatore T. March and Gary D. Scudder",
title = "On the Selection of Efficient Record Segmentations and
Backup Strategies for Large Shared Databases",
journal = j-TODS,
volume = "9",
number = "3",
pages = "409--438",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p409-march/p409-march.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p409-march/",
abstract = "In recent years the information processing
requirements of business organizations have expanded
tremendously. With this expansion, the design of
databases to efficiently manage and protect business
information has become critical. We analyze the impacts
of {\em record segmentation\/} (the assignment of data
items to segments defining subfiles), an
efficiency-oriented design technique, and of {\em
backup and recovery strategies}, a data protection
technique, on the overall process of database design. A
combined record segmentation/backup and recovery
procedure is presented and an application of the
procedure is discussed. Results in which problem
characteristics are varied along three dimensions:
update frequencies, available types of access paths,
and the predominant type of data retrieval that must be
supported by the database, are presented.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "backup strategies; database systems; large shared
databases; record segmentations",
subject = "Data --- Files (E.5): {\bf Organization/structure};
Information Systems --- Information Storage and
Retrieval --- Information Storage (H.3.2): {\bf File
organization}; Software --- Operating Systems ---
Reliability (D.4.5): {\bf Backup procedures}; Software
--- Operating Systems --- File Systems Management
(D.4.3): {\bf File organization}; Data --- Files (E.5):
{\bf Backup/recovery}; Information Systems --- Database
Management --- Database Administration (H.2.7): {\bf
Logging and recovery}",
}
@Article{Manber:1984:CCD,
author = "Udi Manber and Richard E. Ladner",
title = "Concurrency Control in a Dynamic Search Structure",
journal = j-TODS,
volume = "9",
number = "3",
pages = "439--455",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68N25 (68P15)",
MRnumber = "794 546",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: ACM Proc. on Database Systems,
Boston, Apr. 1982, pp. 268--282.",
URL = "http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p439-manbar/",
abstract = "A design of a data structure and efficient algorithms
for concurrent manipulations of a dynamic search
structure by independent user processes is presented in
this paper. The algorithms include updating data,
inserting new elements, and deleting elements. The
algorithms support a high level of concurrency. Each of
the operations listed above requires only constant
amount of locking. In order to make the system even
more efficient for the user processes, maintenance
processes are introduced. The maintenance processes
operate independently in the background to reorganize
the data structure and ``clean up'' after the (more
urgent) user processes. A proof of correctness of the
algorithms is given and some experimental results and
extensions are examined.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- Algorithms; concurrency
control; data processing; dynamic search structure",
}
@Article{Davidson:1984:OCP,
author = "Susan B. Davidson",
title = "Optimism and Consistency in Partitioned Distributed
Database Systems",
journal = j-TODS,
volume = "9",
number = "3",
pages = "456--481",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "794 547",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p456-davidson/p456-davidson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p456-davidson/",
abstract = "A protocol for transaction processing during partition
failures is presented which guarantees mutual
consistency between copies of data-items after repair
is completed. The protocol is ``optimistic'' in that
transactions are processed without restrictions during
failure; conflicts are then detected at repair time
using a {\em precedence graph}, and are resolved by
backing out transactions according to some {\em backout
strategy}. The resulting database state then
corresponds to a serial execution of some subset of
transactions run during the failure. Results from
simulation and probabilistic modeling show that the
optimistic protocol is a reasonable alternative in many
cases. Conditions under which the protocol performs
well are noted, and suggestions are made as to how
performance can be improved. In particular, a backout
strategy is presented which takes into account
individual transaction costs and attempts to minimize
total backout cost. Although the problem of choosing
transactions to minimize total backout cost is, in
general, NP-complete, the backout strategy is efficient
and produces very good results.",
acknowledgement = ack-nhfb,
annote = "Counter example to uniform is last hypothesis of
Christodoulakis.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; DISTRIBUTED database systems",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}; Information
Systems --- Database Management --- Physical Design
(H.2.2): {\bf Recovery and restart}; Mathematics of
Computing --- Discrete Mathematics --- Graph Theory
(G.2.2)",
}
@Article{Ibaraki:1984:ONO,
author = "Toshihide Ibaraki and Tiko Kameda",
title = "On the Optimal Nesting Order for Computing $ {N}
$-Relational Joins",
journal = j-TODS,
volume = "9",
number = "3",
pages = "482--502",
month = sep,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "794 548",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-3/p482-ibaraki/p482-ibaraki.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-3/p482-ibaraki/",
abstract = "Using the nested loops method, this paper addresses
the problem of minimizing the number of page fetches
necessary to evaluate a given query to a relational
database. We first propose a data structure whereby the
number of page fetches required for query evaluation is
substantially reduced and then derive a formula for the
expected number of page fetches. An optimal solution to
our problem is the nesting order of relations in the
evaluation program, which minimizes the number of page
fetches. Since the minimization of the formula is
NP-hard, as shown in the Appendix, we propose a
heuristic algorithm which produces a good suboptimal
solution in polynomial time. For the special case where
the input query is a ``tree query,'' we present an
efficient algorithm for finding an optimal nesting
order.",
acknowledgement = ack-nhfb,
acmcrnumber = "8506 0535",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "N-relational joins; optimal nesting order; TODS query
optimization processing relational model, database
systems",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Transaction processing}; Theory
of Computation --- Analysis of Algorithms and Problem
Complexity --- Nonnumerical Algorithms and Problems
(F.2.2); Information Systems --- Database Management
--- Logical Design (H.2.1): {\bf Data models};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Query processing}",
}
@Article{Elhardt:1984:DCH,
author = "Klaus Elhardt and Rudolf Bayer",
title = "A Database Cache for High Performance and Fast Restart
in Database Systems",
journal = j-TODS,
volume = "9",
number = "4",
pages = "503--525",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p503-elhardt/p503-elhardt.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p503-elhardt/",
abstract = "Performance in database systems is strongly influenced
by buffer management and transaction recovery methods.
This paper presents the principles of the database
cache, which replaces the traditional buffer. In
comparison to buffer management, cache management is
more carefully coordinated with transaction management,
and integrates transaction recovery. High throughput of
\par
small- and medium-sized transactions is achieved by
fast commit processing and low database traffic. Very
fast handling of transaction failures and short restart
time after system failure are guaranteed in such an
environment. Very long retrieval and update
transactions are also supported.",
acknowledgement = ack-nhfb,
affiliation = "Technische Univ, Muenchen, Inst fuer Informatik,
Munich, West Ger",
affiliationaddress = "Technische Univ, Muenchen, Inst fuer Informatik,
Munich, West Ger",
annote = "The Elhardt-Bayer cache does indeed resemble Alpine in
many important respects. The primary difference is that
it requires all of a transaction's updates to be
written to the log in contiguous log pages, which
allows some compact encodings to be used in
representing the log, but also means that more work
must be done synchronously at commit time. Also, their
scheme is not designed to support two-phase commit, and
extending it to handle two-phase commit is sure to mess
up the pretty log encoding, I think. ---Mark Brown.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer management; crash recovery; data processing;
database cache; database systems; fast restart; media
failure",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}; Software ---
Operating Systems --- Storage Management (D.4.2): {\bf
Main memory}",
}
@Article{Reuter:1984:PAR,
author = "Andreas Reuter",
title = "Performance Analysis of Recovery Techniques",
journal = j-TODS,
volume = "9",
number = "4",
pages = "526--559",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p526-reuter/p526-reuter.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p526-reuter/",
abstract = "Various logging and recovery techniques for
centralized transaction-oriented database systems under
performance aspects are described and discussed. The
classification of functional principles that has been
developed in a companion paper is used as a
terminological basis. In the main sections, a set of
analytic models is introduced and evaluated in order to
compare the performance characteristics of nine
different recovery techniques with respect to four key
parameters and a set of other parameters with less
influence. Finally, the results of model evaluation as
well as the limitations of the models themselves are
discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Kaiserslautern, Kaiserslautern, West Ger",
affiliationaddress = "Univ of Kaiserslautern, Kaiserslautern, West
Ger",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; data processing;
database systems; logging and recovery; recovery and
restart; recovery techniques; Reliability; transaction
processing",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart};
Software --- Operating Systems --- Reliability (D.4.5):
{\bf Fault-tolerance}; Software --- Operating Systems
--- Performance (D.4.8): {\bf Modeling and prediction};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}; Information
Systems --- Database Management --- Database
Administration (H.2.7): {\bf Logging and recovery}",
}
@Article{Effelsberg:1984:PDB,
author = "Wolfgang Effelsberg and Theo Haerder",
title = "Principles of Database Buffer Management",
journal = j-TODS,
volume = "9",
number = "4",
pages = "560--595",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p560-effelsberg/p560-effelsberg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p560-effelsberg/",
abstract = "This paper discusses the implementation of a database
buffer manager as a component of a DBMS. The interface
between calling components of higher system layers and
the buffer manager is described; the principal
differences between virtual memory paging and database
buffer management are outlined; the notion of
referencing versus addressing of database pages is
introduced; and the concept of fixing pages in the
buffer to prevent uncontrolled replacement is
explained.\par
Three basic tasks have to be performed by the buffer
manager: buffer search, allocation of frames to
concurrent transactions, and page replacement. For each
of these tasks, implementation alternatives are
discussed and illustrated by examples from a
performance evaluation project of a CODASYL DBMS.",
acknowledgement = ack-nhfb,
affiliation = "IBM, Scientific Cent, Heidelberg, West Ger",
affiliationaddress = "IBM, Scientific Cent, Heidelberg, West Ger",
annote = "an interface between the buffer manager and the DBMS,
choices of page replacement policies; does not cover
sequential I/O (read-ahead and write-behind).",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer management; computer programming ---
algorithms; data processing; database systems; memory
paging; referencing database pages; replacement
algorithms",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2); Software --- Operating Systems
--- Storage Management (D.4.2): {\bf Storage
hierarchies}",
}
@Article{Bernstein:1984:ACC,
author = "Philip A. Bernstein and Nathan Goodman",
title = "An Algorithm for Concurrency Control and Recovery in
Replicated Distributed Databases",
journal = j-TODS,
volume = "9",
number = "4",
pages = "596--615",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "86k:68010",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
Distributed/fault.tolerant.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p596-bernstein/p596-bernstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p596-bernstein/",
abstract = "In a one-copy distributed database, each data item is
stored at exactly one site. In a replicated database,
some data items may be stored at multiple sites. The
main motivation is improved reliability: by storing
important data at multiple sites, the DBS can operate
even though some sites have failed.\par
This paper describes an algorithm for handling
replicated data, which allows users to operate on data
so long as one copy is ``available.'' A copy is
``available'' when (i) its site is up, and (ii) the
copy is not out-of-date because of an earlier crash.
\par
The algorithm handles clean, detectable site failures,
but not Byzantine failures or network partitions.",
acknowledgement = ack-nhfb,
affiliation = "Sequoia Systems Inc, Marlborough, MA, USA",
affiliationaddress = "Sequoia Systems Inc, Marlborough, MA, USA",
annote = "3-phase commit. The first and third phases are
identical to the two phases of 2-phase commit. There is
a `Precommit' phase after the first phase where the
knowledge of the coordinator is replicated elsewhere,
thus protecting against a crash of the coordinator
(which could result in locks being tied up for long
periods).",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Algorithms; computer programming; concurrency control
and recovery; continuous operation; database systems;
replicated distributed databases; serializability;
transaction processing",
subject = "Information Systems --- Database Management ---
Physical Design (H.2.2): {\bf Recovery and restart};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Distributed databases}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Transaction processing}",
}
@Article{Chen:1984:ANV,
author = "Wen Chin Chen and Jeffrey Scott Vitter",
title = "Analysis of New Variants of Coalesced Hashing",
journal = j-TODS,
volume = "9",
number = "4",
pages = "616--645",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "794 550",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p616-chen/p616-chen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p616-chen/",
abstract = "The coalesced hashing method has been shown to be very
fast for dynamic information storage and retrieval.
This paper analyzes in a uniform way the performance of
coalesced hashing and its variants, thus settling some
open questions in the literature.\par
In all the variants, the range of the hash function is
called the {\em address region}, and extra space
reserved for storing colliders is called the {\em
cellar}. We refer to the unmodified method, which was
analyzed previously, as {\em late-insertion\/}
coalesced hashing. In this paper we analyze late
insertion and two new variations called {\em early
insertion\/} and {\em varied insertion}. When there is
no cellar, the early-insertion method is better than
late insertion; however, past experience has indicated
that it might be worse when there is a cellar. Our
analysis confirms that it is worse. The
varied-insertion method was introduced as a means of
combining the advantages of late insertion and early
insertion. This paper shows that varied insertion
requires fewer probes per search, on the average, than
do the other variants.\par
Each of these three coalesced hashing methods has a
parameter that relates the sizes of the address region
and the cellar. Techniques in this paper are designed
for tuning the parameter in order to achieve optimum
search times. We conclude with a list of open
problems.",
acknowledgement = ack-nhfb,
affiliation = "Brown Univ, Dep of Computer Science, Providence, RI,
USA",
affiliationaddress = "Brown Univ, Dep of Computer Science, Providence,
RI, USA",
annote = "Chaining and open addressing. Internal memory is
assumed!",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "address region; cellar; coalesced hashing; computer
programming --- algorithms; data processing; early
insertion; information retrieval systems; late
insertion",
subject = "Data --- Data Storage Representations (E.2): {\bf
Hash-table representations}; Software --- Software
Engineering --- Metrics (D.2.8): {\bf Performance
measures}; Theory of Computation --- Analysis of
Algorithms and Problem Complexity --- Nonnumerical
Algorithms and Problems (F.2.2): {\bf Sorting and
searching}; Mathematics of Computing --- Discrete
Mathematics --- Combinatorics (G.2.1): {\bf Generating
functions}; Mathematics of Computing --- Discrete
Mathematics --- Combinatorics (G.2.1): {\bf
Permutations and combinations}; Mathematics of
Computing --- Discrete Mathematics --- Combinatorics
(G.2.1): {\bf Recurrences and difference equations};
Mathematics of Computing --- Probability and Statistics
(G.3): {\bf Random number generation}; Information
Systems --- Information Storage and Retrieval ---
Information Search and Retrieval (H.3.3): {\bf Search
process}",
}
@Article{Deogun:1984:OCF,
author = "J. S. Deogun and V. V. Raghavan and T. K. W. Tsou",
title = "Organization of Clustered Files for Consecutive
Retrieval",
journal = j-TODS,
volume = "9",
number = "4",
pages = "646--671",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p646-deogun/p646-deogun.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p646-deogun/",
abstract = "This paper studies the problem of storing single-level
and multilevel clustered files. Necessary and
sufficient conditions for a single-level clustered file
to have the consecutive retrieval property (CRP) are
developed. A linear time algorithm to test the CRP for
a given clustered file and to identify the proper
arrangement of objects, if CRP exists, is presented.
For the single-level clustered files that do not have
CRP, it is shown that the problem of identifying a
storage organization with minimum redundancy is
NP-complete.\par
Consequently, an efficient heuristic algorithm to
generate a good storage organization for such files is
developed. Furthermore, it is shown that, for certain
types of multilevel clustered files, there exists a
storage organization such that the objects in each
cluster, for all clusters in each level of the
clustering, appear in consecutive locations.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Nebraska, Lincoln, NE, USA",
affiliationaddress = "Univ of Nebraska, Lincoln, NE, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CLUSTERED FILES; computer programming --- Algorithms;
CONSECUTIVE RETRIEVAL; data processing --- File
Organization; FILE ORGANIZATION; information retrieval
systems; NP-COMPLETE",
subject = "Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3):
{\bf Clustering}; Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2):
{\bf File organization}",
}
@Article{Traub:1984:SSS,
author = "J. F. Traub and Y. Yemini and H. Wozniakowski",
title = "The Statistical Security of a Statistical Database",
journal = j-TODS,
volume = "9",
number = "4",
pages = "672--679",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Dec 8 08:54:10 MST 1996",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This study proposes a statistical perturbation scheme
to protect a statistical database against compromise.
The proposed scheme can handle the security of
numerical as well as nonnumerical sensitive fields or a
combination of fields. Furthermore, knowledge of some
records in a database does not help to compromise
unknown records. The authors use Chebyshev's inequality
to analyze the trade-offs among the magnitude of the
perturbations, the error incurred by statistical
queries, and the size of the query set to which they
apply. They show that if the statistician is given
absolute error guarantees, then a compromise is
possible, but the cost is made exponential in the size
of the database.",
acknowledgement = ack-nhfb,
affiliation = "Columbia Univ, Dep of Computer Science, New York, NY,
USA",
affiliationaddress = "Columbia Univ, Dep of Computer Science, New
York, NY, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Chebyshev's inequality; complexity of compromise; data
processing --- Security of data; database systems;
security; statistical database",
}
@Article{Navathe:1984:VPA,
author = "Shamkant Navathe and Stefano Ceri and Gio Wiederhold
and Jinglie Dou",
title = "Vertical Partitioning Algorithms for Database Design",
journal = j-TODS,
volume = "9",
number = "4",
pages = "680--710",
month = dec,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
note = "Also published in/as: Stanford Un., TR-CS-82-957, Jan.
1983, revised Aug. 1983.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1984-9-4/p680-navathe/p680-navathe.pdf;
http://www.acm.org/pubs/citations/journals/tods/1984-9-4/p680-navathe/",
abstract = "This paper addresses the vertical partitioning of a
set of logical records or a relation into fragments.
The rationale behind vertical partitioning is to
produce fragments, groups of attribute columns, that
``closely match'' the requirements of transactions.
\par
Vertical partitioning is applied in three contexts: a
database stored on devices of a single type, a database
stored in different memory levels, and a distributed
database. In a two-level memory hierarchy, most
transactions should be processed using the fragments in
primary memory. In distributed databases, fragment
allocation should maximize the amount of local
transaction processing.\par
Fragments may be nonoverlapping or overlapping. A
two-phase approach for the determination of fragments
is proposed; in the first phase, the design is driven
by empirical objective functions which do not require
specific cost information. The second phase performs
cost optimization by incorporating the knowledge of a
specific application environment. The algorithms
presented in this paper have been implemented, and
examples of their actual use are shown.",
acknowledgement = ack-nhfb,
affiliation = "Stanford Univ, Dep of Computer Science, Stanford, CA,
USA",
affiliationaddress = "Stanford Univ, Dep of Computer Science,
Stanford, CA, USA",
annote = "based on affinity considerations.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Algorithms; CLUSTERS; computer programming; data
processing; database systems --- Design; FRAGMENT
ALLOCATION; MEMORY LEVELS; VERTICAL PARTITIONING
ALGORITHMS",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1); Information Systems ---
Database Management --- Physical Design (H.2.2);
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Transaction processing}",
}
@Article{Maier:1984:DFG,
author = "D. Maier",
title = "Databases in the Fifth Generation Project: Is {Prolog}
a Database Language?",
journal = j-TODS,
volume = "9",
number = "2",
pages = "??--??",
month = jun,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:48:52 1996",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: ACM SIGMOD, 1984.",
annote = "very readable discussion, includes links to universal
relation research.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Skeen:1984:IAP,
author = "D. Skeen and D. D. Wright",
title = "Increasing Availability in Partitioned Database
Systems",
journal = j-TODS,
volume = "??",
number = "??",
pages = "290--299",
month = Apr,
year = "1984",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:48:54 1996",
bibsource = "Distributed/Dist.Sys.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Franaszek:1985:LCT,
author = "Peter Franaszek and John T. Robinson",
title = "Limitations of Concurrency in Transaction Processing",
journal = j-TODS,
volume = "10",
number = "1",
pages = "1--28",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/real.time.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p1-franaszek/p1-franaszek.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p1-franaszek/;
http://www.acm.org/pubs/toc/Abstracts/tods/3160.html",
abstract = "Given the pairwise probability of conflict p among
transactions in a transaction processing system,
together with the total number of concurrent
transactions n, the effective level of concurrency
E(n,p) is defined as the expected number of the n
transactions that can run concurrently and actually do
useful work. Using a random graph model of concurrency,
we show for three general classes of concurrency
control methods, examples of which are (1) standard
locking, (2) strict priority scheduling, and (3)
optimistic methods, that (1) E(n, p) n(1 - p/2) n-1,
(2) E(n, p) (1 - (1 - p) n)/p, and (3) 1 + ((1 -
p)/p)ln(p(n - 1) + 1) E(n, p) 1 + (1/p)ln(p(n - 1) +
1). Thus, for fixed p, as n ??, (1) E 0 for standard
locking methods, (2) E 1/p for strict priority
scheduling methods, and (3) E for optimistic methods.
Also found are bounds on E in the case where conflicts
are analyzed so as to maximize E.\par
The predictions of the random graph model are confirmed
by simulations of an abstract transaction processing
system. In practice, though, there is a price to pay
for the increased effective level of concurrency of
methods (2) and (3): using these methods there is more
wasted work (i.e., more steps executed by transactions
that are later aborted). In response to this problem,
three new concurrency control methods suggested by the
random graph model analysis are developed. Two of
these, called (a) running priority and (b) older or
running priority, are shown by the simulation results
to perform better than the previously known methods
(l)-(3) for relatively large n or large p, in terms of
achieving a high effective level of concurrency at a
comparatively small cost in wasted work.",
acknowledgement = ack-nhfb,
affiliation = "IBM, Thomas J. Watson Research Cent, Yorktown Heights,
NY, USA",
affiliationaddress = "IBM, Thomas J. Watson Research Cent, Yorktown
Heights, NY, USA",
annote = "6 methods, incl. optimistic (best) but not
version-ing.",
classification = "722; 723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer systems, digital --- multiprocessing;
concurrency control; database systems; mathematical
techniques --- graph theory; performance; theory;
transaction processing, algorithms; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems. {\bf
D.1.3}: Software, PROGRAMMING TECHNIQUES, Concurrent
Programming. {\bf D.4.1}: Software, OPERATING SYSTEMS,
Process Management, Concurrency.",
}
@Article{Sacca:1985:DPC,
author = "Domenico Sacca and Gio Wiederhold",
title = "Database Partitioning in a Cluster of Processors",
journal = j-TODS,
volume = "10",
number = "1",
pages = "29--56",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Parallel/Multi.bib",
note = "Also published in
\cite[242--247]{Schkolnick:1983:ICV}, and IBM Research
Report No. RJ-4076, 1983.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p29-sacca/p29-sacca.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p29-sacca/;
http://www.acm.org/pubs/toc/Abstracts/tods/3161.html",
abstract = "In a distributed database system the partitioning and
allocation of the database over the processor nodes of
the network can be a critical aspect of the database
design effort. In this paper we develop and evaluate
algorithms that perform this task in a computationally
feasible manner. The network we consider is
characterized by a relatively high communication
bandwidth, considering the processing and input output
capacities in its processors. Such a balance is typical
if the processors are connected via busses or local
networks. The common constraint that transactions have
a specific root node no longer exists, so that there
are more distribution choices. However, a poor
distribution leads to less efficient computation,
higher costs, and higher loads in the nodes or in the
communication network so that the system may not be
able to handle the required set of transactions.
\par
Our approach is to first split the database into
fragments which constitute appropriate units for
allocation. The fragments to be allocated are selected
based on maximal benefit criteria using a greedy
heuristic. The assignment to processor nodes uses a
first-fit algorithm. The complete algorithm, called
GFF, is stated in a procedural form.\par
The complexity of the problem and of its candidate
solutions are analyzed and several interesting
relationships are proven. Alternate benefit metrics are
considered, since the execution cost of the allocation
procedure varies by orders of magnitude with the
alternatives of benefit evaluation. A mixed benefit
evaluation strategy is eventually proposed.\par
A model for evaluation is presented. Two of the
strategies are experimentally evaluated, and the
reported results support the discussion. The approach
should be suitable for other cases where resources have
to be allocated subject to resource constraints.",
acknowledgement = ack-nhfb,
affiliation = "IBM, Research Lab, San Jose, CA, USA",
affiliationaddress = "IBM, Research Lab, San Jose, CA, USA",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer systems, digital --- multiprocessing;
database partitioning, parallelism declustering
partitioning disk striping TODS, algorithms; database
systems; design; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems.",
}
@Article{Pramanik:1985:UGT,
author = "Sakti Pramanik and David Ittner",
title = "Use of Graph-Theoretic Models for Optimal Relational
Database Accesses to Perform Join",
journal = j-TODS,
volume = "10",
number = "1",
pages = "57--74",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "794 551",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p57-pramanik/p57-pramanik.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p57-pramanik/;
http://www.acm.org/pubs/toc/Abstracts/tods/3325.html",
abstract = "A graph model is presented to analyze the performance
of a relational join. The amount of page reaccesses,
the page access sequence, and the amount of buffer
needed are represented in terms of graph parameters. By
using the graph model formed from the index on the join
attributes, we determine the relationships between
these parameters. Two types of buffer allocation
strategies are studied, and the upper bound on the
buffer size with no page reaccess is given. This bound
is shown to be the maximum cut value of a graph. Hence,
the problem of computing this upper bound is NP-hard.
We also give algorithms to determine a page access
sequence requiring a near optimal buffer size with no
page reaccess. The optimal page access sequence for a
fixed buffer size has also been considered.",
acknowledgement = ack-nhfb,
affiliation = "Michigan State Univ, Computer Science Dep, East
Lansing, MI, USA",
affiliationaddress = "Michigan State Univ, Computer Science Dep, East
Lansing, MI, USA",
annote = "buffer management for indexes.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Measurement; Performance;
Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; database systems;
experimentation; graph-theoretic models, query
optimization processing TODS, algorithms; mathematical
techniques --- graph theory; measurement; performance;
relational database accesses; relational join; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.2.2}: Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Graph
algorithms.",
}
@Article{Larson:1985:LHO,
author = "Per-{\AA}ke Larson",
title = "Linear Hashing with Overflow-Handling by Linear
Probing",
journal = j-TODS,
volume = "10",
number = "1",
pages = "75--89",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p75-larson/p75-larson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p75-larson/;
http://www.acm.org/pubs/toc/Abstracts/tods/3324.html",
abstract = "Linear hashing is a file structure for dynamic files.
In this paper, a new, simple method for handling
overflow records in connection with linear hashing is
proposed. The method is based on linear probing and
does not rely on chaining. No dedicated overflow area
is required. The expansion sequence of linear hashing
is modified to improve the performance, which requires
changes in the address computation. A new address
computation algorithm and an expansion algorithm are
given. The performance of the method is studied by
simulation. The algorithms for the basic file
operations are very simple, and the overall performance
is competitive with that of other variants of linear
hashing.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Waterloo, Dep of Computer Science, Waterloo,
Ont, Can",
affiliationaddress = "Univ of Waterloo, Dep of Computer Science,
Waterloo, Ont, Can",
annote = "New algorithm for files that grow and shrink
dynamically; the overflow records of a full page are
directed to the next page of a group; the introduction
of five groups and the backwards split order makes this
algorithm better than previous ones.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; data processing;
database systems; design; dynamic hashing; file
organization; linear hashing; measurement; open
addressing, algorithms; performance",
review = "ACM CR 8512-1134",
subject = "{\bf E.2}: Data, DATA STORAGE REPRESENTATIONS,
Hash-table representations. {\bf D.2.2}: Software,
SOFTWARE ENGINEERING, Tools and Techniques, Decision
tables. {\bf E.5}: Data, FILES,
Organization/structure.",
}
@Article{Veklerov:1985:ADH,
author = "Eugene Veklerov",
title = "Analysis of Dynamic Hashing with Deferred Splitting",
journal = j-TODS,
volume = "10",
number = "1",
pages = "90--96",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p90-veklerov/p90-veklerov.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p90-veklerov/",
abstract = "Dynamic hashing with deferred splitting is a file
organization scheme which increases storage
utilization, as compared to `standard' dynamic hashing.
In this scheme, splitting of a bucket is deferred if
the bucket is full but its brother can accommodate new
records. The performance of the scheme is analyzed. In
a typical case the expected storage utilization
increases from 69 to 76 percent.",
acknowledgement = ack-nhfb,
affiliation = "Lawrence Berkeley Lab, Real Time Systems Group,
Berkeley, CA, USA",
affiliationaddress = "Lawrence Berkeley Lab, Real Time Systems Group,
Berkeley, CA, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; database systems; DEFERRED SPLITTING;
DYNAMIC HASHING; File Organization; STORAGE
UTILIZATION",
}
@Article{Palvia:1985:EBS,
author = "Prashant Palvia",
title = "Expressions for Batched Searching of Sequential and
Hierarchical Files",
journal = j-TODS,
volume = "10",
number = "1",
pages = "97--106",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p97-palvia/p97-palvia.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p97-palvia/;
http://www.acm.org/pubs/toc/Abstracts/tods/3326.html",
abstract = "Batching yields significant savings in access costs in
sequential, tree-structured, and random files. A direct
and simple expression is developed for computing the
average number of records\slash pages accessed to
satisfy a batched query of a sequential file. The
advantages of batching for sequential and random files
are discussed. A direct equation is provided for the
number of nodes accessed in unbatched queries of
hierarchical files. An exact recursive expression is
developed for node accesses in batched queries of
hierarchical files. In addition to the recursive
relationship, good, closed-form upper- and lower-bound
approximations are provided for the case of batched
queries of hierarchical files.",
acknowledgement = ack-nhfb,
affiliation = "Temple Univ, Dep of Computer \& Information Sciences,
Philadelphia, PA, USA",
affiliationaddress = "Temple Univ, Dep of Computer \& Information
Sciences, Philadelphia, PA, USA",
classification = "723; 901",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "batched searching; database systems; design;
hierarchical files; information science --- information
retrieval; sequential files, performance; theory",
subject = "{\bf E.5}: Data, FILES, Organization/structure. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Search process.",
}
@Article{Bever:1985:DHS,
author = "Martin Bever and Peter C. Lockemann",
title = "Database Hosting in Strongly-Typed Programming
Languages",
journal = j-TODS,
volume = "10",
number = "1",
pages = "107--126",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-1/p107-bever/p107-bever.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-1/p107-bever/;
http://www.acm.org/pubs/toc/Abstracts/tods/3327.html",
abstract = "Database system support has become an essential part
of many computer applications, which have extended
beyond the more traditional commercial applications to,
among others, engineering applications.
Correspondingly, application programming with the need
to access databases has progressively shifted to
scientifically oriented languages.\par
Modern developments in these languages are
characterized by advanced mechanisms for the liberal
declaration of data types, for type checking, and
facilities for modularization of large programs. The
present paper examines how a DBMS can be accessed from
such a language in a way that conforms to its syntax
and utilizes its type-checking facilities, without
modifying the language specification itself, and hence
its compilers. The basic idea is to rely on facilities
for defining modules as separately compilable units,
and to use these to declare user-defined abstract data
types.\par
The idea is demonstrated by an experiment in which a
specific DBMS (ADABAS) is hosted in the programming
language (LIS). The paper outlines a number of
approaches and their problems, shows how to embed the
DML into LIS, and how a more user-oriented DML can be
provided in LIS.",
acknowledgement = ack-nhfb,
acmcrnumber = "8707-597",
affiliation = "Univ Karlsruhe, Inst fuer Informatik, Karlsruhe, West
Ger",
affiliationaddress = "Univ Karlsruhe, Inst fuer Informatik, Karlsruhe,
West Ger",
annote = "ADABAS is the experimental target system and the
language is LIS.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database hosting,
design; database systems; languages; parameterized data
types; schema mapping; strongly-typed programming
languages",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Data manipulation languages (DML). {\bf
D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Abstract data types. {\bf
D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Data types and structures.
{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Data description
languages (DDL).",
}
@Article{Chen:1985:AAS,
author = "Wen Chin Chen and Jeffrey Scott Vitter",
title = "Addendum to: {``Analysis of Some New Variants of
Coalesced Hashing''} [{ACM} Trans. Database Systems
{\bf 9} (1984), no. 4, 616--645]",
journal = j-TODS,
volume = "10",
number = "1",
pages = "127--127",
month = mar,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "794 552",
bibsource = "Database/Graefe.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Vitter:1985:EIO,
author = "Jeffrey Scott Vitter",
title = "An Efficient {I/O} Interface for Optical Disks",
journal = j-TODS,
volume = "10",
number = "2",
pages = "129--162",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p129-vitter/p129-vitter.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p129-vitter/;
http://www.acm.org/pubs/toc/Abstracts/tods/3862.html",
abstract = "We introduce the notion of an I/O interface for
optical digital (write-once) disks, which is quite
different from earlier research. The purpose of an I/O
interface is to allow existing operating systems and
application programs that use magnetic disks to use
optical disks instead, with minimal change. We define
what it means for an I/O interface to be
disk-efficient. We demonstrate a practical disk-
efficient I/O interface and show that its I/O
performance in many cases is optimum, up to a constant
factor, among all disk-efficient interfaces. The
interface is most effective for applications that are
not update-intensive. An additional capability is a
built-in history mechanism that provides software
support for accessing previous versions of records.
Even if not implemented, the I/O interface can be used
as a programming tool to develop efficient special
purpose applications for use with optical disks.",
acknowledgement = ack-nhfb,
affiliation = "Brown Univ, Dep of Computer Science, Providence, RI,
USA",
affiliationaddress = "Brown Univ, Dep of Computer Science, Providence,
RI, USA",
annote = "An I/O interface supports basic update operations such
as insert write and delete on the block is proposed.
Index techniques for erasable media (Btree is assumed
in this paper) can be implemented on this interface.
Versions of a block is stored as an allocation tree on
an optical disk, which is an efficient implementation
of the pointer fill-in method. Contents of a version of
a block is represented by an offset tree. Theoretical
lower bound of these operations is evaluated. This
paper assumes that appending into existing block is
possible on optical disk.",
classification = "722; 741",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer interfaces; data storage, optical; design;
I/O interface; optical disks, algorithms; performance;
theory",
subject = "{\bf D.4.2}: Software, OPERATING SYSTEMS, Storage
Management, Secondary storage. {\bf D.4.2}: Software,
OPERATING SYSTEMS, Storage Management,
Allocation/deallocation strategies. {\bf D.4.3}:
Software, OPERATING SYSTEMS, File Systems Management,
Access methods. {\bf D.4.3}: Software, OPERATING
SYSTEMS, File Systems Management, File organization.
{\bf E.1}: Data, DATA STRUCTURES, Trees. {\bf E.2}:
Data, DATA STORAGE REPRESENTATIONS, Hash-table
representations. {\bf E.2}: Data, DATA STORAGE
REPRESENTATIONS, Linked representations. {\bf F.2.2}:
Theory of Computation, ANALYSIS OF ALGORITHMS AND
PROBLEM COMPLEXITY, Nonnumerical Algorithms and
Problems, Sorting and searching. {\bf G.2.1}:
Mathematics of Computing, DISCRETE MATHEMATICS,
Combinatorics, Combinatorial algorithms. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Access methods.",
}
@Article{Schkolnick:1985:ECU,
author = "M. Schkolnick and P. Tiberio",
title = "Estimating the Cost of Updates in a Relational
Database",
journal = j-TODS,
volume = "10",
number = "2",
pages = "163--179",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p163-schkolnick/p163-schkolnick.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p163-schkolnick/;
http://www.acm.org/pubs/toc/Abstracts/tods/3863.html",
abstract = "In this paper, cost formulas are derived for the
updates of data and indexes in a relational database.
The costs depend on the data scan type and the
predicates involved in the update statements. We show
that update costs have a considerable influence, both
in the context of the physical database design problem
and in access path selection in query optimization for
relational DBMSs.",
acknowledgement = ack-nhfb,
affiliation = "IBM Research Lab, San Jose, CA, USA",
affiliationaddress = "IBM Research Lab, San Jose, CA, USA",
annote = "tradeoff by a given index query cost against update
cost.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "costs; database systems; measurement; performance;
query optimization; relational databases; update costs,
design",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Query processing.",
}
@Article{Yu:1985:ARC,
author = "C. T. Yu and Cheing-Mei Suen and K. Lam and M. K.
Siu",
title = "Adaptive Record Clustering",
journal = j-TODS,
volume = "10",
number = "2",
pages = "180--204",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p180-yu/p180-yu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p180-yu/;
http://www.acm.org/pubs/toc/Abstracts/tods/3861.html",
abstract = "An algorithm for record clustering is presented. It is
capable of detecting sudden changes in users' access
patterns and then suggesting an appropriate assignment
of records to blocks. It is conceptually simple, highly
intuitive, does not need to classify queries into
types, and avoids collecting individual query
statistics. Experimental results indicate that it
converges rapidly; its performance is about 50 percent
better than that of the total sort method, and about
100 percent better than that of randomly assigning
records to blocks.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Illinois at Chicago Circle, Dep of Electrical
Engineering \& Computer Science, Chicago, IL, USA",
affiliationaddress = "Univ of Illinois at Chicago Circle, Dep of
Electrical Engineering \& Computer Science, Chicago,
IL, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Measurement; Performance;
Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "adaptive record clustering; algorithms; computer
programming --- algorithms; database systems;
experimentation; file organization; measurement;
performance; physical database design; probabilistic
retrieval, CTYU TODS; theory; verification, data
processing",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design. {\bf E.5}: Data, FILES,
Organization/structure. {\bf H.2.m}: Information
Systems, DATABASE MANAGEMENT, Miscellaneous. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods.",
}
@Article{Katoh:1985:CTS,
author = "Naoki Katoh and Toshihide Ibaraki and Tiko Kameda",
title = "Cautious Transaction Schedulers with Admission
Control",
journal = j-TODS,
volume = "10",
number = "2",
pages = "205--229",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p205-katoh/p205-katoh.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p205-katoh/;
http://www.acm.org/pubs/toc/Abstracts/tods/3860.html",
abstract = "We propose a new class of schedulers, called {\em
cautious schedulers}, that grant an input request if it
will not necessitate any rollback in the future. In
particular, we investigate cautious WRW-schedulers that
output schedules in class WRW only. Class WRW consists
of all schedules that are serializable, while
preserving the write-read and read-write conflict, and
is the largest polynomially {\em recognizable\/}
subclass of serializable schedules currently known. It
is shown, in this paper however, that cautious WRW-
{\em scheduling\/} is, in general, NP-complete.
Therefore, we introduce a special type ({\em type
1R\/}) of transaction, which consists of no more than
one read step (an indivisible set of read operations)
followed by multiple write steps. It is shown that
cautious WRW-scheduling can be performed efficiently if
all transactions are of type 1R and if {\em admission
control\/} can be exercised. Admission control rejects
a transaction unless its first request is immediately
grantable.",
acknowledgement = ack-nhfb,
affiliation = "Kobe Univ of Commerce, Dep of Management Science,
Kobe, Japan",
affiliationaddress = "Kobe Univ of Commerce, Dep of Management
Science, Kobe, Japan",
annote = "serializability control for predefined transaction
sequences.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; database systems; scheduling;
serializability; transaction scheduler, algorithms",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing.",
}
@Article{Albano:1985:GST,
author = "Antonio Albano and Luca Cardelli and Renzo Orsini",
title = "{Galileo}: a Strongly-Typed, Interactive Conceptual
Language",
journal = j-TODS,
volume = "10",
number = "2",
pages = "230--260",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/Functional.bib; Object/Nierstrasz.bib",
note = "Also published in \cite{Zdonik:1990:ROO}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p230-albano/p230-albano.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p230-albano/;
http://www.acm.org/pubs/toc/Abstracts/tods/3859.html",
abstract = "Galileo, a programming language for database
applications, is presented. Galileo is a
strongly-typed, interactive programming language
designed specifically to support semantic data model
features (classification, aggregation, and
specialization), as well as the abstraction mechanisms
of modern programming languages (types, abstract types,
and modularization). The main contributions of Galileo
are (a) a flexible type system to model database
structure and semantic integrity constraints; (b) the
inclusion of type hierarchies to support the
specialization abstraction mechanisms of semantic data
models; (c) a modularization mechanism to structure
data and operations into interrelated units (d) the
integration of abstraction mechanisms into an
expression-based language that allows interactive use
of the database without resorting to a new stand-alone
query language.\par
Galileo will be used in the immediate future as a tool
for database design and, in the long term, as a
high-level interface for DBMSs.",
acknowledgement = ack-nhfb,
affiliation = "Univ di Pisa, Dipartmento di Informatica, Pisa,
Italy",
affiliationaddress = "Univ di Pisa, Dipartmento di Informatica, Pisa,
Italy",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data description
languages; data manipulation; database systems;
functional abstract data types; Galileo; languages;
olit-oopl Galileo; query languages, design",
subject = "{\bf D.3.2}: Software, PROGRAMMING LANGUAGES, Language
Classifications, GALILEO. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data description languages
(DDL). {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data manipulation languages
(DML). {\bf D.3.3}: Software, PROGRAMMING LANGUAGES,
Language Constructs and Features, Abstract data types.
{\bf D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Data types and structures.
{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema.",
}
@Article{Huang:1985:HBT,
author = "Shou-Hsuan Stephen Huang",
title = "Height-balanced Trees of Order $ (\beta, \gamma,
\delta) $",
journal = j-TODS,
volume = "10",
number = "2",
pages = "261--284",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P05",
MRnumber = "801 578",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p261-huang/p261-huang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p261-huang/",
abstract = "We study restricted classes of B-trees, called $
H(\beta, \gamma, \delta) $ trees. A class is defined by
three parameters: $ \beta $, the size of a node; $
\gamma $, the minimal number of grandsons a node must
have; and $ \delta $, the minimal number of leaves
bottom nodes must have. This generalizes the brother
condition of 2-3 brother trees in a uniform way to
B-trees of higher order. The class of B-trees of order
m is obtained by choosing $ \beta = m $, $ \gamma = (m
/ 2)^2 $, and $ \delta = m / 2 $. An algorithm to
construct H-trees for any given number of keys is given
in Section 1. Insertion and deletion algorithms are
given in Section 2. The costs of these algorithms
increase smoothly as the parameters are increased.
Furthermore, it is proved that the insertion can be
done in time $ O(?? + \log N) $, where $N$ is the
number of nodes in the tree. Deletion can also be
accomplished without reconstructing the entire tree.
Properties of H-trees are given in Section 3. It is
shown that the height of H-trees decreases as
increases, and the storage utilization increases
significantly as increases. Finally, comparisons with
other restricted classes of B-trees are given in
Section 4 to show the attractiveness of H-trees.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Houston, Dep of Computer Science, Houston, TX,
USA",
affiliationaddress = "Univ of Houston, Dep of Computer Science,
Houston, TX, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; b-trees; compact b-trees; computer
programming --- algorithms; data processing; data
structures; dense multiway trees; height-balanced
trees; performance",
subject = "{\bf E.1}: Data, DATA STRUCTURES, Trees. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Access methods.",
}
@Article{Piwowarski:1985:CBS,
author = "Marek Piwowarski",
title = "Comments on Batched Searching of Sequential and
Tree-Structured Files",
journal = j-TODS,
volume = "10",
number = "2",
pages = "285--287",
month = jun,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Shneiderman:1976:BSS,Batory:1982:UMP}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-2/p285-piwowarski/p285-piwowarski.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-2/p285-piwowarski/;
http://www.acm.org/pubs/toc/Abstracts/tods/214294.html",
abstract = "Exact formulas for the expected cost savings from
batching requests against two types of j-ary trees are
given. Approximate expressions are also presented.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "performance",
subject = "{\bf H.3.2}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Storage, File organization.
{\bf E.1}: Data, DATA STRUCTURES, Trees. {\bf F.2.2}:
Theory of Computation, ANALYSIS OF ALGORITHMS AND
PROBLEM COMPLEXITY, Nonnumerical Algorithms and
Problems, Sorting and searching.",
}
@Article{Ullman:1985:ILQ,
author = "Jeffrey D. Ullman",
title = "Implementation of Logical Query Languages for
Databases",
journal = j-TODS,
volume = "10",
number = "3",
pages = "289--321",
month = sep,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Ai/nonmono.bib; Ai/prolog.1.bib; Compendex database;
Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Sep., YEAR $=$ 1985",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-3/p289-ullman/p289-ullman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-3/p289-ullman/;
http://www.acm.org/pubs/toc/Abstracts/tods/3980.html",
abstract = "We examine methods of implementing queries about
relational databases in the case where these queries
are expressed in first-order logic as a collection of
Horn clauses. Because queries may be defined
recursively, straightforward methods of query
evaluation do not always work, and a variety of
strategies have been proposed to handle subsets of
recursive queries. We express such query evaluation
techniques as ``capture rules'' on a graph representing
clauses and predicates. One essential property of
capture rules is that they can be applied
independently, thus providing a clean interface for
query-evaluation systems that use several different
strategies in different situations. Another is that
there be an efficient test for the applicability of a
given rule. We define basic capture rules corresponding
to application of operators from relational algebra, a
top-down capture rule corresponding to ``backward
chaining,'' that is, repeated resolution of goals, a
bottom-up rule, corresponding to ``forward chaining,''
where we attempt to deduce all true facts in a given
class, and a ``sideways'' rule that allows us to pass
results from one goal to another.",
acknowledgement = ack-nhfb,
affiliation = "Stanford Univ, Dep of Computer Science, Stanford, CA,
USA",
affiliationaddress = "Stanford Univ, Dep of Computer Science,
Stanford, CA, USA",
classification = "723",
conference = "Sel Pap from the 1985 ACM SIGMOD Conf",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database systems; Horn
clauses; languages; logical query languages; relational
databases, Prolog, algorithms; theory; verification",
meetingaddress = "Austin, TX, USA",
meetingdate = "May 28--31 1985",
meetingdate2 = "05/28--31/85",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving, Logic programming. {\bf I.2.4}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Knowledge Representation Formalisms and Methods,
Predicate logic.",
}
@Article{Anonymous:1985:SPA,
author = "Anonymous",
title = "Selected Papers from the 1985 {ACM SIGMOD
Conference}",
journal = j-TODS,
volume = "10",
number = "3",
pages = "289--346",
month = sep,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 10 07:59:49 1998",
bibsource = "Compendex database; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This issue contains 2 conference papers. The topics
covered are: logical query languages for databases; and
modeling concepts for VLSI CAD objects.",
acknowledgement = ack-nhfb,
classification = "714; 723",
conference = "Selected Papers from the 1985 ACM SIGMOD Conference.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
journalabr = "ACM Transactions on Database Systems",
keywords = "CAD; database systems; design automation; integrated
circuits, VLSI --- computer aided design; logical query
languages; relational databases",
meetingaddress = "Austin, TX, USA",
sponsor = "ACM, Special Interest Group on Management of Data, New
York, NY, USA",
}
@Article{Batory:1985:MCV,
author = "D. S. Batory and Won Kim",
title = "Modeling Concepts for {VLSI CAD} Objects",
journal = j-TODS,
volume = "10",
number = "3",
pages = "322--346",
month = sep,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: ACM-SIGMOD 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-3/p322-batory/p322-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-3/p322-batory/;
http://www.acm.org/pubs/toc/Abstracts/tods/4018.html",
abstract = "VLSI CAD applications deal with design objects that
have an interface description and an implementation
description. Versions of design objects have a common
interface but differ in their implementations. A
molecular object is a modeling construct which enables
a database entity to be represented by two sets of
heterogeneous records, one set describes the object's
interface and the other describes its implementation.
Thus a reasonable starting point for modeling design
objects is to begin with the concept of molecular
objects.\par
In this paper, we identify modeling concepts that are
fundamental to capturing the semantics of VLSI CAD
design objects and versions in terms of molecular
objects. A provisional set of user operations on design
objects, consistent with these modeling concepts, is
also defined. The modeling framework that we present
has been found useful for investigating physical
storage techniques and change notification problems in
version control.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Texas at Austin, Dep of Computer Sciences,
Austin, TX, USA",
affiliationaddress = "Univ of Texas at Austin, Dep of Computer
Sciences, Austin, TX, USA",
classification = "714; 723",
conference = "Sel Pap from the 1985 ACM SIGMOD Conf",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CAD; Computer Aided Design; database systems; design
automation; integrated circuits, VLSI; languages;
relational databases; storage techniques, design;
version control",
meetingaddress = "Austin, TX, USA",
meetingdate = "May 28--31 1985",
meetingdate2 = "05/28--31/85",
subject = "{\bf B.7.1}: Hardware, INTEGRATED CIRCUITS, Types and
Design Styles, VLSI (very large scale integration).",
}
@Article{Subieta:1985:SQL,
author = "Kazimierz Subieta",
title = "Semantics of Query Languages for Network Databases",
journal = j-TODS,
volume = "10",
number = "3",
pages = "347--394",
month = sep,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-3/p347-subieta/p347-subieta.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-3/p347-subieta/;
http://www.acm.org/pubs/toc/Abstracts/tods/214293.html",
abstract = "Semantics determines the meaning of language
constructs; hence it says much more than syntax does
about implementing the language. The main purpose of
this paper is a formal presentation of the meaning of
basic language constructs employed in many database
languages (sublanguages). Therefore, stylized query
languages SSL (Sample Selection Language) and J (Joins)
are introduced, wherein most of the typical entries
present in other query languages are collected. The
semantics of SSL and J are defined by means of the
denotational method and explained informally. In SSL
and J, four types of expressions are introduced: a
selector (denotes a set of addresses), a term (denotes
a set of values), a formula (denotes a truth value),
and a join (denotes a set of n-tuples of addresses or
values). In many cases alternative semantics are given
and discussed. In order to obtain more general
properties of the proposed languages, a new database
access model is introduced, intended to be a tool for
the description of the logical access paths to data. In
particular, the access paths of the network and
relational models can be described. SSL and J
expressions may be addressed to both data structures.
In the case of the relational model, expressions of J
are similar to SQL or QUEL statements. Thus J may be
considered a generalization of relational query
languages for the network model. Finally, a programming
language, based on SSL and J, is outlined, and the
issues of SSL and J implementation are considered.",
acknowledgement = ack-nhfb,
affiliation = "Polish Acad of Sciences, Inst of Computer Science,
Warsaw, Pol",
affiliationaddress = "Polish Acad of Sciences, Inst of Computer
Science, Warsaw, Pol",
classification = "723",
conference = "Sel Pap from the 1985 ACM SIGMOD Conf",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data manipulation
languages; database systems; denotational semantics;
query languages; query optimization, languages;
theory",
meetingaddress = "Austin, TX, USA",
meetingdate = "May 28--31 1985",
meetingdate2 = "05/28--31/85",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML).",
}
@Article{Liew:1985:DDP,
author = "Chong K. Liew and Uinam J. Choi and Chung J. Liew",
title = "A Data Distortion by Probability Distribution",
journal = j-TODS,
volume = "10",
number = "3",
pages = "395--411",
month = sep,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-3/p395-liew/p395-liew.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-3/p395-liew/;
http://www.acm.org/pubs/toc/Abstracts/tods/4017.html",
abstract = "This paper introduces data distortion by probability
distribution, a probability distortion that involves
three steps. The first step is to identify the
underlying density function of the original series and
to estimate the parameters of this density function.
The second step is to generate a series of data from
the estimated density function. And the final step is
to map and replace the generated series for the
original one. Because it is replaced by the distorted
data set, probability distortion guards the privacy of
an individual belonging to the original data set. At
the same time, the probability distorted series
provides asymptotically the same statistical properties
as those of the original series, since both are under
the same distribution. Unlike conventional point
distortion, probability distortion is difficult to
compromise by repeated queries, and provides a maximum
exposure for statistical analysis.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Oklahoma, Norman, OK, USA",
affiliationaddress = "Univ of Oklahoma, Norman, OK, USA",
annote = "analysis of pollution technique.",
classification = "723",
conference = "Sel Pap from the 1985 ACM SIGMOD Conf",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data distortion; database systems; probability;
probability distortion; security; statistical
databases, statistical security; TODS, algorithms",
meetingaddress = "Austin, TX, USA",
meetingdate = "May 28--31 1985",
meetingdate2 = "05/28--31/85",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration. {\bf G.3}: Mathematics of
Computing, PROBABILITY AND STATISTICS, Statistical
computing. {\bf G.3}: Mathematics of Computing,
PROBABILITY AND STATISTICS.",
}
@Article{Tay:1985:LPC,
author = "Y. C. Tay and Nathan Goodman and Rajan Suri",
title = "Locking Performance in Centralized Databases",
journal = j-TODS,
volume = "10",
number = "4",
pages = "415--462",
month = dec,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-4/p415-tay/p415-tay.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-4/p415-tay/;
http://www.acm.org/pubs/toc/Abstracts/tods/4880.html",
abstract = "An analytic model is used to study the performance of
dynamic locking. The analysis uses only the
steady-state average values of the variables. The
solution to the model is given by a cubic, which has
exactly one valid root for the range of parametric
values that is of interest. The model's predictions
agree well with simulation results for transactions
that require up to twenty locks. The model separates
data contention from resource contention, thus
facilitating an analysis of their separate effects and
their interaction. It shows that systems with a
particular form of nonuniform access, or with shared
locks, are equivalent to systems with uniform access
and only exclusive locks.\par
Blocking due to conflicts is found to impose an upper
bound on transaction throughput; this fact leads to a
rule of thumb on how much data contention should be
permitted in a system. Throughput can exceed this bound
if a transaction is restarted whenever it encounters a
conflict, provided restart costs and resource
contention are low. It can also be exceeded by making
transactions predeclare their locks. Raising the
multiprogramming level to increase throughput also
raises the number of restarts per completion.
Transactions should minimize their lock requests,
because data contention is proportional to the square
of the number of requests. The choice of how much data
to lock at a time depends on which part of a general
granularity curve the system sees.",
acknowledgement = ack-nhfb,
affiliation = "Natl Univ of Singapore, Singapore, Singapore",
affiliationaddress = "Natl Univ of Singapore, Singapore, Singapore",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Measurement; Performance; Theory;
Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; data contention; database
locking; database systems; measurement; performance;
resource contention, algorithms; theory; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Deadlock avoidance. {\bf C.4}: Computer Systems
Organization, PERFORMANCE OF SYSTEMS, Modeling
techniques. {\bf C.2.2}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Network Protocols.
{\bf C.2.1}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Network Architecture
and Design, Centralized networks.",
}
@Article{Batory:1985:MSA,
author = "D. S. Batory",
title = "Modeling the Storage Architectures of Commercial
Database Systems",
journal = j-TODS,
volume = "10",
number = "4",
pages = "463--528",
month = dec,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-4/p463-batory/p463-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-4/p463-batory/;
http://www.acm.org/pubs/toc/Abstracts/tods/5392.html",
abstract = "Modeling the storage structures of a DBMS is a
prerequisite to understanding and optimizing database
performance. Previously, such modeling was very
difficult because the fundamental role of
conceptual-to-internal mappings in DBMS implementations
went unrecognized.\par
In this paper we present a model of physical databases,
called the transformation model, that makes
conceptual-to-internal mappings explicit. By exposing
such mappings, we show that it is possible to model the
storage architectures (i.e., the storage structures and
mappings) of many commercial DBMSs in a precise,
systematic, and comprehensible way. Models of the
INQUIRE, ADABAS, and SYSTEM 2000 storage architectures
are presented as examples of the model's utility.
\par
We believe the transformation model helps bridge the
gap between physical database theory and practice. It
also reveals the possibility of a technology to
automate the development of physical database
software.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Texas at Austin, Austin, TX, USA",
affiliationaddress = "Univ of Texas at Austin, Austin, TX, USA",
annote = "considers ADABAS, INQUIRE, SYSTEM2000 in depth.
Classification of linksets. modeling storage methods of
Inquire, ADABAS, and System 2000.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Documentation",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing --- data structures; database systems;
documentation; storage architectures, design",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf E.5}: Data,
FILES, Organization/structure. {\bf H.2.m}: Information
Systems, DATABASE MANAGEMENT, Miscellaneous.",
}
@Article{Agrawal:1985:ICC,
author = "Rakesh Agrawal and David J. Dewitt",
title = "Integrated Concurrency Control and Recovery
Mechanisms: Design and Performance Evaluation",
journal = j-TODS,
volume = "10",
number = "4",
pages = "529--564",
month = dec,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-4/p529-agrawal/p529-agrawal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-4/p529-agrawal/;
http://www.acm.org/pubs/toc/Abstracts/tods/4958.html",
abstract = "In spite of the wide variety of concurrency control
and recovery mechanisms proposed during the past
decade, the behavior and the performance of various
concurrency control and recovery mechanisms remain
largely not well understood. In addition, although
concurrency control and recovery mechanisms are
intimately related, the interaction between them has
not been adequately explored. In this paper, we take a
unified view of the problems associated with
concurrency control and recovery for
transaction-oriented multiuser centralized database
management systems, and we present several integrated
mechanisms. We then develop analytical models to study
the behavior and compare the performance of these
integrated mechanisms, and we present the results of
our performance evaluation.",
acknowledgement = ack-nhfb,
affiliation = "AT\&T Bell Lab, Murray Hill, NJ, USA",
affiliationaddress = "AT\&T Bell Lab, Murray Hill, NJ, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; database systems; design;
measurement; performance; recovery mechanisms;
transaction processing, algorithms",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Recovery and restart. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Deadlock avoidance. {\bf D.4.1}:
Software, OPERATING SYSTEMS, Process Management,
Concurrency. {\bf D.4.3}: Software, OPERATING SYSTEMS,
File Systems Management.",
}
@Article{Borgida:1985:LFF,
author = "Alexander Borgida",
title = "Language Features for Flexible Handling of Exceptions
in Information Systems",
journal = j-TODS,
volume = "10",
number = "4",
pages = "565--603",
month = dec,
year = "1985",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Rutgers Un., TR-LCSR-70, rev.
Mar. 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1985-10-4/p565-borgida/p565-borgida.pdf;
http://www.acm.org/pubs/citations/journals/tods/1985-10-4/p565-borgida/;
http://www.acm.org/pubs/toc/Abstracts/tods/4995.html",
abstract = "An exception-handling facility suitable for languages
used to implement database-intensive information
systems is presented. Such a mechanism facilitates the
development and maintenance of more flexible software
systems by supporting the abstraction of details
concerning special or abnormal occurrences. The type
constraints imposed by the schema as well as various
semantic integrity assertions are considered to be
normalcy conditions, and the key contribution of this
work is to allow exceptions to these constraints to
persist. To achieve this, solutions are proposed to a
range of problems, including sharing and computing with
exceptional information, exception handling by users,
the logic of constraints with exceptions, and
implementation issues. The use of exception handling in
dealing with null values, estimates, and measurement is
also illustrated.",
acknowledgement = ack-nhfb,
affiliation = "Rutgers Univ, Dep of Computer Science, New Brunswick,
NJ, USA",
affiliationaddress = "Rutgers Univ, Dep of Computer Science, New
Brunswick, NJ, USA",
annote = "Adding exception handling to database systems to deal
with unusual, unknown, or otherwise exceptional
attribute values. A semantic extension that may inspire
KBMSers. I have a report in my office on the
possibilities of this approach, by Alex Borgida of
Rutgers. It's very readable, and it may inspire someone
to cook up such a scheme of his or her own for Naxos,
thesis, or whatever. -----Marianne W. W.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database systems;
exception handling; languages; semantic integrity;
theory; type constraints, design; verification",
subject = "{\bf D.2.5}: Software, SOFTWARE ENGINEERING, Testing
and Debugging, Error handling and recovery. {\bf
H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
description languages (DDL). {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML).",
}
@Article{Hagmann:1986:PAS,
author = "Robert Brian Hagmann and Domenico Ferrari",
title = "Performance Analysis of Several Back-End Database
Architectures",
journal = j-TODS,
volume = "11",
number = "1",
pages = "1--26",
month = mar,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-1/p1-hagmann/p1-hagmann.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-1/p1-hagmann/;
http://www.acm.org/pubs/toc/Abstracts/tods/5242.html",
abstract = "The growing acceptance of database systems makes their
performance increasingly more important. One way to
gain performance is to off-load some of the functions
of the database system to aback-end computer. The
problem is what functions should be off-loaded to
maximize the benefits of distributed processing.
\par
Our approach to this problem consisted of constructing
several variants of an existing relational database
system. INGRES, that partition the database system
software into two parts, and assigning these two parts
to two computers connected by a local area network. For
the purposes of this experiment, six different variants
of the database software were constructed to test the
sir most interesting functional subdivisions. Each
variant was then benchmarked using two different
databases and query streams. The communication medium
and the communication software were also benchmarked to
measure their contribution to the performance of each
configuration.\par
Combining the database and network measurement results,
various conclusions were reached about the viability of
the configurations, the desirable properties of the
communications mechanisms to he used, the operating
system interface and overhead, and the performance of
the database system. The variants to be preferred
depend on the hardware technology, operating system
features, database system internal structure, and
network software overhead.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, Berkely, CA, USA",
affiliationaddress = "Univ of California, Berkely, CA, USA",
annote = "an experimental methodology using INGRES.",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Experimentation; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "back-end database architectures; computer networks ---
local networks; computer systems, digital ---
distributed; database systems; experimentation; Ingres
database system; measurement; performance; relational
databases, hardware support database machine TODS,
design",
subject = "{\bf H.2.6}: Information Systems, DATABASE MANAGEMENT,
Database Machines. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems. {\bf C.4}: Computer Systems
Organization, PERFORMANCE OF SYSTEMS. {\bf H.2.0}:
Information Systems, DATABASE MANAGEMENT, General,
INGRES.",
}
@Article{Garcia-Molina:1986:ABA,
author = "H{\'e}ctor Garc{\'\i}a-Molina and Frank Pittelli and
Susan Davidson",
title = "Applications of {Byzantine} Agreement in Database
Systems",
journal = j-TODS,
volume = "11",
number = "1",
pages = "27--47",
month = mar,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-1/p27-molina/p27-molina.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-1/p27-molina/;
http://www.acm.org/pubs/toc/Abstracts/tods/5243.html",
abstract = "In this paper we study when and how a Byzantine
agreement protocol can be used in general-purpose
database management, systems. We present an overview of
the failure model used for Bizantine agreement, and of
the protocol itself. We then present correctness
criteria for database processing in this failure
environment and discuss strategies for satisfying them.
In doing this, we present new failure models for
input\slash output nodes and study ways to distribute
input transactions to processing nodes under these
models. Finally, we investigate applications of
Byzantine agreement protocols in the more common
failure environment where processors are assumed to
halt after a failure.",
acknowledgement = ack-nhfb,
affiliation = "Princeton Univ, Princeton, NJ, USA",
affiliationaddress = "Princeton Univ, Princeton, NJ, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; Byzantine agreement protocol; data
processing; database systems; distributed; failure
models; fault tolerance; reliability",
subject = "{\bf D.4.5}: Software, OPERATING SYSTEMS, Reliability,
Fault-tolerance. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Distributed systems. {\bf
C.2.2}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Network Protocols.
{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases.",
}
@Article{Segev:1986:OJO,
author = "Arie Segev",
title = "Optimization of Join Operations in Horizontally
Partitioned Database Systems",
journal = j-TODS,
volume = "11",
number = "1",
pages = "48--80",
month = mar,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-1/p48-segev/p48-segev.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-1/p48-segev/;
http://www.acm.org/pubs/toc/Abstracts/tods/5241.html",
abstract = "This paper analyzes the problem of joining two
horizontally partitioned relations in a distributed
database system. Two types of semijoin strategies are
introduced, local and remote. Local semijoins are
performed at the site of the restricted relation (or
fragment), and remote semijoins can be performed at an
arbitrary site. A mathematical model of a semijoin
strategy for the case of remote semijoins is developed,
and lower bounding and heuristic procedures are
proposed. The results of computational experiments are
reported. The experiments include an analysis of the
heuristics' performance relative to the lower bounds,
sensitivity analysis, and error analysis. These results
reveal a good performance of the heuristic procedures,
and demonstrate the benefit of using semijoin
operations to reduce the size of fragments prior to
their transmission. The algorithms for the case of
remote semijoins were found to be superior to the
algorithms for the case of local semijoins. In
addition, we found that the estimation accuracy of the
selectivity factors has a significant effect on the
incurred communication cost.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, Berkely, CA, USA",
affiliationaddress = "Univ of California, Berkely, CA, USA",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; database systems;
distributed; horizontally partitioned database systems,
query processing optimization tods; join operations;
mathematical models; optimization",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.2.2}: Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Trees.
{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Distributed
systems. {\bf G.2.1}: Mathematics of Computing,
DISCRETE MATHEMATICS, Combinatorics, Combinatorial
algorithms.",
}
@Article{Gyssens:1986:CJD,
author = "Marc Gyssens",
title = "On the Complexity of Join Dependencies",
journal = j-TODS,
volume = "11",
number = "1",
pages = "81--108",
month = mar,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "87g:68011",
MRreviewer = "J. Paredaens",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-1/p81-gyssens/p81-gyssens.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-1/p81-gyssens/;
http://www.acm.org/pubs/toc/Abstracts/tods/5237.html",
abstract = "In [10] a method is proposed for decomposing join
dependencies (jds) in a relational database using the
notion of a hinge. This method was subsequently studied
in [11] and [12]. We show how the technique of
decomposition can be used to make integrity checking
more efficient. It turns out that it is important to
find a decomposition that minimizes the number of edges
of its largest element. We show that the decompositions
obtained with the method described in [10] are optimal
in this respect. This minimality criterion leads to the
definition of the {\em degree of cyclicity}, which
allows us to classify jds and leads to the notion of
{\em n-cyclicity}, of which acyclicity is a special
case for n = 2. We then show that, for a fixed value of
n (which may be greater than 2). integrity checking can
be performed in polynomial time provided we restrict
ourselves to {\em n-cyclic\/} jds. Finally, we
generalize a well-known characterization for acyclic
jds by proving that n-cyclicity is equivalent to
``n-wise consistency implies global consistency.'' As a
consequence, consistency checking can be performed in
polynomial time if we restrict ourselves to n-cyclic
jds, for a tired value of n, not necessarily equal to
2.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Antwerp, Antwerp, Belg",
affiliationaddress = "Univ of Antwerp, Antwerp, Belg",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CYCLICITY; database systems; DECOMPOSITION; JOIN
DEPENDENCIES; MATHEMATICAL TECHNIQUES --- Graph Theory;
Relational",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms. {\bf G.2.2}: Mathematics
of Computing, DISCRETE MATHEMATICS, Graph Theory, Graph
algorithms. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design, Schema and subschema. {\bf
G.2.2}: Mathematics of Computing, DISCRETE MATHEMATICS,
Graph Theory, Trees.",
}
@Article{Sacco:1986:FTE,
author = "Giovanni Maria Sacco",
title = "Fragmentation: a technique for Efficient Query
Processing",
journal = j-TODS,
volume = "11",
number = "2",
pages = "113--133",
month = jun,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: University of Torino, TR., Aug.
1983.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-2/p113-sacco/p113-sacco.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-2/p113-sacco/;
http://www.acm.org/pubs/toc/Abstracts/tods/5638.html",
abstract = "A `divide and conquer' strategy to compute natural
joins by sequential scans on unordered relations is
described. This strategy is shown to always be better
than merging scans when both relations must be sorted
before joining, and generally better in practical cases
when only the largest relation must be sorted.",
acknowledgement = ack-nhfb,
affiliation = "Univ di Torino",
affiliationaddress = "Turin, Italy",
annote = "Join by hashing: Create fragments by hashing, as many
fragments as buffers can be allocated in memory. Then
repeat that for the other relation. Then do a nested
unsorted join, as Kim, W. 1980, on the fragment
pairs.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Economics; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- Algorithms; database systems;
divide-and-conquer algorithms; economics;
fragmentation; natural joins, join hash partitioning
overflow avoidance recursion parallelism TODS,
algorithms; performance; query processing",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing.",
}
@Article{Beeri:1986:IAL,
author = "Catriel Beeri and Michael Kifer",
title = "An Integrated Approach to Logical Design of Relational
Database Schemes",
journal = j-TODS,
volume = "11",
number = "2",
pages = "134--158",
month = jun,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "848 633",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-2/p134-beeri/p134-beeri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-2/p134-beeri/;
http://www.acm.org/pubs/toc/Abstracts/tods/214291.html",
abstract = "We propose a new approach to the design of relational
database schemes. The main features of the approach are
the following:\par
A combination of the traditional decomposition and
synthesis approaches, thus allowing the use of both
functional and multivalued dependencies.
\par
Separation of structural dependencies relevant for the
design process from integrity constraints, that is,
constraints that do not bear any structural information
about the data and which should therefore be discarded
at the design stage. This separation is supported by a
simple syntactic test filtering out nonstructural
dependencies.\par
Automatic correction of schemes which lack certain
desirable properties.",
acknowledgement = ack-nhfb,
affiliation = "Hebrew Univ of Jerusalem, Jerusalem, Isr",
affiliationaddress = "Hebrew Univ of Jerusalem, Jerusalem, Isr",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "acyclic schemes, design; database systems;
decomposition; functional dependencies; multivalued
dependencies; relational; synthesis; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Normal forms.",
}
@Article{Mendelson:1986:IIC,
author = "Haim Mendelson and Aditya N. Saharia",
title = "Incomplete Information Costs and Database Design",
journal = j-TODS,
volume = "11",
number = "2",
pages = "159--185",
month = jun,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-2/p159-mendelson/p159-mendelson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-2/p159-mendelson/;
http://www.acm.org/pubs/toc/Abstracts/tods/5678.html",
abstract = "This paper presents a methodology for trading-off the
cost of incomplete information against the data-related
costs in the design of database systems. It
investigates how the usage patterns of the database,
defined by the characteristics of information requests
presented to it, affect its conceptual design. The
construction of minimum-cost answers to information
requests for a variety of query types and cost
structures is also studied. The resulting costs of
incomplete database information are balanced against
the data-related costs in the derivation of the optimal
design.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Rochester, Rochester, NY, USA",
affiliationaddress = "Univ of Rochester, Rochester, NY, USA",
annote = "information value, missing data, decision theory
framework, applied to ships in the Mediterranean.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Economics; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data-related costs, design; database systems; design;
economics; incomplete information costs; optimization;
theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.1.1}: Information Systems,
MODELS AND PRINCIPLES, Systems and Information Theory.
{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval.",
}
@Article{Ginsburg:1986:CTS,
author = "Seymour Ginsburg and Katsumi Tanaka",
title = "Computation-Tuple Sequences and Object Histories",
journal = j-TODS,
volume = "11",
number = "2",
pages = "186--212",
month = jun,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "848 634",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-2/p186-ginsburg/p186-ginsburg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-2/p186-ginsburg/;
http://www.acm.org/pubs/toc/Abstracts/tods/5924.html",
abstract = "A record-based, algebraically-oriented model is
introduced for describing data for ``object histories''
(with computation), such as checking accounts, credit
card accounts, taxes, schedules, and so on. The model
consists of sequences of computation tuples defined by
a computation-tuple sequence scheme (CSS). The CSS has
three major features (in addition to input data):
computation (involving previous computation tuples),
``uniform'' constraints (whose satisfaction by a
computation-tuple sequence $u$ implies satisfaction by
every interval of $u$ ), and specific sequences with
which to start the valid computation-tuple sequences. A
special type of CSS, called ``local,'' is singled out
for its relative simplicity in maintaining the validity
of a computation-tuple sequence. A necessary and
sufficient condition for a CSS to be equivalent to at
least one local CSS is given. Finally, the notion of
``local bisimulatability'' is introduced for regarding
two CSS as conveying the same information, and two
results on local bisimulatability in connection with
local CSS are established.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Southern California, Los Angeles, CA, USA",
affiliationaddress = "Univ of Southern California, Los Angeles, CA,
USA",
annote = "Sequential history tuples and objects with input,
computation, and result. Some constraints applied per
sequential entry cause satisfaction of global
constraints. Temporal issues are very specific.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computation history; data description; database state
transitions; database systems; theory; transaction
processing, algorithms; verification",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.1.0}: Information
Systems, MODELS AND PRINCIPLES, General. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing.",
}
@Article{Garg:1986:OPK,
author = "Anil K. Garg and C. C. Gotlieb",
title = "Order-Preserving Key Transformations",
journal = j-TODS,
volume = "11",
number = "2",
pages = "213--234",
month = jun,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-2/p213-garg/p213-garg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-2/p213-garg/;
http://www.acm.org/pubs/toc/Abstracts/tods/5923.html",
abstract = "File organizations based on conventional hash
functions provide faster access to the stored records
in comparison with tree-like file structures. Tree
structures such as B** plus -trees and ISAM do provide
for sequential processing, but require considerable
storage for the indices. When sequential processing is
needed a table that performs an order-preserving
transformation on keys can be used. H is an
order-preserving key transform if H(K//1) greater than
equivalent to H(K//2), for all keys K//1 greater than
K//2. We present methodologies for constructing such
key transforms, and illustrate them for some real-life
key sets. Storage requirements for the table needed to
carry out the transformation are less than those needed
for the indices.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Toronto, Toronto, Ont, Can",
affiliationaddress = "Univ of Toronto, Toronto, Ont, Can",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Management; Measurement;
Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access methods, algorithms; data processing; database
systems; design; dynamic files; file organization; key
transformations; management; measurement;
order-preserving hashing; performance; theory",
subject = "{\bf E.5}: Data, FILES, Organization/structure. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods.",
}
@Article{Shapiro:1986:JPD,
author = "Leonard D. Shapiro",
title = "Join Processing in Database Systems with Large Main
Memories",
journal = j-TODS,
volume = "11",
number = "3",
pages = "239--264",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/database.bib; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-3/p239-shapiro/p239-shapiro.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-3/p239-shapiro/;
http://www.acm.org/pubs/toc/Abstracts/tods/6315.html",
abstract = "We study algorithms for computing the equijoin of two
relations in a system with a standard architecture hut
with large amounts of main memory. Our algorithms are
especially efficient when the main memory available is
a significant fraction of the size of one of the
relations to he joined; but they can be applied
whenever there is memory equal to approximately the
square root of the size of one relation. We present a
new algorithm which is a hybrid of two hash-based
algorithms and which dominates the other algorithms we
present, including sort-merge. Even in a virtual memory
environment, the hybrid algorithm dominates all the
others we study.\par
Finally, we describe how three popular tools to
increase the efficiency of joins, namely filters, Babb
arrays, and semijoins, can he grafted onto any of our
algorithms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; memory query evaluation classical simple
hybrid hash joins TODS, algorithms; performance",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.0}: Information
Systems, DATABASE MANAGEMENT, General. {\bf H.2.6}:
Information Systems, DATABASE MANAGEMENT, Database
Machines. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design.",
}
@Article{Gavish:1986:SQO,
author = "Bezalel Gavish and Arie Segev",
title = "Set Query Optimization in Distributed Database
Systems",
journal = j-TODS,
volume = "11",
number = "3",
pages = "265--293",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-3/p265-gavish/p265-gavish.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-3/p265-gavish/;
http://www.acm.org/pubs/toc/Abstracts/tods/6488.html",
abstract = "This paper addresses the problem of optimizing queries
that involve set operations (set queries) in a
distributed relational database system. A particular
emphasis is put on the optimization of such queries in
horizontally partitioned database systems. A
mathematical programming model of the set query problem
is developed and its NP-completeness is proved.
Solution procedures are proposed and computational
results presented. One of the main results of the
computational experiments is that, for many queries,
the solution procedures are not sensitive to errors in
estimating the size of results of set operations.",
acknowledgement = ack-nhfb,
annote = "The time complexity is NP-complete. Three
approximations.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; languages; theory",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf G.2.2}: Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Trees.
{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing.",
}
@Article{Lafortune:1986:STM,
author = "St{\'e}phane Lafortune and Eugene Wong",
title = "A State Transition Model for Distributed Query
Processing",
journal = j-TODS,
volume = "11",
number = "3",
pages = "294--322",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/database.bib; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/des.bib; Misc/Discrete.event.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-3/p294-lafortune/p294-lafortune.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-3/p294-lafortune/;
http://www.acm.org/pubs/toc/Abstracts/tods/6460.html",
abstract = "A state transition model for the optimization of query
processing in a distributed database system is
presented. The problem is parameterized by means of a
state describing the amount of processing that has been
performed at each site where the database is located. A
state transition occurs each time a new join or
semijoin is executed. Dynamic programming is used to
compute recursively the costs of the states and the
globally optimal solution, taking into account
communication and local processing costs. The state
transition model is general enough to account for the
possibility of parallel processing among the various
sites, as well as for redundancy in the database. The
model also permits significant reductions of the
necessary computations by taking advantage of simple
additivity and site-uniformity properties of a cost
model, and of clever strategies that improve on the
basic dynamic programming algorithm.",
acknowledgement = ack-nhfb,
bib = "koz",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory, Optimization
TODS",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Distributed
systems. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing.",
}
@Article{Lozinskii:1986:POI,
author = "Eliezer L. Lozinskii",
title = "A Problem-Oriented Inferential Database System",
journal = j-TODS,
volume = "11",
number = "3",
pages = "323--356",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68T20)",
MRnumber = "87k:68025",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-3/p323-lozinskii/p323-lozinskii.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-3/p323-lozinskii/;
http://www.acm.org/pubs/toc/Abstracts/tods/6419.html",
abstract = "Recently developed inferential database systems face
some common problems: a very fast growth of search
space and difficulties in recognizing inference
termination (especially for recursive axioms). These
shortcomings stem mainly from the fact that the
inference process is usually separated from database
operations. A problem-oriented inferential system i8
described which refers to the database prior to query
(or subquery) processing, so that the inference from
the very beginning is directed by data relevant to the
query. A multiprocessor implementation of the system is
presented based on a computer network conforming to
database relations and axioms. The system provides an
efficient indication of query termination, and is
complete in the sense that it produces all correct
answers to a query in a finite time.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory;
Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory;
verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving, Deduction. {\bf C.1.3}: Computer
Systems Organization, PROCESSOR ARCHITECTURES, Other
Architecture Styles, Data-flow architectures.",
}
@Article{Osborn:1986:DRD,
author = "Sylvia L. Osborn and T. E. Heaven",
title = "The Design of a Relational Database System with
Abstract Data Types for Domains",
journal = j-TODS,
volume = "11",
number = "3",
pages = "357--373",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-3/p357-osborn/p357-osborn.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-3/p357-osborn/;
http://www.acm.org/pubs/toc/Abstracts/tods/6461.html",
abstract = "An extension to the relational model is described in
which domains can he arbitrarily defined as abstract
data types. Operations on these data types include
primitive operations, aggregates, and transformations.
It is shown that these operations make the query
language complete in the sense of Chandra and Harel.
The system has been designed in such a way that new
data types and their operations can be defined with a
minimal amount of interaction with the database
management system.",
acknowledgement = ack-nhfb,
annote = "Operations on simple objects, operations on aggregates
and `transformations' can be defined on relations. It
is possible to implement a transitive closure RAD uses
the data dictionary. ---Ong, Fogg and Stonebraker.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf D.3.3}: Software,
PROGRAMMING LANGUAGES, Language Constructs and
Features, Abstract data types. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages.",
}
@Article{Gawlick:1986:RIW,
author = "Dieter Gawlick",
title = "Report on the International Workshop on
High-Performance Transaction Systems",
journal = j-TODS,
volume = "11",
number = "4",
pages = "375--377",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p375-gawlick/p375-gawlick.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p375-gawlick/;
http://www.acm.org/pubs/toc/Abstracts/tods/17346.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; performance",
subject = "{\bf A.0}: General Literature, GENERAL. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing. {\bf C.4}: Computer Systems
Organization, PERFORMANCE OF SYSTEMS, Reliability,
availability, and serviceability.",
}
@Article{Mohan:1986:TMR,
author = "C. Mohan and B. Lindsay and R. Obermarck",
title = "Transaction Management in the {R*} Distributed
Database Management System",
journal = j-TODS,
volume = "11",
number = "4",
pages = "378--396",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p378-mohan/p378-mohan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p378-mohan/;
http://www.acm.org/pubs/toc/Abstracts/tods/7266.html",
abstract = "This paper deals with the transaction management
aspects of the R* distributed database system. It
concentrates primarily on the description of the R*
commit protocols, Presumed Abort (PA) and Presumed
Commit (PC). PA and PC are extensions of the
well-known, two-phase (2P) commit protocol. PA is
optimized for read-only transactions and a class of
multisite update transactions, and PC is optimized for
other classes of multisite update transactions. The
optimizations result in reduced intersite message
traffic and log writes, and, consequently, a better
response time. The paper also discusses R*'s approach
toward distributed deadlock detection and resolution.",
acknowledgement = ack-nhfb,
affiliation = "IBM, San Jose, CA, USA",
affiliationaddress = "IBM, San Jose, CA, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "commit protocols; concurrency control, RSTAR TODS,
algorithms; database systems; deadlock victim
selection; design; distributed; optimization;
reliability; transaction management",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Concurrency. {\bf D.4.1}: Software,
OPERATING SYSTEMS, Process Management, Deadlocks. {\bf
D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Synchronization. {\bf D.4.5}: Software,
OPERATING SYSTEMS, Reliability, Fault-tolerance. {\bf
D.4.7}: Software, OPERATING SYSTEMS, Organization and
Design, Distributed systems. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Recovery
and restart. {\bf H.2.7}: Information Systems, DATABASE
MANAGEMENT, Database Administration, Logging and
recovery.",
}
@Article{Bayer:1986:CTR,
author = "Rudolf Bayer",
title = "Consistency of Transactions and Random Batch",
journal = j-TODS,
volume = "11",
number = "4",
pages = "397--404",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p397-bayer/p397-bayer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p397-bayer/;
http://www.acm.org/pubs/toc/Abstracts/tods/214287.html",
abstract = "A synchronization technique and scheduling strategy is
described, which allows us to run a batch process
simultaneously with on-line transactions. The batch
process and the transactions are serialized in such a
way that consistency level 3 is achieved.",
acknowledgement = ack-nhfb,
affiliation = "Technische Univ Muenchen, West Ger",
affiliationaddress = "Technische Univ Muenchen, West Ger",
classification = "723; 913",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control, algorithms; consistency of
transactions; database systems; design; performance;
random batch; scheduling; synchronization",
subject = "{\bf D.4.1}: Software, OPERATING SYSTEMS, Process
Management. {\bf D.4.7}: Software, OPERATING SYSTEMS,
Organization and Design. {\bf E.5}: Data, FILES. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems.",
}
@Article{ONeil:1986:ETM,
author = "Patrick E. O'Neil",
title = "The {Escrow} Transactional Method",
journal = j-TODS,
volume = "11",
number = "4",
pages = "405--430",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p405-o_neil/p405-o_neil.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p405-o_neil/;
http://www.acm.org/pubs/toc/Abstracts/tods/7265.html",
abstract = "A method is presented for permitting record updates by
long-lived transactions without forbidding simultaneous
access by other users to records modified. Earlier
methods presented separately by Gawlick and Reuter are
comparable but concentrate on ``hot-spot'' situations,
where even short transactions cannot lock frequently
accessed fields without causing bottlenecks. The Escrow
Method offered here is designed to support nonblocking
record updates by transactions that are ``long lived''
and thus require long periods to complete.
Recoverability of intermediate results prior to commit
thus becomes a design goal, so that updates as of a
given time can be guaranteed against memory or media
failure while still retaining the prerogative to abort.
This guarantee basically completes phase one of a
two-phase commit, and several advantages result: (1) As
with Gawlick's and Reuter's methods, high-concurrency
items in the database will not act as a bottleneck; (2)
transaction commit of different updates can be
performed asynchronously, allowing natural distributed
transactions; indeed, distributed transactions in the
presence of delayed messages or occasional line
disconnection become feasible in a way that we argue
will tie up minimal resources for the purpose intended;
and (3) it becomes natural to allow for human
interaction in the middle of a transaction without loss
of concurrent access or any special difficulty for the
application programmer. The Escrow Method, like
Gawlick's Fast Path and Reuter's Method, requires the
database system to be an ``expert'' about the type of
transactional updates performed, most commonly updates
involving incremental changes to aggregate quantities.
However, the Escrow Method is extendable to other types
of updates.",
acknowledgement = ack-nhfb,
affiliation = "Computer Corp of America, Cambridge, MA, USA",
affiliationaddress = "Computer Corp of America, Cambridge, MA, USA",
annote = "For aggregate values (counts, sum) concurrency control
can use soft tolerances and keep them in escrow",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; design; escrow transactional method;
long-lived transactions; multiuser environment, locking
quantities, not variables TODS, algorithms; nested
transactions; performance; theory; two-phase commit",
subject = "{\bf D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Concurrency. {\bf D.4.1}: Software,
OPERATING SYSTEMS, Process Management, Deadlocks. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Recovery and restart. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Escrow. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing.",
}
@Article{Hsu:1986:PTP,
author = "Meichun Hsu and Arvola Chan",
title = "Partitioned Two-Phase Locking",
journal = j-TODS,
volume = "11",
number = "4",
pages = "431--446",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p431-hsu/p431-hsu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p431-hsu/;
http://www.acm.org/pubs/toc/Abstracts/tods/7477.html",
abstract = "In a large integrated database, there often exists an
``information hierarchy,'' where both raw data and
derived data are stored and used together. Therefore,
among update transactions, there will often be some
that perform only read accesses from a certain (i.e.,
the ``raw'' data) portion of the database and write
into another (i.e., the ``derived'' data) portion. A
conventional concurrency control algorithm would have
treated such transactions as regular update
transactions and subjected them to the usual protocols
for synchronizing update transactions. In this paper
such transactions are examined more closely. The
purpose is to devise concurrency control methods that
allow the computation of derived information to proceed
without interfering with the updating of raw data.
\par
The first part of the paper presents a proof method for
correctness of concurrency control algorithms in a
hierarchically decomposed database. The proof method
provides a framework for understanding the intricacies
in dealing with hierarchically decomposed databases.
The second part of the paper is an application of the
proof method to show the correctness of a
two-phase-locking- based algorithm, called partitioned
two-phase locking, for hierarchically decomposed
databases. This algorithm is a natural extension to the
Version Pool method proposed previously in the
literature.",
acknowledgement = ack-nhfb,
affiliation = "Harvard Univ, Cambridge, MA, USA",
affiliationaddress = "Harvard Univ, Cambridge, MA, USA",
annote = "revisions also for update",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; concurrency
control; database systems; theory; transaction
processing, algorithms; two-phase locking",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design.",
}
@Article{Luk:1986:EEL,
author = "W. S. Luk and Steve Kloster",
title = "{ELFS}: {English} Language from {SQL}",
journal = j-TODS,
volume = "11",
number = "4",
pages = "447--472",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Dec 8 08:54:10 MST 1996",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this paper we describe a system which, given a
query in SQL-like relational database language, will
display its meaning in clear, unambiguous natural
language. The syntax-driven translation mechanism is
independent of the application domain. It has direct
applications in designing computer-based SQL tutorial
systems and program debugging systems. The research
results obtained in the paper will also be useful in
query optimization and design of a more user-friendly
language front-end for casual users.",
acknowledgement = ack-nhfb,
affiliation = "Simon Fraser Univ, Burnaby, BC, Can",
affiliationaddress = "Simon Fraser Univ, Burnaby, BC, Can",
annote = "display meaning in natural language is independent of
the application domain.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- Program Debugging; database
systems; ELFS; Query Languages; relational database
language; SQL",
}
@Article{Sacco:1986:BMR,
author = "Giovanni Maria Sacco and Mario Schkolnick",
title = "Buffer Management in Relational Database Systems",
journal = j-TODS,
volume = "11",
number = "4",
pages = "473--498",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p473-sacco/p473-sacco.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p473-sacco/;
http://www.acm.org/pubs/toc/Abstracts/tods/7336.html",
abstract = "The hot-set model, characterizing the buffer
requirements of relational queries, is presented. This
model allows the system to determine the optimal buffer
space to be allocated to a query; it can also be used
by the query optimizer to derive efficient execution
plans accounting for the available buffer space, and by
a query scheduler to prevent thrashing. The hot-set
model is compared with the working-set model. A
simulation study is presented.",
acknowledgement = ack-nhfb,
acmcr = "8708-0695",
affiliation = "Univ di Torino",
affiliationaddress = "Turin, Italy",
annote = "The hot-set model provides a more meaningful measure
of cost than simple I/O counts.",
classification = "723; 913",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "buffer management; database systems; performance;
query optimizer, algorithms; query processing;
relational; scheduling; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design. {\bf
D.4.2}: Software, OPERATING SYSTEMS, Storage
Management.",
}
@Article{Ariav:1986:TOD,
author = "Gad Ariav",
title = "A Temporally Oriented Data Model",
journal = j-TODS,
volume = "11",
number = "4",
pages = "499--527",
month = dec,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1986-11-4/p499-ariav/p499-ariav.pdf;
http://www.acm.org/pubs/citations/journals/tods/1986-11-4/p499-ariav/;
http://www.acm.org/pubs/toc/Abstracts/tods/7350.html",
abstract = "The research into time and data models has so far
focused on the identification of extensions to the
classical relational model that would provide it with
``adequate'' semantic capacity to deal with time. The
temporally oriented data model (TODM) presented in this
paper is a result of a different approach, namely, it
directly operationalizes the pervasive
three-dimensional metaphor for time. One of the main
results is thus the development of the notion of the
data cube: a three-dimensional and inherently temporal
data construct where time, objects, and attributes are
the primary dimensions of stored data. TODM's cube adds
historical depth to the tabular notions of data and
provides a framework for storing and retrieving data
within their temporal context. The basic operations in
the model allow the formation of new cubic views from
existing ones, or viewing data as one moves up and down
in time within cubes.\par
This paper introduces TODM, a consistent set of
temporally oriented data constructs, operations, and
constraints, and then presents TOSQL, a corresponding
end-user's SQL-like query syntax. The model is a
restricted but consistent superset of the relational
model, and the query syntax incorporates temporal
notions in a manner that likewise avoids penalizing
users who are interested solely in the current view of
data (rather than in a temporal perspective). The
naturalness of the spatial reference to time and the
added semantic capacity of TODM come with a price--the
definitions of the cubic constructs and basic
operations are relatively cumbersome. As rudimentary as
it is, TODM nonetheless provides a comprehensive basis
for formulating an external data model for a temporally
oriented database.",
acknowledgement = ack-nhfb,
affiliation = "New York Univ, New York, NY, USA",
affiliationaddress = "New York Univ, New York, NY, USA",
annote = "at least one timestamp, time of record, plus other
temporal --- event stamps.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data cube; database systems; information modeling;
languages; relational; temporally oriented data model;
theory; TODM, design; TOSQL",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML). {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages.",
}
@Article{Albano:1986:OSG,
author = "Antonio Albano and S. Alfo and Luca Cardelli and Renzo
Orsini",
title = "An Overview of {SIDEREUS}: a Graphical Database Schema
Editor for {Galileo}",
journal = j-TODS,
volume = "11",
number = "??",
pages = "568--571",
month = "????",
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:51:20 1996",
bibsource = "Distributed/gesturing.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Durand:1986:FMS,
author = "Charles Durand",
title = "Forward Multidimensional Search with Applications to
Information Retrieval",
journal = j-TODS,
volume = "??",
number = "??",
pages = "??--??",
month = sep,
year = "1986",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:51:25 1996",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Submitted.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Spyratos:1987:PMD,
author = "Nicolas Spyratos",
title = "The partition model: a deductive database model",
journal = j-TODS,
volume = "12",
number = "1",
pages = "1--37",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Institut National de la
Recherche en Informatique et Automatique, TR-286, Apr.
1983.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-1/p1-spyratos/p1-spyratos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-1/p1-spyratos/;
http://www.acm.org/pubs/toc/Abstracts/tods/22718.html",
abstract = "We present a new database model in which each
attribute is modeled by a family of disjoint subsets of
an underlying population of objects. Such a family is
called a partitioning, and the set of all partitionings
is turned into a lattice by appropriately defining
product and sum. A database is seen as a function from
a sublattice into the lattice of partitionings. The
model combines the following features:\par
(1) syntactic simplicity (essentially that of the
relational model),\par
(2) powerful means for the specification of semantic
information (in the form of lattice equations), and
\par
(3) deductive capability (essentially that of set
theory).\par
The relational model of data and the basic constructs
of semantic modeling can be embedded into our model in
a simple and straightforward manner.",
acknowledgement = ack-nhfb,
affiliation = "Univ de Paris-Sud, Orsay, Fr",
affiliationaddress = "Univ de Paris-Sud, Orsay, Fr",
annote = "Type hierarchies and lattices.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database semantics; database systems; deductive
database model; partition model; theory",
subject = "{\bf F.3.2}: Theory of Computation, LOGICS AND
MEANINGS OF PROGRAMS, Semantics of Programming
Languages, Algebraic approaches to semantics. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models.",
}
@Article{Wu:1987:ASM,
author = "C. T. Wu and Walter A. Burkhard",
title = "Associative Searching in Multiple Storage Units",
journal = j-TODS,
volume = "12",
number = "1",
pages = "38--64",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Discusses interpolation hashing, a multidimensional
variant of linear hashing.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-1/p38-wu/p38-wu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-1/p38-wu/;
http://www.acm.org/pubs/toc/Abstracts/tods/12048.html",
abstract = "A file maintenance model, called the multiple random
access storage units model, is introduced. Storage
units can be accessed simultaneously, and the parallel
processing of an associative query is achieved by
distributing data evenly among the storage units.
Maximum parallelism is obtained when data satisfying an
associative query are evenly distributed for every
possible query. An allocation scheme called $M$-cycle
allocation is proposed to maintain large files of data
on multiple random access storage units. The allocation
scheme provides an efficient and straightforward
indexing over multidimensional key spaces and supports
the parallel processing of orthogonal range queries.
Our analysis shows that $M$-cycle allocation achieves
the near-optimum parallelism for processing the
orthogonal range queries. Moreover, there is no
duplication of records and no increase in
insertion\slash deletion cost.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, San Diego, CA, USA",
affiliationaddress = "Univ of California, San Diego, CA, USA",
classification = "723; 903",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "associative searching; data processing --- file
organization; database systems; design; file
maintenance model; information science --- information
retrieval; multiple storage units; performance; random
access, algorithms; theory",
subject = "{\bf E.5}: Data, FILES. {\bf E.1}: Data, DATA
STRUCTURES. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design.",
}
@Article{Lomet:1987:PEF,
author = "David B. Lomet",
title = "Partial Expansions for File Organizations with an
Index",
journal = j-TODS,
volume = "12",
number = "1",
pages = "65--84",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-1/p65-lomet/p65-lomet.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-1/p65-lomet/;
http://www.acm.org/pubs/toc/Abstracts/tods/12049.html",
abstract = "A new way to increase file space in dynamically
growing files is introduced in which substantial
improvement in file utilization can be achieved. It
makes use of partial expansions in which, instead of
doubling the space associated with some part of the
file, the space grows at a slower rate. Unlike previous
versions of partial expansion in which the number of
buckets involved in file growth is increased by less
than a factor of two, the new method expands file space
by increasing bucket size via `elastic buckets'. This
permits partial expansions to be used with a wide range
of indexed files, including B-trees. The results of
using partial expansions are analyzed, and the analysis
confirmed by a simulation study. The analysis and
simulation demonstrate that the file utilization gains
are substantial and that fears of excessive insertion
cost resulting from more frequent file growth are
unfounded.",
acknowledgement = ack-nhfb,
affiliation = "Wang Inst of Graduate Studies, Tyngboro, MA, USA",
affiliationaddress = "Wang Inst of Graduate Studies, Tyngboro, MA,
USA",
annote = "a way to increase file space with substantial
improvement in file utilization elastic buckets come in
a number of sizes.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; database systems; File Organization;
FILE UTILIZATION; INSERTION COST; PARTIAL EXPANSIONS",
subject = "{\bf D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, Access methods. {\bf D.4.3}: Software,
OPERATING SYSTEMS, File Systems Management, File
organization. {\bf H.2.2}: Information Systems,
DATABASE MANAGEMENT, Physical Design, Access methods.
{\bf H.3.2}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Storage, File
organization.",
}
@Article{Fedorowicz:1987:DPE,
author = "Jane Fedorowicz",
title = "Database Performance Evaluation in an Indexed File
Environment",
journal = j-TODS,
volume = "12",
number = "1",
pages = "85--110",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-1/p85-fedorowicz/p85-fedorowicz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-1/p85-fedorowicz/;
http://www.acm.org/pubs/toc/Abstracts/tods/13675.html",
abstract = "The use of database systems for managerial decision
making often incorporates information-retrieval
capabilities with numeric report generation. Of great
concern to the user of such a system is the response
time associated with issuing a query to the database.
This study presents a procedure for estimating response
time for one of the most frequently encountered
physical storage mechanisms, the indexed file. The
model provides a fairly high degree of accuracy, but is
simple enough so that the cost of applying the model is
not exorbitant. The model incorporates the knowledge
that the distribution of access key occurrences is
known to follow Zipf's law. It first estimates the
access time required to complete the query, which
includes the time needed for all input and output
transactions, and CPU time used in performing the
search. The effects of multiple users on an
individual's response time are then assessed using a
simple regression estimation technique. The two-step
procedure allows for the separation of access time from
multiuser influences.",
acknowledgement = ack-nhfb,
affiliation = "Boston Univ, Boston, MA, USA",
affiliationaddress = "Boston Univ, Boston, MA, USA",
annote = "a procedure for estimating response time; distribution
of access key occurrences follow Zipf's law. Early
version with Kellogg, J. L. Model provides a fairly
high degree of accuracy but is simple. The effects of
multiple users are assessed using simple regression
estimation.",
classification = "723; 912; 922",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing --- File organization; database
performance; database systems; indexed file
environment; MANAGEMENT --- Information Systems;
multiple users, design; Performance; performance;
response time; statistical methods --- regression
analysis; Zipf's law",
subject = "{\bf D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, File organization. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.3.2}: Information Systems, INFORMATION
STORAGE AND RETRIEVAL, Information Storage, File
organization. {\bf H.3.3}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Search
and Retrieval, Retrieval models.",
}
@Article{Ozsoyoglu:1987:NNF,
author = "Z. Meral {\"O}zsoyo{\u{g}}lu and Li-Yan Yuan",
title = "A New Normal Form for Nested Relations",
journal = j-TODS,
volume = "12",
number = "1",
pages = "111--136",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "886 100",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-1/p111-ozsoyoglu/p111-ozsoyoglu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-1/p111-ozsoyoglu/;
http://www.acm.org/pubs/toc/Abstracts/tods/13676.html",
abstract = "We consider nested relations whose schemes are
structured as trees, called scheme trees, and introduce
a normal form for such relations, called the nested
normal form. Given a set of attributes $U$, and a set
of multivalued dependencies (MVDs) $M$ over these
attributes, we present an algorithm to obtain a nested
normal form decomposition of $U$ with respect to $M$.
Such a decomposition has several desirable properties,
such as explicitly representing a set of full and
embedded MVDs implied by $M$, and being a faithful and
nonredundant representation of $U$. Moreover, if the
given set of MVDs is conflict-free, then the nested
normal form decomposition is also
dependency-preserving. Finally, we show that if $M$ is
conflict-free, then the set of root-to-leaf paths of
scheme trees in nested normal form decomposition is
precisely the unique 4NF decomposition $ [9, 16] $ of
$U$ with respect to $M$.",
acknowledgement = ack-nhfb,
affiliation = "Case Western Reserve Univ, Cleveland, OH, USA",
affiliationaddress = "Case Western Reserve Univ, Cleveland, OH, USA",
annote = "non-first normal form.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; data structures; database systems ---
design; decomposition, algorithms; design; multivalued
dependency; nested relations; normal form; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Normal
forms.",
}
@Article{Christodoulakis:1987:ARP,
author = "Stavros Christodoulakis",
title = "Analysis of Retrieval Performance for Records and
Objects using Optical Disk Technology",
journal = j-TODS,
volume = "12",
number = "2",
pages = "137--169",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p137-christodoulakis/p137-christodoulakis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p137-christodoulakis/;
http://www.acm.org/pubs/toc/Abstracts/tods/23015.html",
abstract = "In this paper we examine the problem of object and
record retrieval from optical disks. General objects
(such as images, documents, etc.) may be long and their
length may have high variance. We assume that all the
components of an object are stored consecutively in
storage to speed-up retrieval performance. We first
present an optical disk model and an optimal schedule
for retrieval of records and objects which qualify in a
single query on a file stored on an optical disk
device. We then provide {\em exact\/} and {\em
approximate\/} analytic results for evaluating the
retrieval performance for objects from an optical disk.
The analysis provides some basic analytic tools for
studying the performance of various file and database
organizations for optical disks. The results involve
probability distribution of block accesses, probability
distributions of span accesses, and probability
distribution of seek times. Record retrieval is an
important special case. This analysis differs from
similar ones in database environments in the following
respects: (1) the large size and large variance of the
size of objects; (2) crossing of track boundaries by
objects; (3) the capability for span access that
optical disks provide (e.g., when the optical assembly
is located in a given position, information can be read
from a number of consecutive tracks (span) with a small
additional cost).",
acknowledgement = ack-nhfb,
affiliation = "Univ of Waterloo, Waterloo, Ont, Can",
affiliationaddress = "Univ of Waterloo, Waterloo, Ont, Can",
classification = "723; 741; 903",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Measurement; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data storage, optical --- storage devices; information
retrieval; information science; optical disk
technology, measurement; performance; retrieval
performance; theory",
subject = "{\bf C.4}: Computer Systems Organization, PERFORMANCE
OF SYSTEMS, Modeling techniques. {\bf D.4.3}: Software,
OPERATING SYSTEMS, File Systems Management, File
organization.",
}
@Article{Herlihy:1987:DQA,
author = "Maurice Herlihy",
title = "Dynamic Quorum Adjustment for Partitioned Data",
journal = j-TODS,
volume = "12",
number = "2",
pages = "170--194",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p170-herlihy/p170-herlihy.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p170-herlihy/;
http://www.acm.org/pubs/toc/Abstracts/tods/22953.html",
abstract = "A partition occurs when functioning sites in a
distributed system are unable to communicate. This
paper introduces a new method for managing replicated
data objects in the presence of partitions. Each
operation provided by a replicated object has a set of
quorums, which are sets of sites whose cooperation
suffices to execute the operation. The method permits
an object's quorums to be adjusted dynamically in
response to failures and recoveries. A transaction that
is unable to progress using one set of quorums may
switch to another, more favorable set, and transactions
in different partitions may progress using different
sets. This method has three novel aspects: (1) it
supports a wider range of quorums than earlier
proposals, (2) it scales up effectively to large
systems because quorum adjustments do not require
global reconfiguration, and (3) it systematically
exploits the semantics of typed objects to support more
flexible quorum adjustment.",
acknowledgement = ack-nhfb,
affiliation = "Carnegie-Mellon Univ, Pittsburgh, PA, USA",
affiliationaddress = "Carnegie-Mellon Univ, Pittsburgh, PA, USA",
annote = "Each operation provided by a replicated object has a
set of quorums, sites whose cooperation suffices to
execute the operation.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer systems, digital --- distributed; database
systems; distributed; dynamic quorum adjustment;
languages; partitioned data, algorithms; reliability",
subject = "{\bf D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Abstract data types. {\bf
D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, Distributed file systems. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf D.3.3}: Software, PROGRAMMING
LANGUAGES, Language Constructs and Features, Data types
and structures. {\bf D.4.5}: Software, OPERATING
SYSTEMS, Reliability, Fault-tolerance. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing.",
}
@Article{Ellis:1987:CLH,
author = "Carla Schlatter Ellis",
title = "Concurrency in Linear Hashing",
journal = j-TODS,
volume = "12",
number = "2",
pages = "195--217",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite{ACM:1985:PFA}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p195-ellis/p195-ellis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p195-ellis/;
http://www.acm.org/pubs/toc/Abstracts/tods/22954.html",
abstract = "Concurrent access to complex shared data structures,
particularly structures useful as database indices, has
long been of interest in the database community. In
dynamic databases, tree structures such as B-trees have
been used as indices because of their ability to handle
growth; whereas hashing has been used for fast access
in relatively static databases. Recently, a number of
techniques for dynamic hashing have appeared. They
address the major deficiency of traditional hashing
when applied to databases that experience significant
change in the amount of data being stored. This paper
presents a solution that allows concurrency in one of
these dynamic hashing data structures, namely linear
hash files. The solution is based on locking protocols
and minor modifications in the data structures.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Rochester, USA",
affiliationaddress = "Univ of Rochester, USA",
annote = "Searching can proceed in parallel with splits. Also
discusses distributed access.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "complex shared data structures, algorithms; concurrent
access; data processing; Data Structures; database
systems; linear hashing",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf D.4.1}: Software, OPERATING
SYSTEMS, Process Management,
Multiprocessing/multiprogramming. {\bf E.1}: Data, DATA
STRUCTURES. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design. {\bf H.3.2}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Storage, File organization.",
}
@Article{Valduriez:1987:JI,
author = "Patrick Valduriez",
title = "Join Indices",
journal = j-TODS,
volume = "12",
number = "2",
pages = "218--246",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Compares join indices with inverted indices, clustered
indices, B+ trees, linked lists, and hybrid hash
techniques.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p218-valduriez/p218-valduriez.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p218-valduriez/;
http://www.acm.org/pubs/toc/Abstracts/tods/22955.html",
abstract = "In new application areas of relational database
systems, such as artificial intelligence, the join
operator is used more extensively than in conventional
applications. In this paper, we propose a simple data
structure, called a join index, for improving the
performance of joins in the context of complex queries.
For most of the joins, updates to join indices incur
very little overhead. Some properties of a join index
are (i) its efficient use of memory and adaptiveness to
parallel execution, (ii) its compatibility with other
operations (including select and union), (iii) its
support for abstract data type join predicates, (iv)
its support for multirelation clustering, and (v) its
use in representing directed graphs and in evaluating
recursive queries. Finally, the analysis of the join
algorithm using join indices shows its excellent
performance.",
acknowledgement = ack-nhfb,
affiliation = "Microelectronics \& Computer Technology Corp, Austin,
TX, USA",
affiliationaddress = "Microelectronics \& Computer Technology Corp,
Austin, TX, USA",
annote = "arrays of combined indices are maintained to
precompute joins among tuples. The technique is very
similar to that implemented as ADABAS correlators.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data types; computer programming ---
Algorithms; data processing --- Data Structures;
database systems; design; join algorithm, including
semi-join join index with rid list from selection index
TODS, algorithms; JOIN index; multirelation clustering;
performance; Relational",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf E.1}: Data, DATA
STRUCTURES, Trees. {\bf E.5}: Data, FILES,
Organization/structure. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf H.3.1}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Content Analysis and Indexing, Indexing methods.",
}
@Article{Snodgrass:1987:TQL,
author = "Richard Snodgrass",
title = "The {Temporal Query Language TQUEL}",
journal = j-TODS,
volume = "12",
number = "2",
pages = "247--298",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p247-snodgrass/p247-snodgrass.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p247-snodgrass/;
http://www.acm.org/pubs/toc/Abstracts/tods/22956.html",
abstract = "Recently, attention has been focused on {\em temporal
databases}, representing an enterprise over time. We
have developed a new language, {\em Tquel}, to query a
temporal database. TQuel was designed to be a minimal
extension, both syntactically and semantically, of
Quel, the query language in the Ingres relational
database management system. This paper discusses the
language informally, then provides a tuple relational
calculus semantics for the TQuel statements that differ
from their Quel counterparts, including the
modification statements. The three additional temporal
constructs defined in Tquel are shown to be direct
semantic analogues of Quel's where clause and target
list. We also discuss reducibility of the semantics to
Quel's semantics when applied to a static database.
TQuel is compared with ten other query languages
supporting time.",
acmcrnumber = "8712-1006",
affiliation = "Univ of North Carolina, Chapel Hill, NC, USA",
affiliationaddress = "Univ of North Carolina, Chapel Hill, NC, USA",
annote = "Describes extensions to Quel to handle temporal
queries. Three kinds of temporal information are
handled: `Transaction time', when information was
stored in the database, `valid time' when the stored
info models reality, and `user-defined time' explicitly
stored by user in the database.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; database systems;
relational calculus; temporal databases; temporal query
language; theory; TQUEL; tuple calculus, languages",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.7}: Information
Systems, DATABASE MANAGEMENT, Database Administration,
Logging and recovery. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Query languages. {\bf
H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, TQUEL.",
}
@Article{Wong:1987:MIR,
author = "S. K. M. Wong and W. Ziarko and V. V. Raghavan and P.
C. N. Wong",
title = "On Modeling of Information Retrieval Concepts in
Vector Spaces",
journal = j-TODS,
volume = "12",
number = "2",
pages = "299--321",
month = jun,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-2/p299-wong/p299-wong.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-2/p299-wong/;
http://www.acm.org/pubs/toc/Abstracts/tods/22957.html",
abstract = "The Vector Space Model (VSM) has been adopted in
information retrieval as a means of coping with inexact
representation of documents and queries, and the
resulting difficulties in determining the relevance of
a document relative to a given query. The major problem
in employing this approach is that the explicit
representation of term vectors is not known a priori.
Consequently, earlier researchers made the assumption
that the vectors corresponding to terms are pairwise
orthogonal. Such an assumption is clearly unrealistic.
Although attempts have been made to compensate for this
assumption by some separate, corrective steps, such
methods are ad hoc and, in most cases, formally
inconsistent.\par
In this paper, a generalization of the VSM, called the
GVSM, is advanced. The developments provide a solution
not only for the computation of a measure of similarity
(correlation) between terms, but also for the
incorporation of these similarities into the retrieval
process.\par
The major strength of the GVSM derives from the fact
that it is theoretically sound and elegant.
Furthermore, experimental evaluation of the model on
several test collections indicates that the performance
is better than that of the VSM. Experiments have been
performed on some variations of the GVSM, and all these
results have also been compared to those of the VSM,
based on inverse document frequency weighting. These
results and some ideas for the efficient implementation
of the GVSM are discussed.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Regina, Regina, Sask, Can",
affiliationaddress = "Univ of Regina, Regina, Sask, Can",
annote = "The space for both documents and queries is an
n-dimensional vector space. In GVSM, terms are not
assumed to be linearly independent; measure of
independence is based on the number of common
documents.",
classification = "723; 903",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Experimentation; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "document representation; experimentation; generalized
vector space; Information Retrieval; information
retrieval systems --- Mathematical Models; information
science; languages; query representation, design;
theory",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf H.3.1}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Content Analysis and
Indexing, Thesauruses. {\bf H.3.1}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Content
Analysis and Indexing, Indexing methods. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval.",
}
@Article{Rybinski:1987:FOL,
author = "Henryk Rybi{\'n}ski",
title = "On First-Order-Logic Databases",
journal = j-TODS,
volume = "12",
number = "3",
pages = "325--349",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (03B70)",
MRnumber = "88j:68033",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p325-rybinski/p325-rybinski.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p325-rybinski/;
http://www.acm.org/pubs/toc/Abstracts/tods/27630.html",
abstract = "The use of first-order logic as database logic is
shown to be powerful enough for formalizing and
implementing not only relational but also hierarchical
and network-type databases. It enables one to treat all
the types of databases in a uniform manner. This paper
focuses on the database language for heterogeneous
databases. The language is shown to be general enough
to specify constraints for a particular type of
database, so that a specification of database type can
be ``translated'' to the specification given in the
database language, creating a ``logical environment''
for different views that can be defined by users. Owing
to the fact that any database schema is seen as a
first-order theory expressed by a finite set of
sentences, the problems concerned with completeness and
compactness of the database logic discussed by Jacobs
(``On Database Logic,'' {\em J. ACM 29\/}, 2 (Apr.
1982), 310-332) are avoided.",
acknowledgement = ack-nhfb,
annote = "Successor of Jacobs's work. Language Ld can specify
constraints for any database type, which can then be
`translated' to a particular database domain.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer metatheory --- formal logic; database logic;
design; first-order logic; hierarchical databases;
languages; network databases; relational databases;
theory, database systems",
review = "ACM Computing Reviews, Jan 1989",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML). {\bf F.4.1}: Theory of
Computation, MATHEMATICAL LOGIC AND FORMAL LANGUAGES,
Mathematical Logic. {\bf I.2.4}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Knowledge
Representation Formalisms and Methods, Predicate
logic.",
}
@Article{Stonebraker:1987:EDS,
author = "Michael Stonebraker and Jeff Anton and Eric Hanson",
title = "Extending a Database System with Procedures",
journal = j-TODS,
volume = "12",
number = "3",
pages = "350--376",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: UCB/ERL memo M85/59, 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p350-stonebraker/p350-stonebraker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p350-stonebraker/;
http://www.acm.org/pubs/toc/Abstracts/tods/27631.html",
abstract = "This paper suggests that more powerful database
systems (DBMS) can be built by supporting database
procedures as full-fledged database objects. In
particular, allowing fields of a database to be a
collection of queries in the query language of the
system is shown to allow the natural expression of
complex data relationships. Moreover, many of the
features present in object-oriented systems and
semantic data models can be supported by this facility.
\par
In order to implement this construct, extensions to a
typical relational query language must be made, and
considerable work on the execution engine of the
underlying DBMS must be accomplished. This paper
reports on the extensions for one particular query
language and data manager and then gives performance
figures for a prototype implementation. Even though the
performance of the prototype is competitive with that
of a conventional system, suggestions for improvement
are presented.",
acknowledgement = ack-nhfb,
annote = "Stored procedures follow DBTG suggestions from 1971.
The INGRES+ results were `competitive'.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database procedures, design; database systems;
object-oriented systems; relational query language;
semantic data models",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing.",
}
@Article{Ozsoyoglu:1987:RMM,
author = "Z. Meral {\"O}zsoyo{\u{g}}lu and Li-Yan Yuan",
title = "Reduced {MVDs} and Minimal Covers",
journal = j-TODS,
volume = "12",
number = "3",
pages = "377--394",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "88h:68017",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p377-ozsoyoolu/;
http://www.acm.org/pubs/toc/Abstracts/tods/214286.html",
abstract = "Multivalued dependencies (MVDs) are data dependencies
that appear frequently in the ``real world'' and play
an important role in designing relational database
schemes. Given a set of MVDs to constrain a database
scheme, it is desirable to obtain an equivalent set of
MVDs that do not have any redundancies. In this paper
we define such a set of MVDs, called reduced MVDs, and
present an algorithm to obtain reduced MVDs. We also
define a minimal cover of a set of MVDs, which is a set
of reduced MVDs, and give an efficient method to find
such a minimal cover. The significance and properties
of reduced MVDs are also discussed in the context of
database design (e.g., 4NF decomposition) and
conflict-free MVDs.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; computer programming --- algorithms;
database schema design; database systems; design;
minimal covers; multivalued dependencies; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Normal
forms.",
}
@Article{Faloutsos:1987:OSE,
author = "Christos Faloutsos and Stavros Christodoulakis",
title = "Optimal Signature Extraction and Information Loss",
journal = j-TODS,
volume = "12",
number = "3",
pages = "395--428",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p395-faloutsos/p395-faloutsos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p395-faloutsos/;
http://www.acm.org/pubs/toc/Abstracts/tods/214285.html",
abstract = "Signature files seem to be a promising access method
for text and attributes. According to this method, the
documents (or records) are stored sequentially in one
file (``text file''), while abstractions of the
documents (``signatures'') are stored sequentially in
another file (``signature file''). In order to resolve
a query, the signature file is scanned first, and many
nonqualifying documents are immediately rejected. We
develop a framework that includes primary key hashing,
multiattribute hashing, and signature files. Our effort
is to find the optimal signature extraction method.
\par
The main contribution of this paper is that we present
optimal and efficient suboptimal algorithms for
assigning words to signatures in several environments.
Another contribution is that we use information theory,
and study the relationship of the false drop
probability $ F_d $ and the information that is lost
during signature extraction. We give tight lower bounds
on the achievable $ F_d $ and show that a simple
relationship holds between the two quantities in the
case of optimal signature extraction with uniform
occurrence and query frequencies. We examine hashing as
a method to map words to signatures (instead of the
optimal way), and show that the same relationship holds
between $ F_d $ and {\em loss}, indicating that an
invariant may exist between these two quantities for
every signature extraction method.",
acknowledgement = ack-nhfb,
annote = "superimposed coding",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing; database systems; information loss;
optimal signature extraction; performance; signature
files, design",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf E.4}: Data,
CODING AND INFORMATION THEORY, Data compaction and
compression. {\bf E.5}: Data, FILES. {\bf H.3.2}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Storage, File organization.",
}
@Article{Ibaraki:1987:SC,
author = "Toshihide Ibaraki and Tiko Kameda and Toshimi
Minoura",
title = "Serializability with Constraints",
journal = j-TODS,
volume = "12",
number = "3",
pages = "429--452",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "909 139",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p429-ibaraki/p429-ibaraki.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p429-ibaraki/;
http://www.acm.org/pubs/toc/Abstracts/tods/214284.html",
abstract = "This paper deals with the serializability theory for
single-version and multiversion database systems. We
first introduce the concept of {\em disjoint-interval
topological sort\/} ({\em DITS}, for short) of an
arc-labeled directed acyclic graph. It is shown that a
history is serializable if and only if its {\em
transaction IO graph\/} has a DITS. We then define
several subclasses of serializable histories, based on
the constraints imposed by write-write, write-read,
read-write, or read-read conflicts, and investigate
inclusion relationships among them. In terms of DITS,
we give a sufficient condition for a class of
serializable histories to be polynomially recognizable,
which is then used to show that a new class of
histories, named WRW, can be recognized in polynomial
time. We also present NP-completeness results for the
problem of testing membership in some other classes.
\par
In the second half of this paper, we extend these
results to multiversion database systems. The inclusion
relationships among multiversion classes defined by
constraints, such as write-write and write-read, are
investigated. One such class coincides with class
DMVSR, introduced by Papadimitriou and Kanellakis, and
gives a simple characterization of this class. It is
shown that for most constraints, multiversion classes
properly contain the corresponding single-version
classes. Complexity results for the membership testing
are also discussed.",
acknowledgement = ack-nhfb,
annote = "classification and properties of conflict graphs, with
and without versions.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer systems programming --- sorting; concurrency
control; database systems; disjoint-interval
topological sort, algorithms; serializability; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing.",
}
@Article{Wolfson:1987:OLC,
author = "Ouri Wolfson",
title = "The Overhead of Locking (and Commit) Protocols in
Distributed Databases",
journal = j-TODS,
volume = "12",
number = "3",
pages = "453--471",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p453-wolfson/p453-wolfson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p453-wolfson/;
http://www.acm.org/pubs/toc/Abstracts/tods/28053.html",
abstract = "The main purpose of a locking protocol is to ensure
correct interleaving of actions executed by concurrent
transactions. The locking protocol consists of a set of
rules dictating how accessed entities should be locked
and unlocked. As a result of obeying the rules,
transactions in a distributed database incur an
overhead. We propose three measures of evaluating this
overhead, each most suitable to a different type of
underlying communication network. Then, using a graph
theoretic model, we analyze and compare three protocols
according to each measure: two-phase locking, two-phase
locking with a fixed order imposed on the database
entities (ensuring deadlock freedom), and the tree
protocol. In practice, a transaction also executes the
two-phase commit protocol in order to guarantee
atomicity. Therefore, the combined overhead of each
locking protocol and the two-phase commit protocol is
also determined.",
acknowledgement = ack-nhfb,
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Measurement; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "commit protocols; computer networks --- protocols;
concurrency control, algorithms; database systems;
locking protocols; measurement; message passing;
performance; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf C.4}: Computer Systems
Organization, PERFORMANCE OF SYSTEMS. {\bf C.2.4}:
Computer Systems Organization, COMPUTER-COMMUNICATION
NETWORKS, Distributed Systems, Distributed databases.
{\bf D.2.8}: Software, SOFTWARE ENGINEERING, Metrics,
Performance measures. {\bf H.2.2}: Information Systems,
DATABASE MANAGEMENT, Physical Design. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing.",
}
@Article{Su:1987:CBD,
author = "Stanley Y. W. Su and Jozo Dujmovic and D. S. Batory
and S. B. Navathe and Richard Elnicki",
title = "A Cost-Benefit Decision Model: Analysis, Comparison,
and Selection of Data Management Systems",
journal = j-TODS,
volume = "12",
number = "3",
pages = "472--520",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p472-su/p472-su.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p472-su/;
http://www.acm.org/pubs/toc/Abstracts/tods/33403.html",
abstract = "This paper describes a general cost-benefit decision
model that is applicable to the evaluation, comparison,
and selection of alternative products with a
multiplicity of features, such as complex computer
systems. The application of this model is explained and
illustrated using the selection of data management
systems as an example.\par
The model has the following features: (1) it is
mathematically based on an extended continuous logic
and a theory of complex criteria; (2) the
decision-making procedure is very general yet
systematic, well-structured, and quantitative; (3) the
technique is based on a comprehensive cost analysis and
an elaborate analysis of benefits expressed in terms of
the decision maker's preferences. The decision
methodology, when applied to the problem of selecting a
data management system, takes into consideration the
life cycle of a DMS and the objectives and goals for
the new systems under evaluation. It allows the cost
and preference analyses to be carried out separately
using two different models. The model for preference
analysis makes use of comprehensive performance (or
preference) parameters and allows what we call a
``logic scoring of preferences'' using continuous
values between zero and one, to express the degree with
which candidate systems satisfy stated requirements. It
aggregates preference parameters based on their
relative weights and logical relationships to compute a
global performance (preference) score for each system.
The cost model incorporates an aggregation of costs
which may be estimated over different time horizons and
discounted at appropriate discount rates. A procedure
to establish an overall ranking of alternative systems
based on their global preference scores and global
costs is also discussed.",
acknowledgement = ack-nhfb,
annote = "The LPS model results from a NBS study. Preference
scoring, facility costs.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cost-benefit decision model; data management systems,
SYWSU TODS; database systems; mathematical models",
subject = "{\bf H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration. {\bf K.6.3}: Computing
Milieux, MANAGEMENT OF COMPUTING AND INFORMATION
SYSTEMS, Software Management. {\bf D.2.9}: Software,
SOFTWARE ENGINEERING, Management, Cost estimation.",
}
@Article{Keller:1987:CBS,
author = "Arthur M. Keller",
title = "Comment on {Bancilhon} and {Spyratos}' {``Update
semantics and relational views''}",
journal = j-TODS,
volume = "12",
number = "3",
pages = "521--523",
month = sep,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Bancilhon:1981:USR}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-3/p521-keller/p521-keller.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-3/p521-keller/;
http://www.acm.org/pubs/toc/Abstracts/tods/214296.html",
acknowledgement = ack-nhfb,
annote = "a small relaxation of constraints increases the
feasibility of view update",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; theory",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf H.2.1}: Information Systems,
DATABASE MANAGEMENT, Logical Design, Data models.",
}
@Article{Abiteboul:1987:IFS,
author = "Serge Abiteboul and Richard Hull",
title = "{IFO}: a Formal Semantic Database Model",
journal = j-TODS,
volume = "12",
number = "4",
pages = "525--565",
month = dec,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "88i:68017",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Also published in/as: ACM SIGACT-SIGMOD Symp. on
Principles of Database Systems, 1984 (short version).
Also published in/as: USC CSD, TR-84-304, Apr. 1984.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-4/p525-abiteboul/p525-abiteboul.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-4/p525-abiteboul/;
http://www.acm.org/pubs/toc/Abstracts/tods/32205.html",
abstract = "A new, formally defined database model is introduced
that combines fundamental principles of ``semantic''
database modeling in a coherent fashion. Using a
graph-based formalism, the IFO model provides
mechanisms for representing structured objects, and
functional and ISA relationships between them. A number
of fundamental results concerning semantic data
modeling are obtained in the context of the IFO model.
Notably, the types of object structure that can arise
as a result of multiple uses of ISA relationships and
object construction are described. Also, a natural,
formal definition of update propagation is given, and
it is shown that (under certain conditions) a correct
update always exists.",
acknowledgement = ack-nhfb,
annote = "A graph-based formal semantic database model. Well
written. The model appears to be well founded.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; theory; verification",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf I.2.4}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Knowledge
Representation Formalisms and Methods, Semantic
networks.",
}
@Article{Ozsoyoglu:1987:ERA,
author = "G. {\"O}zsoyo{\u{g}}lu and Z. M. {\"O}zsoyo{\u{g}}lu
and V. Matos",
title = "Extending Relational Algebra and Relational Calculus
with Set-Valued Attributes and Aggregate Functions",
journal = j-TODS,
volume = "12",
number = "4",
pages = "566--592",
month = dec,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "920 253",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-4/p566-ozsoyoglu/p566-ozsoyoglu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-4/p566-ozsoyoglu/;
http://www.acm.org/pubs/toc/Abstracts/tods/32219.html",
abstract = "In commercial network database management systems,
set-valued fields and aggregate functions are commonly
supported. However, the relational database model, as
defined by Codd, does not include set-valued attributes
or aggregate functions. Recently, Klug extended the
relational model by incorporating aggregate functions
and by defining relational algebra and calculus
languages.\par
In this paper, relational algebra and relational
calculus database query languages (as defined by Klug)
are extended to manipulate set-valued attributes and to
utilize aggregate functions. The expressive power of
the extended languages is shown to be equivalent. We
extend the relational algebra with three new operators,
namely, pack, unpack, and aggregation-by-template. The
extended languages form a theoretical framework for
statistical database query languages.",
acknowledgement = ack-nhfb,
annote = "Nested relations.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; languages; theory; verification;
{\"O}zsoyo{\u{g}}lu Nested NF2 TODS",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages.",
}
@Article{Palley:1987:URM,
author = "Michael A. Palley and Jeffrey S. Simonoff",
title = "The Use of Regression Methodology for the Compromise
of Confidential Information in Statistical Databases",
journal = j-TODS,
volume = "12",
number = "4",
pages = "593--608",
month = dec,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-4/p593-palley/p593-palley.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-4/p593-palley/;
http://www.acm.org/pubs/toc/Abstracts/tods/42174.html",
abstract = "A regression methodology based technique can be used
to compromise confidentiality in a statistical
database. This holds true even when the DBMS prevents
application of regression methodology to the database.
Existing inference controls, including cell
restriction, perturbation, and table restriction
approaches, are shown to be generally ineffective
against this compromise technique. The effect of
incomplete supplemental knowledge on the regression
methodology based compromise technique is examined.
Finally, some potential complicators of this disclosure
scheme are introduced.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Legal Aspects; Management; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "legalaspects; management; security, security TODS",
subject = "{\bf H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration. {\bf H.2.8}: Information
Systems, DATABASE MANAGEMENT, Database applications.
{\bf K.4.1}: Computing Milieux, COMPUTERS AND SOCIETY,
Public Policy Issues, Privacy. {\bf K.6.m}: Computing
Milieux, MANAGEMENT OF COMPUTING AND INFORMATION
SYSTEMS, Miscellaneous, Security*. {\bf H.2.0}:
Information Systems, DATABASE MANAGEMENT, General,
Security, integrity, and protection. {\bf G.3}:
Mathematics of Computing, PROBABILITY AND STATISTICS,
Statistical computing.",
}
@Article{Agrawal:1987:CCP,
author = "Rakesh Agrawal and Michael J. Carey and Miron Livny",
title = "Concurrency Control Performance Modeling: Alternatives
and Implications",
journal = j-TODS,
volume = "12",
number = "4",
pages = "609--654",
month = dec,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/real.time.bib",
note = "Also published in/as: ACM SIGMOD Conf. on the
Management of Data, 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-4/p609-agrawal/p609-agrawal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-4/p609-agrawal/;
http://www.acm.org/pubs/toc/Abstracts/tods/32220.html",
abstract = "A number of recent studies have examined the
performance of concurrency control algorithms for
database management systems. The results reported to
date, rather than being definitive, have tended to be
contradictory. In this paper, rather than presenting
``yet another algorithm performance study,'' we
critically investigate the assumptions made in the
models used in past studies and their implications. We
employ a fairly complete model of a database
environment for studying the relative performance of
three different approaches to the concurrency control
problem under a variety of modeling assumptions. The
three approaches studied represent different extremes
in how transaction conflicts are dealt with, and the
assumptions addressed pertain to the nature of the
database system's resources, how transaction restarts
are modeled, and the amount of information available to
the concurrency control algorithm about transactions'
reference strings. We show that differences in the
underlying assumptions explain the seemingly
contradictory performance results. We also address the
question of how realistic the various assumptions are
for actual database systems.",
acknowledgement = ack-nhfb,
annote = "This paper is unique in that it studies the
implications of fundamental assumptions regarding
system resources, transactions restarts, and
predeclarations of writes. Essential reading.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "performance",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf D.4.8}: Software, OPERATING
SYSTEMS, Performance, Simulation. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing. {\bf D.4.2}: Software,
OPERATING SYSTEMS, Storage Management.",
}
@Article{Sacks-Davis:1987:MAM,
author = "R. Sacks-Davis and A. Kent and K. Ramamohanarao",
title = "Multikey Access Methods Based on Superimposed Coding
Techniques",
journal = j-TODS,
volume = "12",
number = "4",
pages = "655--696",
month = dec,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1987-12-4/p655-sacks-davis/p655-sacks-davis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1987-12-4/p655-sacks-davis/;
http://www.acm.org/pubs/toc/Abstracts/tods/32222.html",
abstract = "Both single-level and two-level indexed descriptor
schemes for multikey retrieval are presented and
compared. The descriptors are formed using superimposed
coding techniques and stored using a bit-inversion
technique. A fast-batch insertion algorithm for which
the cost of forming the bit-inverted file is less than
one disk access per record is presented. For large data
files, it is shown that the two-level implementation is
generally more efficient for queries with a small
number of matching records. For queries that specify
two or more values, there is a potential problem with
the two-level implementation in that costs may accrue
when blocks of records match the query but individual
records within these blocks do not. One approach to
overcoming this problem is to set bits in the
descriptors based on pairs of indexed terms. This
approach is presented and analyzed.",
acknowledgement = ack-nhfb,
annote = "Expressions for the cost of a two-level and one-level
scheme.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "descriptors; Design; hashing; partial match retrieval;
performance; record signatures; superimposed coding,
design",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.3.2}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Storage, File organization. {\bf H.4.1}:
Information Systems, INFORMATION SYSTEMS APPLICATIONS,
Office Automation. {\bf I.7.m}: Computing
Methodologies, TEXT PROCESSING, Miscellaneous.",
}
@Article{Elhardt:1987:SQO,
author = "K. Elhardt",
title = "Support for Query Optimization by Optimal Predicate
Splitting",
journal = j-TODS,
volume = "??",
number = "??",
pages = "??--??",
month = mar,
year = "1987",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Accepted.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Vianu:1988:DFO,
author = "Victor Vianu",
title = "A Dynamic Framework for Object Projection Views",
journal = j-TODS,
volume = "13",
number = "1",
pages = "1--22",
month = mar,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "933 215",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-1/p1-vianu/p1-vianu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-1/p1-vianu/;
http://www.acm.org/pubs/toc/Abstracts/tods/42202.html",
abstract = "User views in a relational database obtained through a
single projection ('projection views') are considered
in a new framework. Specifically, such views, where
each tuple in the view represents an object
('object-projection views'), are studied using the
dynamic relational model, which captures the evolution
of the database through consecutive updates. Attribute
sets that yield object-projection views are
characterized using the static and dynamic functional
dependencies satisfied by the database.
Object-projection views are then described using the
static and dynamic functional dependencies `inherited'
from the original database. Finally, the impact of
dynamic constraints on the view update problem is
studied in a limited context. This paper demonstrates
that new, useful information about views can be
obtained by looking at the evolution of the database as
captured by the dynamic relational model.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, San Diego, CA, USA",
affiliationaddress = "Univ of California, San Diego, CA, USA",
annote = "Assumes simplest translation to the underlying
database. Very restrictive unirelational database FDs
and DFDs, no exclusions or deletions. Technically very
good. Rejecting update object projections.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Management; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database schema, design; database systems; dynamic
constraints; functional dependency; languages;
management; object projection views; relational;
theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Data description
languages (DDL).",
}
@Article{Sellis:1988:MQO,
author = "Timos K. Sellis",
title = "Multiple-Query Optimization",
journal = j-TODS,
volume = "13",
number = "1",
pages = "23--52",
month = mar,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-1/p23-sellis/p23-sellis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-1/p23-sellis/;
http://www.acm.org/pubs/toc/Abstracts/tods/42203.html",
abstract = "Some recently proposed extensions to relational
database systems, as well as to deductive database
systems, require support for multiple-query processing.
For example, in a database system enhanced with
inference capabilities, a simple query involving a rule
with multiple definitions may expand to more than one
actual query that has to be run over the database. It
is an interesting problem then to come up with
algorithms that process these queries together instead
of one query at a time. The main motivation for
performing such an interquery optimization lies in the
fact that queries may share common data. We examine the
problem of multiple-query optimization in this paper.
The first major contribution of the paper is a
systematic look at the problem, along with the
presentation and analysis of algorithms that can be
used for multiple-query optimization. The second
contribution lies in the presentation of experimental
results. Our results show that using multiple-query
processing algorithms may reduce execution cost
considerably.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, Berkeley, CA, USA",
affiliationaddress = "Univ of California, Berkeley, CA, USA",
annote = "Two architectures: Interleaving the results of locally
optimal access plans or a global optimizer.
Experimental results, a decrease of 20-50 percent show
in I/O and CPU time. ---Sava-Segal.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "common access paths; computer programming ---
algorithms; database systems; deductive databases;
heuristic methods, global query TODS, algorithms;
multiple-query optimization; optimization; performance;
Relational",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models. {\bf I.2.8}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Problem Solving, Control
Methods, and Search, Heuristic methods. {\bf H.3.4}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Systems and Software.",
}
@Article{Shasha:1988:CSS,
author = "Dennis Shasha and Nathan Goodman",
title = "Concurrent Search Structure Algorithms",
journal = j-TODS,
volume = "13",
number = "1",
pages = "53--90",
month = mar,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-1/p53-shasha/p53-shasha.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-1/p53-shasha/;
http://www.acm.org/pubs/toc/Abstracts/tods/42204.html",
abstract = "A dictionary is an abstract data type supporting the
actions member, insert, and delete. A search structure
is a data structure used to implement a dictionary.
Examples include B trees, hash structures, and
unordered lists. Concurrent algorithms on search
structures can achieve more parallelism than standard
concurrency control methods would suggest, by
exploiting the fact that many different search
structure states represent one dictionary state. We
present a framework for verifying such algorithms and
for inventing new ones. We give several examples, one
of which exploits the structure of Banyan family
interconnection networks. We also discuss the
interaction between concurrency control and recovery as
applied to search structures.",
acknowledgement = ack-nhfb,
affiliation = "New York Univ, New York, NY, USA",
affiliationaddress = "New York Univ, New York, NY, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data type; Banyan interconnection networks;
computer programming --- algorithms; concurrent
algorithms, algorithms; data processing; Data
Structures; design; dictionary; performance; search
structure",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf D.4.1}: Software, OPERATING
SYSTEMS, Process Management, Concurrency. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.",
}
@Article{Finkelstein:1988:PDD,
author = "S. J. Finkelstein and M. Schkolnick and P. Tiberio",
title = "Physical Database Design for Relational Databases",
journal = j-TODS,
volume = "13",
number = "1",
pages = "91--128",
month = mar,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Also published in/as: IBM Research Report No. RJ5034,
Nov. 1986, preprint IBM Aug. 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-1/p91-finkelstein/p91-finkelstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-1/p91-finkelstein/;
http://www.acm.org/pubs/toc/Abstracts/tods/42205.html",
abstract = "This paper describes the concepts used in the
implementation of DBDSGN, an experimental physical
design tool for relational databases developed at the
IBM San Jose Research Laboratory. Given a workload for
System R (consisting of a set of SQL statements and
their execution frequencies), DBDSGN suggests physical
configurations for efficient performance. Each
configuration consists of a set of indices and an
ordering for each table. Workload statements are
evaluated only for atomic configurations of indices,
which have only one index per table. Costs for any
configuration can be obtained from those of the atomic
configurations. DBDSGN uses information supplied by the
System R optimizer both to determine which columns
might be worth indexing and to obtain estimates of the
cost of executing statements in different
configurations. The tool finds efficient solutions to
the index-selection problem; if we assume the cost
estimates supplied by the optimizer are the actual
execution costs, it finds the optimal solution.
Optionally, heuristics can be used to reduce execution
time. The approach taken by DBDSGN in solving the
index-selection problem for multiple-table statements
significantly reduces the complexity of the problem.
DBDSGN's principles were used in the Relational Design
Tool (RDT), an IBM product based on DBDSGN, which
performs design for SQL/DS, a relational system based
on System R. System R actually uses DBDSGN's suggested
solutions as the tool expects because cost estimates
and other necessary information can be obtained from
System R using a new SQL statement, the EXPLAIN
statement. This illustrates how a system can export a
model of its internal assumptions and behavior so that
other systems (such as tools) can share this model.",
acknowledgement = ack-nhfb,
affiliation = "IBM",
affiliationaddress = "IBM",
annote = "DBDSGN led to IBM RDT; input are relational tables and
a set of queries expected to be run; produces
specifications of indexes, clustered; it uses the
actual DBMS (SQL/DS) optimizer.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance;
Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "DBDSGN; design; experimentation; IBM DBDSGN tool TODS,
database systems; optimization; performance; physical
database design; relational; System R, algorithms;
theory",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf D.4.8}: Software,
OPERATING SYSTEMS, Performance, Modeling and
prediction. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf E.1}: Data,
DATA STRUCTURES, Tables.",
}
@Article{Raju:1988:FFD,
author = "K. V. S. V. N. Raju and Arun K. Majumdar",
title = "Fuzzy Functional Dependencies and Lossless Join
Decomposition of Fuzzy Relational Database Systems",
journal = j-TODS,
volume = "13",
number = "2",
pages = "129--166",
month = jun,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-2/p129-raju/p129-raju.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-2/p129-raju/;
http://www.acm.org/pubs/toc/Abstracts/tods/42344.html",
abstract = "This paper deals with the application of fuzzy logic
in a relational database environment with the objective
of capturing more meaning of the data. It is shown that
with suitable interpretations for the fuzzy membership
functions, a fuzzy relational data model can be used to
represent ambiguities in data values as well as
impreciseness in the association among them. Relational
operators for fuzzy relations have been studied, and
applicability of fuzzy logic in capturing integrity
constraints has been investigated. By introducing a
fuzzy resemblance measure EQUAL for comparing domain
values, the definition of classical functional
dependency has been generalized to fuzzy functional
dependency (ffd). The implication problem of ffds has
been examined and a set of sound and complete inference
axioms has been proposed. Next, the problem of lossless
join decomposition of fuzzy relations for a given set
of fuzzy functional dependencies is investigated. It is
proved that with a suitable restriction on EQUAL, the
design theory of a classical relational database with
functional dependencies can be extended to fuzzy
relations satisfying fuzzy functional dependencies.",
acknowledgement = ack-nhfb,
affiliation = "Ahdhra Univ, Visakhapatnam, India",
affiliationaddress = "Ahdhra Univ, Visakhapatnam, India",
annote = "Extend Armstrong's axioms to fuzzy domains. The
concept works out theoretically, but may not
necessarily agree with the intuition of the database
user. This paper is highly theoretical and notationally
intimidating. Yet worth to peruse.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; fuzzy functional dependencies; fuzzy
relational database systems, design; lossless join
decomposition; mathematical techniques --- fuzzy sets;
relational; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf E.5}: Data, FILES. {\bf I.2.3}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Deduction and Theorem Proving, Uncertainty, ``fuzzy,''
and probabilistic reasoning.",
}
@Article{Winslett:1988:MBA,
author = "Marianne Winslett",
title = "A Model-Based Approach to Updating Databases with
Incomplete Information",
journal = j-TODS,
volume = "13",
number = "2",
pages = "167--196",
month = jun,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/bibdb.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-2/p167-winslett/p167-winslett.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-2/p167-winslett/;
http://www.acm.org/pubs/toc/Abstracts/tods/42386.html",
abstract = "Suppose one wishes to construct, use, and maintain a
database of facts about the real world, even though the
state of that world is only partially known. In the
artificial intelligence domain, this problem arises
when an agent has a base set of beliefs that reflect
partial knowledge about the world, and then tries to
incorporate new, possibly contradictory knowledge into
this set of beliefs. In the database domain, one facet
of this situation is the well-known null values
problem. We choose to represent such a database as a
logical theory, and view the models of the theory as
representing possible states of the world that are
consistent with all known information.\par
How can new information be incorporated into the
database? For example, given the new information that
``$b$ or $c$ is true,'' how can one get rid of all
outdated information about $b$ and $c$, add the new
information, and yet in the process not disturb any
other information in the database? In current-day
database management systems, the difficult and tedious
burden of determining exactly what to add and remove
from the database is placed on the user. The goal of
our research was to relieve users of that burden, by
equipping the database management system with update
algorithms that can automatically determine what to add
and remove from the database. \par
Under our approach, new information about the state of
the world is input to the database management system as
a well-formed formula that the state of the world is
now known to satisfy. We have constructed database
update algorithms to interpret this update formula and
incorporate the new information represented by the
formula into the database without further assistance
from the user. In this paper we show how to embed the
incomplete database and the incoming information in the
language of mathematical logic, explain the semantics
of our update operators, and discuss the algorithms
that implement these operators.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Illinois, Urbana, IL, USA",
affiliationaddress = "Univ of Illinois, Urbana, IL, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Human Factors; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; database systems;
database updates; humanfactors; incomplete information;
languages; theory; uncertainty, algorithms; update
algorithms",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems. {\bf H.3.0}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, General. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Retrieval
models. {\bf I.2.3}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem
Proving.",
}
@Article{Eich:1988:DCC,
author = "Margaret H. Eich and David L. Wells",
title = "Database Concurrency Control using Data Flow Graphs",
journal = j-TODS,
volume = "13",
number = "2",
pages = "197--227",
month = jun,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "943 408",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-2/p197-eich/p197-eich.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-2/p197-eich/;
http://www.acm.org/pubs/toc/Abstracts/tods/42345.html",
abstract = "A specialized data flow graph, {\em Database Flow
Graph\/} ({\em DBFG\/}) is introduced. DBFGs may be
used for scheduling database operations, particularly
in an MIMD database machine environment. A DBFG
explicitly maintains intertransaction and
intratransaction dependencies, and is constructed from
the Transaction Flow Graphs (TFG) of active
transactions. A TFG, in turn, is the generalization of
a query tree used, for example, in DIRECT [15].
\par
All DBFG schedules are serializable and deadlock free.
Operations needed to create and maintain the DBFG
structure as transactions are added or removed from the
system are discussed. Simulation results show that DBFG
scheduling performs as well as two-phase locking.",
acknowledgement = ack-nhfb,
affiliation = "Southern Methodist Univ, Dallas, TX, USA",
affiliationaddress = "Southern Methodist Univ, Dallas, TX, USA",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data flow graphs; database concurrency control;
database systems; deadlock, algorithms; distributed;
mathematical techniques --- graph theory; performance;
serializability",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Deadlock avoidance. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Transaction processing.",
}
@Article{Batory:1988:ICE,
author = "D. S. Batory and T. Y. Leung and T. E. Wise",
title = "Implementation Concepts for an Extensible Data Model
and Data Language",
journal = j-TODS,
volume = "13",
number = "3",
pages = "231--262",
month = sep,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Un. Texas, TR-86-24, Oct.
1986.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-3/p231-batory/p231-batory.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-3/p231-batory/;
http://www.acm.org/pubs/toc/Abstracts/tods/45062.html",
abstract = "Future database systems must feature extensible data
models and data languages in order to accommodate the
novel data types and special-purpose operations that
are required by nontraditional database applications.
In this paper, we outline a functional data model and
data language that are targeted for the semantic
interface of GENESIS, an extensible DBMS. The model and
language are generalizations of FQL [11] and DAPLEX
[40], and have an implementation that fits ideally with
the modularity required by extensible database
technologies. We explore different implementations of
functional operators and present experimental evidence
that they have efficient implementations. We also
explain the advantages of a functional front-end to 1NF
databases, and show how our language and implementation
are being used to process queries on both 1NF and 1NF
relations.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Texas at Austin, Austin, TX, USA",
affiliationaddress = "Univ of Texas at Austin, Austin, TX, USA",
annote = "Illustrates a functional data model of GENESIS.
Defines GDM, the data model, and GDL, the data
language. GDM productions are stream rewrite rules and
GDM computations are expressed as streams of tokens.
Promotes extensibility. To build a non-1NF query
processor is an example.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming languages; data language;
database systems; functional data model; languages;
lazy evaluation, TODS genesis functional language join
joins lazy eager nested relations, design; Management;
performance; stream translators",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Data manipulation languages (DML). {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing. {\bf I.1.3}: Computing Methodologies,
ALGEBRAIC MANIPULATION, Languages and Systems,
Evaluation strategies. {\bf I.1.3}: Computing
Methodologies, ALGEBRAIC MANIPULATION, Languages and
Systems, Nonprocedural languages.",
}
@Article{Apers:1988:DAD,
author = "Peter M. G. Apers",
title = "Data Allocation in Distributed Database Systems",
journal = j-TODS,
volume = "13",
number = "3",
pages = "263--304",
month = sep,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-3/p263-apers/p263-apers.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-3/p263-apers/;
http://www.acm.org/pubs/toc/Abstracts/tods/45063.html",
abstract = "The problem of allocating the data of a database to
the sites of a communication network is investigated.
This problem deviates from the well-known file
allocation problem in several aspects. First, the
objects to be allocated are not known a priori; second,
these objects are accessed by schedules that contain
transmissions between objects to produce the result. A
model that makes it possible to compare the cost of
allocations is presented; the cost can be computed for
different cost functions and for processing schedules
produced by arbitrary query processing algorithms.
\par
For minimizing the total transmission cost, a method is
proposed to determine the fragments to be allocated
from the relations in the conceptual schema and the
queries and updates executed by the users.\par
For the same cost function, the complexity of the data
allocation problem is investigated. Methods for
obtaining optimal and heuristic solutions under various
ways of computing the cost of an allocation are
presented and compared.\par
Two different approaches to the allocation management
problem are presented and their merits are discussed.",
acknowledgement = ack-nhfb,
affiliation = "Vrije Univ, Enschede, Neth",
affiliationaddress = "Vrije Univ, Enschede, Neth",
annote = "Fragments are allocated. The strength of the paper is
its rigor, the weakness is in the applicability of the
model.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Measurement; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer networks; computer software --- software
engineering; data allocation; database systems; design;
distributed; dynamic schedules; greedy method;
heuristic allocations, algorithms; measurement; optimal
allocations; static schedules; theory",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
D.2.8}: Software, SOFTWARE ENGINEERING, Metrics,
Performance measures.",
}
@Article{Storey:1988:MCU,
author = "Veda C. Storey and Robert C. Goldstein",
title = "A Methodology for Creating User Views in Database
Design",
journal = j-TODS,
volume = "13",
number = "3",
pages = "305--338",
month = sep,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-3/p305-storey/p305-storey.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-3/p305-storey/;
http://www.acm.org/pubs/toc/Abstracts/tods/45064.html",
abstract = "The View Creation System (VCS) is an expert system
that engages a user in a dialogue about the information
requirements for some application, develops an
Entity-Relationship model for the user's database view,
and then converts the E-R model to a set of Fourth
Normal Form relations. This paper describes the
knowledge base of VCS. That is, it presents a formal
methodology, capable of mechanization as a computer
program, for accepting requirements from a user,
identifying and resolving inconsistencies,
redundancies, and ambiguities, and ultimately producing
a normalized relational representation. Key aspects of
the methodology are illustrated by applying VCS's
knowledge base to an actual database design task.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Rochester, Rochester, NY, USA",
affiliationaddress = "Univ of Rochester, Rochester, NY, USA",
annote = "Engages the user in a dialogue about the information
requirements for some application, develops an E-R
model and Fourth Normal Form relations.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming; database systems; design; expert
system; knowledge base; user views, design; view
creation system (VCS)",
subject = "{\bf I.2.1}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Applications and Expert Systems. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.2.7}: Information Systems,
DATABASE MANAGEMENT, Database Administration.",
}
@Article{Diederich:1988:NMF,
author = "Jim Diederich and Jack Milton",
title = "New Methods and Fast Algorithms for Database
Normalization",
journal = j-TODS,
volume = "13",
number = "3",
pages = "339--365",
month = sep,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 196",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "Also published in/as: UCD, Math, revised Jun. 1987.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-3/p339-diederich/p339-diederich.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-3/p339-diederich/;
http://www.acm.org/pubs/toc/Abstracts/tods/44499.html",
abstract = "A new method for computing minimal covers is presented
using a new type of closure that allows significant
reductions in the number of closures computed for
normalizing relations. Benchmarks are reported
comparing the new and the standard techniques.",
acknowledgement = ack-nhfb,
affiliation = "Univ of California, Davis, CA, USA",
affiliationaddress = "Univ of California, Davis, CA, USA",
annote = "Modify existing algorithms to make the process
faster.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; database
normalization; database systems; design; fast
algorithms; functional dependency; management;
redundant dependencies; relational database,
algorithms",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms.",
}
@Article{Larson:1988:LHS,
author = "Per-{\AA}ke Larson",
title = "Linear Hashing with Separators --- {A} Dynamic Hashing
Scheme Achieving One-Access Retrieval",
journal = j-TODS,
volume = "13",
number = "3",
pages = "366--388",
month = sep,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-3/p366-larson/p366-larson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-3/p366-larson/;
http://www.acm.org/pubs/toc/Abstracts/tods/44500.html",
abstract = "A new dynamic hashing scheme is presented. Its most
outstanding feature is that any record can be retrieved
in exactly one disk access. This is achieved by using a
small amount of supplemental internal storage that
stores enough information to uniquely determine the
current location of any record. The amount of internal
storage required is small: typically one byte for each
page of the file. The necessary address computation,
insertion, and expansion algorithms are presented and
the performance is studied by means of simulation. The
new method is the first practical method offering
one-access retrieval for large dynamic files.",
acknowledgement = ack-nhfb,
affiliation = "Univ of Waterloo, Waterloo, Ont, Can",
affiliationaddress = "Univ of Waterloo, Waterloo, Ont, Can",
annote = "A small amount of supplemental internal storage stores
enough information to uniquely determine the current
location of any record.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "address computation; data processing --- File
organization; design; dynamic hashing schemes;
extendible hashing; linear hashing; linear probing;
Management; one-access retrieval; open addressing,
algorithms; open addressing, database systems;
performance",
review = "ACM CR 8811-0850",
subject = "{\bf D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, Access methods. {\bf D.4.3}: Software,
OPERATING SYSTEMS, File Systems Management, File
organization. {\bf E.5}: Data, FILES,
Organization/structure. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods.",
}
@Article{Roth:1988:EAC,
author = "Mark A. Roth and Henry F. Korth and Abraham
Silberschatz",
title = "Extended Algebra and Calculus for Nested Relational
Databases",
journal = j-TODS,
volume = "13",
number = "4",
pages = "389--417",
month = dec,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 197",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/database.bib;
Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
note = "See comment \cite{Tansel:1992:MRH}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-4/p389-roth/p389-roth.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-4/p389-roth/;
http://www.acm.org/pubs/toc/Abstracts/tods/49347.html",
abstract = "Relaxing the assumption that relations are always in
First-Normal-Form (1NF) necessitates a reexamination of
the fundamentals of relational database theory. In this
paper we take a first step towards unifying the various
theories of $ \not $1NF databases. We start by
determining an appropriate model to couch our
formalisms in. We then define an extended relational
calculus as the theoretical basis for our $ \not $1NF
relational calculus. We define a class of $ \not $1NF
relations with certain ``good'' properties and extend
our algebra operators to work within this domain. We
prove certain desirable equivalences that hold only if
we restrict our language to this domain.",
acknowledgement = ack-nhfb,
affiliation = "Texas Univ., Austin, TX, USA",
affiliationaddress = "Austin, TX, USA",
annote = "Only two new operators, nest and unnest.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "languages; mathematical techniques --- algebra; nested
relational databases; non-first normal form database;
partitioned normal forms; query languages; relational;
relational calculus; theory, extended algebra and
calculus, nested relations, non-first normal form,
partitioned normal form, database systems",
owner = "curtis",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Normal
forms. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Query languages.",
}
@Article{Gadia:1988:HRM,
author = "Shashi K. Gadia",
title = "A Homogeneous Relational Model and Query Languages for
Temporal Databases",
journal = j-TODS,
volume = "13",
number = "4",
pages = "418--448",
month = dec,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 198",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-4/p418-gadia/p418-gadia.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-4/p418-gadia/;
http://www.acm.org/pubs/toc/Abstracts/tods/50065.html",
abstract = "In a temporal database, time values are associated
with data item to indicate their periods of validity.
We propose a model for temporal databases within the
framework of the classical database theory. Our model
is realized as a temporal parameterization of static
relations. We do not impose any restrictions upon the
schemes of temporal relations. The classical concepts
of normal forms and dependencies are easily extended to
our model, allowing a suitable design for a database
scheme. We present a relational algebra and a tuple
calculus for our model and prove their equivalence. Our
data model is homogeneous in the sense that the periods
of validity of all the attributes in a given tuple of a
temporal relation are identical. We discuss how to
relax the homogeneity requirement to extend the
application domain of our approach.",
acknowledgement = ack-nhfb,
affiliation = "Iowa State Univ., Ames, IA, USA",
affiliationaddress = "Ames, IA, USA",
annote = "temporal tuples and temporal relations; the temporal
domain varies from tuple to tuple but it is constant
with respect to attributes.",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; mathematical techniques ---
algebra; query languages; relational; relational
algebra; relational calculus; temporal databases;
theory, database systems; tuple calculus",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages.",
}
@Article{Brosda:1988:URR,
author = "Volkert Brosda and Gottfried Vossen",
title = "Update and Retrieval in a Relational Database Through
a Universal Schema Interface",
journal = j-TODS,
volume = "13",
number = "4",
pages = "449--485",
month = dec,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 199",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-4/p449-brosda/p449-brosda.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-4/p449-brosda/;
http://www.acm.org/pubs/toc/Abstracts/tods/49884.html",
abstract = "A database system that is based on the universal
relation (UR) model aims at freeing its users from
specifying access paths on both the physical and on the
logical levels. All information about the logical
structure of the database (i.e., its conceptual scheme)
is hidden from users; they need only to know the
attribute names, which now carry all the semantics of
the database.\par
Previous work on UR interfaces has concentrated on the
design and implementation of query languages that serve
to facilitate retrieval of data from a relational
database. On the other hand, updates are always handled
as before, which means that users still have to know
the logical structure of the database in case they want
to insert, delete, or modify tuples.\par
In this paper the concepts underlying a UR interface,
which is really ``universal,'' are presented; it is
based on the UR model, and it permits not only queries
but also updates: Combinations of attributes that may
participate in an update-operation (``objects'') have
to be specified during the design phase of the
database, and are then embodied into the database
scheme by an extended synthesis algorithm. They form
the basis for any insertion or deletion operation. A
precise definition of ``insertable'' tuples, and of the
insert- and delete-operation in this new context, is
given. It is then shown that these operations modify a
database state in such a way that a representative
instance always exists. This is accomplished by
providing a more detailed version of Sagiv's uniqueness
condition and by exploring the structure of nonunique
objects. Since the underlying database always has a
representative instance, this instance can be used to
define the window function for retrieval. It is shown
that it is still possible to compute windows by a union
of minimal extension joins.",
acknowledgement = ack-nhfb,
affiliation = "Rheinisch-Westfalische Tech. Hochschule Aachen, West
Germany",
affiliationaddress = "Aachen, West Ger",
classification = "723; 903",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer interfaces; database systems; database
updates; information science --- information retrieval;
languages; minimal extension joins; relational; theory;
universal relation interface; universal scheme
interfaces, design",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf D.2.2}: Software,
SOFTWARE ENGINEERING, Tools and Techniques, User
interfaces. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data manipulation languages
(DML). {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Transaction processing. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing.",
}
@Article{Gottlob:1988:PUS,
author = "Georg Gottlob and Paolo Paolini and Roberto Zicari",
title = "Properties and Update Semantics of Consistent Views",
journal = j-TODS,
volume = "13",
number = "4",
pages = "486--524",
month = dec,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 200",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-4/p486-gottlob/p486-gottlob.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-4/p486-gottlob/;
http://www.acm.org/pubs/toc/Abstracts/tods/50068.html",
abstract = "The problem of translating view updates to database
updates is considered. Both databases and views are
modeled as data abstractions. A data abstraction
consists of a set of states and of a set of primitive
update operators representing state transition
functions. It is shown how complex update programs can
be built from primitive update operators and how view
update programs are translated into database update
programs. Special attention is paid to a class of views
that we call ``consistent.'' Loosely speaking, a
consistent view is a view with the following property:
If the effect of a view update program on a view state
is determined, then the effect of the corresponding
database update is unambiguously determined. Thus, in
order to know how to translate a given view update into
a database update, it is sufficient to be aware of a
functional specification of such a program. We show
that consistent views have a number of interesting
properties with respect to the concurrency of
(high-level) update transactions. Moreover we show that
the class of consistent views includes as a subset the
class of views that translate updates under maintenance
of a constant complement. However, we show that there
exist consistent views that do not translate under
constant complement. The results of Bancilhon and
Spyratos [6] are generalized in order to capture the
update semantics of the entire class of consistent
views. In particular we show that the class of
consistent views is obtained if we relax the
requirement of a constant complement by allowing the
complement to decrease according to a suitable partial
order.",
acknowledgement = ack-nhfb,
affiliation = "Inst. for Appl. Math., CNR, Genoa, Italy",
affiliationaddress = "Genoa, Italy",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency, design; consistent views; data
abstractions; database systems; theory; update
semantics; view updates",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems.",
}
@Article{Lomet:1988:SBD,
author = "David B. Lomet",
title = "A Simple Bounded Disorder File Organization with Good
Performance",
journal = j-TODS,
volume = "13",
number = "4",
pages = "525--551",
month = dec,
year = "1988",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1988-13-4/p525-lomet/p525-lomet.pdf;
http://www.acm.org/pubs/citations/journals/tods/1988-13-4/p525-lomet/;
http://www.acm.org/pubs/toc/Abstracts/tods/50067.html",
abstract = "A bounded-disorder (BD) file is one in which data are
organized into nodes that are indexed, e.g., by means
of a B-tree. The data nodes are multibucket nodes that
are accessed by hashing. In this paper we present two
important improvements to the BD organization as
originally described. First, records in a data node
that overflow their designated primary bucket are
stored in a single overflow bucket which is itself a
bucket of the data node. Second, when file space needs
to be increased, partial expansions are used that
employ elastic buckets. Analysis and simulation results
demonstrate that this variant of the BD organization
has utilization, random access performance, and file
growth performance that can be competitive with good
extendible hashing methods, while supporting
high-performance sequential access. The simplicity of
the organization results in simple algorithms for
realizing the organization.",
acknowledgement = ack-nhfb,
affiliation = "Digital Equip. Corp., Nashua, NH, USA",
annote = "Index entries refer to large data nodes which are
treated as separate hashed files.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bounded disorder file organization; computer
programming --- algorithms; computer simulation; data
processing; design; dynamic files; file organization;
index sequential access; indexed files; performance;
storage management, algorithms",
review = "ACM CR 8904-0253",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.3.2}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Storage, File organization. {\bf D.4.3}:
Software, OPERATING SYSTEMS, File Systems Management,
Access methods. {\bf D.4.3}: Software, OPERATING
SYSTEMS, File Systems Management, File organization.",
}
@Article{Freytag:1989:TRQ,
author = "Johann Christoph Freytag and Nathan Goodman",
title = "On the Translation of Relational Queries into
Iterative Programs",
journal = j-TODS,
volume = "14",
number = "1",
pages = "1--27",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p1-freytag/p1-freytag.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p1-freytag/",
abstract = "This paper investigates the problem of translating
set-oriented query specifications into iterative
programs. The translation uses techniques of functional
programming and program transformation.\par
We present two algorithms that generate iterative
programs from algebra-based query specifications. The
first algorithm translates query specifications into
recursive programs. Those are simplified by sets of
transformation rules before the algorithm generates the
final iterative form. The second algorithm uses a
two-level translation that generates iterative programs
faster than the first algorithm. On the first level a
small set of transformation rules performs structural
simplification before the functional combination on the
second level yields the final iterative form.",
acknowledgement = ack-nhfb,
affiliation = "Eur. Comput. Ind. Res. Centre, Munich, West Germany",
affiliationaddress = "Cambridge, MA, USA",
annote = "Functional programming is used for the formulation of
simple algebraic rules",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algebraic specification; algorithms; computer
programming --- algorithms; functional programming;
iterative programs; languages; mathematical techniques
--- algebra; performance; program transformation;
relational; relational queries; theory, database
systems",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf D.1.1}: Software,
PROGRAMMING TECHNIQUES, Applicative (Functional)
Programming. {\bf I.2.2}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Automatic Programming, Program
transformation. {\bf H.2.5}: Information Systems,
DATABASE MANAGEMENT, Heterogeneous Databases, Program
translation.",
}
@Article{Ahad:1989:ECP,
author = "Rafiul Ahad and K. V. {Bapa Rao} and Dennis McLeod",
title = "On Estimating the Cardinality of the Projection of a
Database Relation",
journal = j-TODS,
volume = "14",
number = "1",
pages = "28--40",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p28-ahad/p28-ahad.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p28-ahad/;
http://www.acm.org/pubs/toc/Abstracts/tods/62034.html",
abstract = "We present an analytical formula for estimating the
cardinality of the projection on certain attributes of
a subset of a relation in a relational database. This
formula takes into account a priori knowledge of the
semantics of the real-world objects and relationships
that the database is intended to represent.
Experimental testing of the formula shows that it has
an acceptably low percentage error, and that its
worst-case error is smaller than the best-known
formula. Furthermore, the formula presented here has
the advantage that it does not require a scan of the
relation.",
acknowledgement = ack-nhfb,
affiliation = "Maryland Univ., College Park, MD, USA",
affiliationaddress = "College Park, MD, USA",
annote = "Uses normal distribution estimates.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Experimentation; Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "application semantics; cardinality estimation, data
semantics selectivity estimation TODS, design; computer
simulation; data semantics; database systems;
experimentation; measurement; performance; relational",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing.",
}
@Article{Ramesh:1989:VDT,
author = "R. Ramesh and A. J. G. Babu and J. Peter Kincaid",
title = "Variable-Depth Trie Index Optimization: Theory and
Experimental Results",
journal = j-TODS,
volume = "14",
number = "1",
pages = "41--74",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p41-ramesh/p41-ramesh.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p41-ramesh/;
http://www.acm.org/pubs/toc/Abstracts/tods/77249.html",
abstract = "We develop an efficient approach to Trie index
optimization. A {\em Trie\/} is a data structure used
to index a file having a set of attributes as record
identifiers. In the proposed methodology, a file is
horizontally partitioned into subsets of records using
a Trie index whose depth of indexing is allowed to
vary. The retrieval of a record from the file proceeds
by ``stepping through'' the index to identify a subset
of records in the file in which a binary search is
performed. This paper develops a taxonomy of
optimization problems underlying variable-depth Trie
index construction. All these problems are solvable in
polynomial time, and their characteristics are studied.
Exact algorithms and heuristics for their solution are
presented. The algorithms are employed in CRES-an
expert system for editing written narrative material,
developed for the Department of the Navy. CRES uses
several large-to-very-large dictionary files for which
Trie indexes are constructed using these algorithms.
Computational experience with CRES shows that search
and retrieval using variable-depth Trie indexes can be
as much as six times faster than pure binary search.
The space requirements of the Tries are reasonable. The
results show that the variable-depth Tries constructed
according to the proposed algorithms are viable and
efficient for indexing large-to-very-large files by
attributes in practical applications.",
acknowledgement = ack-nhfb,
affiliation = "State Univ. of New York, Buffalo, NY, USA",
affiliationaddress = "Buffalo, NY, USA",
classification = "723; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance;
Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "artificial intelligence --- expert systems; computer
editing; computer programming --- algorithms; CRES
expert system; data processing; data structures;
design; experimentation; information science ---
information retrieval; optimization; performance;
theory; trie index optimization, algorithms",
subject = "{\bf E.1}: Data, DATA STRUCTURES, Trees. {\bf E.5}:
Data, FILES. {\bf E.2}: Data, DATA STORAGE
REPRESENTATIONS, Contiguous representations. {\bf
H.3.1}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Content Analysis and Indexing. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Search process. {\bf
E.2}: Data, DATA STORAGE REPRESENTATIONS, Linked
representations.",
}
@Article{Gladney:1989:DRD,
author = "H. M. Gladney",
title = "Data Replicas in Distributed Information Services",
journal = j-TODS,
volume = "14",
number = "1",
pages = "75--97",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; Distributed/CCR.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "{\it Reviews}: Computing Reviews, Vol. 30, No. 11,
November 1989",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p75-gladney/p75-gladney.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p75-gladney/;
http://www.acm.org/pubs/toc/Abstracts/tods/62035.html",
abstract = "In an information distribution network in which
records are repeatedly read, it is cost-effective to
keep read-only copies in work locations. This paper
presents a method of updating replicas that need not be
immediately synchronized with the source data or with
each other. The method allows an arbitrary mapping from
source records to replica records. It is fail-safe,
maximizes workstation autonomy, and is well suited to a
network with slow, unreliable, and/or expensive
communications links.\par
The algorithm is a manipulation of queries, which are
represented as short encodings. When a response is
generated, we record which portion of the source
database was used. Later, when the source data are
updated, this information is used to identify obsolete
replicas. For each workstation, the identity of
obsolete replicas is saved until a workstation process
asks for this information. This workstation process
deletes each obsolete replica, and replaces it by an
up-to-date version either promptly or the next time the
application asks for this particular item. Throughout,
queries are grouped so that the impact of each source
update transaction takes effect atomically at each
workstation.\par
Optimizations of the basic algorithm are outlined.
These overlap change dissemination with user service,
allow the mechanism to be hidden within the data
delivery subsystem, and permit very large networks.",
acknowledgement = ack-nhfb,
affiliation = "IBM Almaden Res. Center, San Jose, CA, USA",
affiliationaddress = "San Jose, CA, USA",
annote = "Server and workstations.",
classification = "723; 903; 921",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Languages; Performance;
Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; design;
distributed; information services; languages;
optimization, algorithms; performance; reliability;
reviews, database systems",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed applications. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems.",
}
@Article{McLeish:1989:FRS,
author = "Mary McLeish",
title = "Further Results on the Security of Partitioned Dynamic
Statistical Databases",
journal = j-TODS,
volume = "14",
number = "1",
pages = "98--113",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p98-mcleish/p98-mcleish.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p98-mcleish/;
http://www.acm.org/pubs/toc/Abstracts/tods/62036.html",
abstract = "Partitioning is a highly secure approach to protecting
statistical databases. When updates are introduced,
security depends on putting restrictions on the sizes
of partition sets which may be queried. To overcome
this problem, attempts have been made to add ``dummy''
records. Recent work has shown that this leads to high
information loss.\par
This paper reconsiders the restrictions on the size of
partitioning sets required to achieve a high level of
security. Updates of two records at a time were studied
earlier, and security was found to hold if the sizes of
the partition sets were kept even. In this paper an
extended model is presented, allowing very general
updates to be performed. The security problem is
thoroughly studied, giving if and only if conditions.
The earlier result is shown to be part of a corollary
to the main theorem of this paper. Alternatives to
adding dummy records are presented and the practical
implications of the theory for the database manager are
discussed.",
acknowledgement = ack-nhfb,
affiliation = "Guelph Univ., Ont., Canada",
affiliationaddress = "Guelph, Ont, Can",
classification = "723; 922",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Security; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data processing --- security of data; database
security, algorithms; database systems; partitioned
databases; performance; security; statistical
databases; statistical methods; theory",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
G.3}: Mathematics of Computing, PROBABILITY AND
STATISTICS. {\bf K.4.1}: Computing Milieux, COMPUTERS
AND SOCIETY, Public Policy Issues, Privacy.",
}
@Article{Bic:1989:ADD,
author = "Lubomir Bic and Robert L. Hartmann",
title = "{AGM}: a Dataflow Database Machine",
journal = j-TODS,
volume = "14",
number = "1",
pages = "114--146",
month = mar,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-1/p114-bic/p114-bic.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-1/p114-bic/;
http://www.acm.org/pubs/toc/Abstracts/tods/62037.html",
abstract = "In recent years, a number of database machines
consisting of large numbers of parallel processing
elements have been proposed. Unfortunately, there are
two main limitations in database processing that
prevent a high degree of parallelism; these are the
available I/O bandwidth of the underlying storage
devices and the concurrency control mechanisms
necessary to guarantee data integrity. The main problem
with conventional approaches is the lack of a
computational model capable of utilizing the potential
of any significant number of processing elements and
storage devices and, at the same time, preserving the
integrity of the database.\par
This paper presents a database model and its associated
architecture, which is based on the principles of
data-driven computation. According to this model, the
database is represented as a network in which each node
is conceptually an independent, asynchronous processing
element, capable of communicating with other nodes by
exchanging messages along the network arcs. To answer a
query, one or more such messages, called tokens, are
created and injected into the network. These then
propagate asynchronously through the network in search
of results satisfying the given query.\par
The asynchronous nature of processing permits the model
to be mapped onto a computer architecture consisting of
large numbers of independent disk units and processing
elements. This increases both the available I/O
bandwidth as well as the processing potential of the
machine. At the same time, new concurrency control and
error recovery mechanisms are necessary to cope with
the resulting parallelism.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Irvine, CA, USA",
affiliationaddress = "Irvine, CA, USA",
classification = "722; 723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Active Graph Machine, design; AGM Model; Computer
Architecture; Database Machines; Database Systems;
Dataflow Computing; hardware support token flow on
multi-processor data connection graph TODS; languages;
Models; performance",
subject = "{\bf H.2.6}: Information Systems, DATABASE MANAGEMENT,
Database Machines. {\bf C.1.2}: Computer Systems
Organization, PROCESSOR ARCHITECTURES, Multiple Data
Stream Architectures (Multiprocessors), Parallel
processors. {\bf C.1.3}: Computer Systems Organization,
PROCESSOR ARCHITECTURES, Other Architecture Styles,
Data-flow architectures. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf C.4}: Computer Systems Organization,
PERFORMANCE OF SYSTEMS, Modeling techniques.",
}
@Article{Yu:1989:FER,
author = "C. T. Yu and W. Meng and S. Park",
title = "A Framework for Effective Retrieval",
journal = j-TODS,
volume = "14",
number = "2",
pages = "147--167",
month = jun,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "1 072 201",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-2/p147-yu/p147-yu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-2/p147-yu/;
http://www.acm.org/pubs/toc/Abstracts/tods/63519.html",
abstract = "The aim of an effective retrieval system is to yield
high recall and precision (retrieval effectiveness).
The nonbinary independence model, which takes into
consideration the number of occurrences of terms in
documents, is introduced. It is shown to be optimal
under the assumption that terms are independent. It is
verified by experiments to yield significant
improvement over the binary independence model. The
nonbinary model is extended to normalized vectors and
is applicable to more general queries.\par
Various ways to alleviate the consequences of the term
independence assumption are discussed. Estimation of
parameters required for the nonbinary independence
model is provided, taking into consideration that a
term may have different meanings.",
acknowledgement = ack-nhfb,
acmcrnumber = "8912-0901",
affiliation = "Dept. of Electr. Eng. and Comput. Sci., Illinois
Univ., Chicago, IL, USA",
affiliationaddress = "Chicago, IL, USA",
annote = "probabilistic models with parameters estimated from
previously retrieved relevant and irrelevant
documents.",
classification = "723; 903; 921; 922",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Database Systems; Information Retrieval; Information
Science; Mathematical Techniques --- Estimation;
Nonbinary Independence Model; Parameter Estimation;
Retrieval Effectiveness",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf H.3.3}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Search
and Retrieval, Query formulation. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Clustering.",
}
@Article{Embley:1989:NNF,
author = "David W. Embley",
title = "{NFQL}: The {Natural Forms Query Language}",
journal = j-TODS,
volume = "14",
number = "2",
pages = "168--211",
month = jun,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Brigham Young Un., TR-CS-87-6,
Mar. 1987.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-2/p168-embley/p168-embley.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-2/p168-embley/;
http://www.acm.org/pubs/toc/Abstracts/tods/64125.html",
abstract = "A means by which ordinary forms can be exploited to
provide a basis for nonprocedural specification of
information processing is discussed. The Natural Forms
Query Language (NFQL) is defined. In NFQL data
retrieval requests and computation specifications are
formulated by sketching ordinary forms to show what
data are desired and update operations are specified by
altering data on filled-in forms. The meaning of a form
depends on a store of knowledge that includes extended
abstract data types for defining elementary data items,
a database scheme defined by an entity-relationship
model, and a conceptual model of an ordinary form.
Based on this store of knowledge, several issues are
addressed and resolved in the context of NFQL. These
issues include automatic generation of query
expressions from weak specifications, the view update
problem, power and completeness, and a heuristic
approach to resolving computational relationships. A
brief status report of an implementation of NFQL is
also given.",
acknowledgement = ack-nhfb,
affiliation = "Brigham Young Univ., Prov., UT, USA",
affiliationaddress = "Provo, UT, USA",
annote = "Uses surrogate keys in the ER model.",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database systems; entity-relationship model; forms
oriented interfaces; informal software specification;
information science --- information retrieval;
languages; natural forms query language; nonprocedural
specification; query languages; relational database,
algorithms; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, NFQL. {\bf H.2.1}: Information Systems,
DATABASE MANAGEMENT, Logical Design, Data models. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.4.1}:
Information Systems, INFORMATION SYSTEMS APPLICATIONS,
Office Automation. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Query
formulation. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data description languages
(DDL). {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data manipulation languages
(DML). {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Query languages.",
}
@Article{Atzeni:1989:EOS,
author = "Paolo Atzeni and Edward P. F. Chan",
title = "Efficient Optimization of Simple Chase Join
Expressions",
journal = j-TODS,
volume = "14",
number = "2",
pages = "212--230",
month = jun,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 202",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-2/p212-atzeni/p212-atzeni.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-2/p212-atzeni/;
http://www.acm.org/pubs/toc/Abstracts/tods/63520.html",
abstract = "Simple chase join expressions are relational algebra
expressions, involving only projection and join
operators, defined on the basis of the functional
dependencies associated with the database scheme. They
are meaningful in the weak instance model, because for
certain classes of schemes, including independent
schemes, the total projections of the representative
instance can be computed by means of unions of simple
chase join expressions. We show how unions of simple
chase join expressions can be optimized efficiently,
without constructing and chasing the corresponding
tableaux. We also present efficient algorithms for
testing containment and equivalence, and for optimizing
individual simple chase join expressions.",
acknowledgement = ack-nhfb,
affiliation = "IASI-CNR, Rome, Italy",
affiliationaddress = "Rome, Italy",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer programming --- algorithms; containment
testing; database systems; equivalence testing,
algorithms; functional dependencies; languages;
optimization; performance; relational; relational
algebra expressions; simple chase join expressions;
theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Normal forms.",
}
@Article{Ramakrishna:1989:FOU,
author = "M. V. Ramakrishna and Per-{\AA}ke Larson",
title = "File Organization Using Composite Perfect Hashing",
journal = j-TODS,
volume = "14",
number = "2",
pages = "231--263",
day = "1",
month = jun,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib; UnCover
library database",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-2/p231-ramakrishna/p231-ramakrishna.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-2/p231-ramakrishna/;
http://www.acm.org/pubs/toc/Abstracts/tods/63521.html",
abstract = "Perfect hashing refers to hashing with no overflows.
We propose and analyze a composite perfect hashing
scheme for large external files. The scheme guarantees
retrieval of any record in a single disk access.
Insertions and deletions are simple, and the file size
may vary considerably without adversely affecting the
performance. A simple variant of the scheme supports
efficient range searches in addition to being a
completely dynamic file organization scheme. These
advantages are achieved at the cost of a small amount
of additional internal storage and increased cost of
insertions.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Michigan State Univ., East
Lansing, MI, USA",
affiliationaddress = "East Lansing, MI, USA",
classification = "723; 903",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "composite perfect hashing; data processing; database
systems; design; dynamic file organization, algorithms;
experimentation; file organization; information science
--- information retrieval; large external files;
performance; range searches",
subject = "{\bf E.2}: Data, DATA STORAGE REPRESENTATIONS,
Hash-table representations. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Sorting and searching. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods.",
}
@Article{ElAbaddi:1989:MAP,
author = "Amr {El Abaddi} and Sam Toueg",
title = "Maintaining Availability in Partitioned Replicated
Databases",
journal = j-TODS,
volume = "14",
number = "2",
pages = "264--290",
month = jun,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 072 203",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Compendex database; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: ACM SIGACT-SIGMOD Symp. on
Principles of Database Systems, Cambridge MA, Mar.
1986.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-2/p264-abbadi/p264-abbadi.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-2/p264-abbadi/;
http://www.acm.org/pubs/toc/Abstracts/tods/63501.html",
abstract = "In a replicated database, a data item may have copies
residing on several sites. A replica control protocol
is necessary to ensure that data items with several
copies behave as if they consist of a single copy, as
far as users can tell. We describe a new replica
control protocol that allows the accessing of data in
spite of site failures and network partitioning. This
protocol provides the database designer with a large
degree of flexibility in deciding the degree of data
availability, as well as the cost of accessing data.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Cornell Univ., Ithaca, NY,
USA",
affiliationaddress = "Ithaca, NY, USA",
classification = "723",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "computer operating systems; concurrency control;
database availability, algorithms; database systems;
design; distributed; partitioned replicated databases;
partitioning failures; performance; reliability;
replica control; serializability",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, Distributed file systems. {\bf D.4.5}:
Software, OPERATING SYSTEMS, Reliability,
Fault-tolerance. {\bf C.2.2}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS, Network
Protocols. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design, Access methods.",
}
@Article{Hudson:1989:CSA,
author = "Scott E. Hudson and Roger King",
title = "{Cactis}: a Self-Adaptive, Concurrent Implementation
of an Object-Oriented Database Management System",
journal = j-TODS,
volume = "14",
number = "3",
pages = "291--321",
month = sep,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-3/p291-hudson/p291-hudson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-3/p291-hudson/;
http://www.acm.org/pubs/toc/Abstracts/tods/68013.html",
abstract = "Cactis is an object-oriented, multiuser DBMS developed
at the University of Colorado. The system supports
functionally-defined data and uses techniques based on
attributed graphs to optimize the maintenance of
functionally-defined data. The implementation is
self-adaptive in that the physical organization and the
update algorithms dynamically change in order to reduce
disk access. The system is also concurrent. At any
given time there are some number of computations that
must be performed to bring the database up to date;
these computations are scheduled independently and are
performed when the expected cost to do so is minimal.
The DBMS runs in the Unix/C Sun workstation
environment. Cactis is designed to support applications
that require rich data modeling capabilities and the
ability to specify functionally-defined data, but that
also demand good performance. Specifically, Cactis is
intended for use in the support of such applications as
VLSI and PCB design, and software environments.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Arizona Univ., Tucson, AZ,
USA",
annote = "attributes of objects can be derived; dynamic
definition of a scheme, depending on the user's
requirements functionally defined data, intelligent
update algorithms",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; clustering derived update propagation
TODS; design; performance",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Cactis. {\bf H.2.1}: Information Systems,
DATABASE MANAGEMENT, Logical Design, Data models. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design. {\bf J.6}: Computer Applications,
COMPUTER-AIDED ENGINEERING.",
}
@Article{Sheard:1989:AVD,
author = "Tim Sheard and David Stemple",
title = "Automatic Verification of Database Transaction
Safety",
journal = j-TODS,
volume = "14",
number = "3",
pages = "322--368",
month = sep,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: U. Mass, COINS TR-88-29, Apr.
1988, also TR-86-30, 1986.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-3/p322-sheard/p322-sheard.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-3/p322-sheard/;
http://www.acm.org/pubs/toc/Abstracts/tods/68014.html",
abstract = "Maintaining the integrity of databases is one of the
promises of database management systems. This includes
assuring that integrity constraints are invariants of
database transactions. This is very difficult to
accomplish efficiently in the presence of complex
constraints and large amounts of data. One way to
minimize the amount of processing required to maintain
database integrity over transaction processing is to
prove at compile-time that transactions cannot, if run
atomically, disobey integrity constraints. We report on
a system that performs such verification for a robust
set of constraint and transaction classes. The system
accepts database schemas written in a more or less
traditional style and accepts programs in a high-level
programming language. Automatic verification fast
enough to be effective on current workstation hardware
is performed.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. and Inf. Sci., Massachusetts Univ.,
Amherst, MA, USA",
annote = "LISP; inference techniques based on Boyer--Moore.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Reliability; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; reliability; verification",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Schema and subschema. {\bf D.2.4}: Software,
SOFTWARE ENGINEERING, Program Verification.",
}
@Article{Blakeley:1989:UDR,
author = "Jos{\'e} A. Blakeley and Neil Coburn and Per-{\AA}ke
Larson",
title = "Updating Derived Relations: Detecting Irrelevant and
Autonomously Computable Updates",
journal = j-TODS,
volume = "14",
number = "3",
pages = "369--400",
month = sep,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 073 202",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Indiana Un., TR-235, Nov. 1987.
Also published in \cite{Kambayashi:1986:TIC}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-3/p369-blakeley/p369-blakeley.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-3/p369-blakeley/;
http://www.acm.org/pubs/toc/Abstracts/tods/68015.html",
abstract = "Consider a database containing not only base relations
but also stored derived relations (also called
materialized or concrete views). When a base relation
is updated, it may also be necessary to update some of
the derived relations. This paper gives sufficient and
necessary conditions for detecting when an update of a
base relation cannot affect a derived relation (an
irrelevant update), and for detecting when a derived
relation can be correctly updated using no data other
than the derived relation itself and the given update
operation (an autonomously computable update). The
class of derived relations considered is restricted to
those defined by {\em PSJ\/}-expressions, that is, any
relational algebra expressions constructed from an
arbitrary number of project, select and join operations
(but containing no self-joins). The class of update
operations consists of insertions, deletions, and
modifications, where the set of tuples to be deleted or
modified is specified by a selection condition on
attributes of the relation being updated.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Waterloo Univ., Ont., Canada",
annote = "Identity implementation; rigorous mathematical proofs;
expressions that are capable of being tested constitute
a large and commonly occurring class.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Schema and subschema. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods.",
}
@Article{Mackert:1989:ISU,
author = "Lothar F. Mackert and Guy M. Lohman",
title = "Index Scans Using a Finite {LRU} Buffer: a Validated
{I/O} Model",
journal = j-TODS,
volume = "14",
number = "3",
pages = "401--424",
month = sep,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: IBM, TR-RC-4836, Sep. 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-3/p401-mackert/p401-mackert.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-3/p401-mackert/;
http://www.acm.org/pubs/toc/Abstracts/tods/68016.html",
abstract = "Indexes are commonly employed to retrieve a portion of
a file or to retrieve its records in a particular
order. An accurate performance model of indexes is
essential to the design, analysis, and tuning of file
management and database systems, and particularly to
database query optimization. Many previous studies have
addressed the problem of estimating the number of disk
page fetches when randomly accessing $k$ records out of
$N$ given records stored on $T$ disk pages. This paper
generalizes these results, relaxing two assumptions
that usually do not hold in practice: unlimited buffer
and unique records for each key value. Experiments show
that the performance of an index scan is very sensitive
to buffer size limitations and multiple records per key
value. A model for these more practical situations is
presented and a formula derived for estimating the
performance of an index scan. We also give a
closed-form approximation that is easy to compute. The
theoretical results are validated using the $R$ *
distributed relational database system. Although we use
database terminology throughout the paper, the model is
more generally applicable whenever random accesses are
made using keys.",
acknowledgement = ack-nhfb,
affiliation = "IBM Almaden Res. Center, San Jose, CA, USA",
annote = "consider limited buffer and now unique records for
each key value.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Measurement; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; measurement; performance; theory, clustering
non-clustering B-tree lookup cost Starburst System R
IBM Almaden TODS",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.3.2}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Storage, File organization. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.3.3}: Information Systems, INFORMATION
STORAGE AND RETRIEVAL, Information Search and
Retrieval, Retrieval models. {\bf H.3.1}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Content
Analysis and Indexing, Indexing methods. {\bf E.5}:
Data, FILES, Organization/structure. {\bf C.4}:
Computer Systems Organization, PERFORMANCE OF SYSTEMS,
Performance attributes.",
}
@Article{Manolopoulos:1989:PTH,
author = "Y. Manolopoulos and J. G. Kollias",
title = "Performance of a Two-Headed Disk System when Serving
Database Queries Under the Scan Policy",
journal = j-TODS,
volume = "14",
number = "3",
pages = "425--442",
month = sep,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-3/p425-manolopoulos/p425-manolopoulos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-3/p425-manolopoulos/;
http://www.acm.org/pubs/toc/Abstracts/tods/68017.html",
abstract = "Disk drives with movable two-headed arms are now
commercially available. The two heads are separated by
a fixed number of cylinders. A major problem for
optimizing disk head movement, when answering database
requests, is the specification of the optimum number of
cylinders separating the two heads. An earlier
analytical study assumed a FCFS model and concluded
that the optimum separation distance should be equal to
0.44657 of the number of cylinders $N$ of the disk.
This paper considers that the SCAN scheduling policy is
used in file access, and it applies combinatorial
analysis to derive exact formulas for the expected head
movement. Furthermore, it is proven that the optimum
separation distance is $ N / 2 - 1 $ ($ \lceil N / 2 -
1 \rceil $ and $ \lfloor N / 2 - 1 \rfloor $ ) if $N$
is even (odd). In addition, a comparison with a
single-headed disk system operating under the same
scheduling policy shows that if the two heads are
optimally spaced, then the mean seek distance is less
than one-half of the value obtained with one head. In
fact that the SCAN policy is used for many database
applications (for example,batching and secondary key
retrieval) demonstrates the potential of two-headed
disk systems for improving the performance of database
systems.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Electr. Eng., Aristotelian Univ. of
Thessaloniki, Greece",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; hardware support I/O seek machine TODS,
algorithms; performance",
subject = "{\bf D.4.2}: Software, OPERATING SYSTEMS, Storage
Management, Secondary storage. {\bf D.4.1}: Software,
OPERATING SYSTEMS, Process Management, Scheduling. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Sequencing and scheduling.",
}
@Article{Dreizen:1989:ISR,
author = "Howard M. Dreizen and Shi-Kuo Chang",
title = "Imprecise Schema: a Rationale for Relations with
Embedded Subrelations",
journal = j-TODS,
volume = "14",
number = "4",
pages = "447--479",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Misc/is.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p447-dreizen/p447-dreizen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p447-dreizen/;
http://www.acm.org/pubs/toc/Abstracts/tods/76903.html",
abstract = "{\em Exceptional conditions\/} are anomalous data
which meet the intent of a schema but not the schema
definition, represent a small proportion of the
database extension, and may become known only after the
schema is in use. Admission of exceptional conditions
is argued to suggest a representation that locally
stretches the schema definition by use of relations
with embedded subrelations. Attempted normalization of
these relations to 1NF does not yield the static schema
typically associated with such transformations. A class
of relations, termed Exceptional Condition Nested Form
(ECNF), is defined which allows the necessary
representation of exceptional conditions while
containing sufficient restrictions to prevent arbitrary
and chaotic inclusion of embedded subrelations. Queries
on a subset of exceptional conditions, the {\em
exceptional constraints}, are provided an
interpretation via an algorithm that transforms ECNF
relations into 1NF relations containing two types of
null values. Extensions of relational algebraic
operators, suitable for interactive query navigation,
are defined for use with ECNF relations containing all
forms of exceptional conditions.",
acknowledgement = ack-nhfb,
affiliation = "Illinois Inst. of Technol., Chicago, IL, USA",
annote = "If the data contain only a few `exceptional' tuples,
their effect might better be confined to a local schema
change rather than changing the global schema; the
effect of processing is only partly answered.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing.",
}
@Article{Motro:1989:IVC,
author = "Amihai Motro",
title = "Integrity = Validity + Completeness",
journal = j-TODS,
volume = "14",
number = "4",
pages = "480--502",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p480-motro/p480-motro.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p480-motro/;
http://www.acm.org/pubs/toc/Abstracts/tods/76904.html",
abstract = "Database integrity has two complementary components:
{\em validity}, which guarantees that all false
information is excluded from the database, and {\em
completeness}, which guarantees that all true
information is included in the database. This article
describes a uniform model of integrity for relational
databases, that considers both validity and
completeness. To a large degree, this model subsumes
the prevailing model of integrity (i.e., integrity
constraints). One of the features of the new model is
the determination of the integrity of answers issued by
the database system in response to user queries. To
users, answers that are accompanied with such detailed
certifications of their integrity are more meaningful.
First, the model is defined and discussed. Then, a
specific mechanism is described that implements this
model. With this mechanism, the determination of the
integrity of an answer is a process analogous to the
determination of the answer itself.",
acknowledgement = ack-nhfb,
affiliation = "Univ. of Southern California, Los Angeles, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models.",
}
@Article{Farrag:1989:USK,
author = "Abdel Aziz Farrag and M. Tamer {\"O}zsu",
title = "Using Semantic Knowledge of Transactions to Increase
Concurrency",
journal = j-TODS,
volume = "14",
number = "4",
pages = "503--525",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Accepted. Also published in/as: Un. Alberta, DCS,
TR-85-11, Jul. 1985.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p503-farrag/p503-farrag.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p503-farrag/;
http://www.acm.org/pubs/toc/Abstracts/tods/76905.html",
abstract = "When the only information available about transactions
is syntactic information, serializability is the main
correctness criterion for concurrency control.
Serializability requires that the execution of each
transaction must appear to every other transaction as a
single atomic step (i.e., the execution of the
transaction cannot be interrupted by other
transactions). Many researchers, however, have realized
that this requirement is unnecessarily strong for many
applications and can significantly increase transaction
response time. To overcome this problem, a new approach
for controlling concurrency that exploits the semantic
information available about transactions to allow
controlled nonserializable interleavings has recently
been proposed. This approach is useful when the cost of
producing only serializable interleavings is
unacceptably high. The main drawback of the approach is
the extra overhead incurred by utilizing the semantic
information. We examine this new approach in this paper
and discuss its strengths and weaknesses. We introduce
a new formalization for the concurrency control problem
when semantic information is available about the
transactions. This semantic information takes the form
of transaction types, transaction steps, and
transaction break-points. We define a new class of
``safe'' schedules called relatively consistent (RC)
schedules. This class contains serializable as well as
nonserializable schedules. We prove that the execution
of an RC schedule cannot violate consistency and
propose a new concurrency control mechanism that
produces only RC schedules. Our mechanism assumes fewer
restrictions on the interleavings among transactions
than previously introduced semantic-based mechanisms.",
acknowledgement = ack-nhfb,
affiliation = "Dalhousie Univ., Halifax, NS, Canada",
annote = "By setting breakpoints to interleave compatible
transactions. But aborts can require rollbacks or
offsetting transactions. Compatible transactions can
interleave. Nested compatibility in interleaving
transactions.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.",
}
@Article{Ozsoyoglu:1989:QPT,
author = "Gultekin {\"O}zsoyo{\u{g}}lu and Victor Matos and Z.
Meral {\"O}zsoyo{\u{g}}lu",
title = "Query Processing Techniques in the
Summary-Table-by-Example Database Query Language",
journal = j-TODS,
volume = "14",
number = "4",
pages = "526--573",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p526-ozsoyoglu/p526-ozsoyoglu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p526-ozsoyoglu/;
http://www.acm.org/pubs/toc/Abstracts/tods/76906.html",
abstract = "Summary-Table-by-Example (STBE) is a graphical
language suitable for statistical database
applications. STBE queries have a hierarchical subquery
structure and manipulate summary tables and relations
with set-valued attributes.\par
The hierarchical arrangement of STBE queries naturally
implies a tuple-by-tuple subquery evaluation strategy
(similar to the nested loops join implementation
technique) which may not be the best query processing
strategy. In this paper we discuss the query processing
techniques used in STBE. We first convert an STBE query
into an ``extended'' relational algebra (ERA)
expression. Two transformations are introduced to
remove the hierarchical arrangement of subqueries so
that query optimization is possible. To solve the
``empty partition'' problem of aggregate function
evaluation, directional join (one-sided outer-join) is
utilized. We give the algebraic properties of the ERA
operators to obtain an ``improved'' ERA expression.
Finally we briefly discuss the generation of
alternative implementations of a given ERA expression.
\par
STBE is implemented in a prototype statistical database
management system. We discuss the STBE-related features
of the implemented system.",
acknowledgement = ack-nhfb,
affiliation = "Case Western Reserve Univ., Cleveland, OH, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; languages; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design, Data models. {\bf G.3}:
Mathematics of Computing, PROBABILITY AND STATISTICS,
Statistical software.",
}
@Article{Grady:1989:EJO,
author = "Dani{\`e}le Grady and Claude Puech",
title = "On the Effect of Join Operations on Relation Sizes",
journal = j-TODS,
volume = "14",
number = "4",
pages = "574--603",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 073 203",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p574-grady/p574-grady.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p574-grady/;
http://www.acm.org/pubs/toc/Abstracts/tods/76907.html",
abstract = "We propose a generating function approach to the
problem of evaluating the sizes of derived relations in
a relational database framework. We present a model of
relations and show how to use it to deduce
probabilistic estimations of derived relation sizes.
These are found to asymptotically follow normal
distributions under a variety of assumptions.",
acknowledgement = ack-nhfb,
affiliation = "Univ. Paris-Sud, Orsay, France",
annote = "Polynomial generating function is given; derived
relation sizes asymptotically follow normal
distributions.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; generating functions; performance;
selectivity estimation; theory; TODS",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.2.1}: Mathematics of
Computing, DISCRETE MATHEMATICS, Combinatorics,
Generating functions. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Computations on discrete structures. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Schema and subschema. {\bf H.3.3}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval.",
}
@Article{Lang:1989:UAB,
author = "Sheau-Dong Lang and James R. Driscoll and Jiann H.
Jou",
title = "A Unified Analysis of Batched Searching of Sequential
and Tree-Structured Files",
journal = j-TODS,
volume = "14",
number = "4",
pages = "604--618",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10 (68P20)",
MRnumber = "1 073 204",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1989-14-4/p604-lang/p604-lang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1989-14-4/p604-lang/;
http://www.acm.org/pubs/toc/Abstracts/tods/76908.html",
abstract = "A direct and unified approach is used to analyze the
efficiency of batched searching of sequential and
tree-structured files. The analysis is applicable to
arbitrary search distributions, and closed-form
expressions are obtained for the expected batched
searching cost and savings. In particular, we consider
a search distribution satisfying Zipf's law for
sequential files and four types of uniform (random)
search distribution for sequential and tree-structured
files. These results unify and extend earlier research
on batched searching and estimating block accesses for
database systems.",
acknowledgement = ack-nhfb,
affiliation = "Central Florida Univ., Orlando, FL, USA",
annote = "closed-form expressions for the number of accesses
needed given arbitrary search distributions.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval, Search
process. {\bf H.3.2}: Information Systems, INFORMATION
STORAGE AND RETRIEVAL, Information Storage, File
organization. {\bf H.2.2}: Information Systems,
DATABASE MANAGEMENT, Physical Design, Access methods.",
}
@Article{Motro:1989:QDK,
author = "A. Motro and Q. Yuan",
title = "Querying Database Knowledge",
journal = j-TODS,
volume = "14",
number = "4",
pages = "??--??",
month = dec,
year = "1989",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in \cite{Garcia-Molina:1990:PAS}.",
annote = "The describe statement inquires about the meaning of a
concept under specified circumstances",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
xxnote = "This paper does not seem to be published in TODS.",
}
@Article{Liu:1990:IMI,
author = "Ken-Chih C. Liu and Rajshekhar Sunderraman",
title = "Indefinite and Maybe Information in Relational
Databases",
journal = j-TODS,
volume = "15",
number = "1",
pages = "1--39",
month = mar,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 073 205",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-1/p1-liu/p1-liu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-1/p1-liu/;
http://www.acm.org/pubs/toc/Abstracts/tods/77644.html",
abstract = "This paper extends the relational model to represent
indefinite and maybe kinds of incomplete information. A
data structure, called an I-table, which is capable of
representing indefinite and maybe facts, is introduced.
The information content of I-tables is precisely
defined, and an operator to remove redundant facts is
presented. The relational algebra is then extended in a
semantically correct way to operate on I-tables.
Queries are posed in the same way as in conventional
relational algebra; however, the user may now expect
indefinite as well as maybe answers.",
acknowledgement = ack-nhfb,
affiliation = "AT\&T Bell Labs., Naperville, IL, USA",
annote = "an I-table is capable of representing indefinite and
maybe facts, is introduced; an operator to remove
redundant facts is presented. The relational algebra is
then extended; user may now expect indefinite as well
as maybe answers",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf E.1}: Data, DATA STRUCTURES, Tables.
{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval.",
}
@Article{Langerak:1990:VUR,
author = "Rom Langerak",
title = "View Updates in Relational Databases with an
Independent Scheme",
journal = j-TODS,
volume = "15",
number = "1",
pages = "40--66",
month = mar,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 073 206",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-1/p40-langerak/p40-langerak.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-1/p40-langerak/;
http://www.acm.org/pubs/toc/Abstracts/tods/77645.html",
abstract = "A view on a database is a mapping that provides a user
or application with a suitable way of looking at the
data. Updates specified on a view have to be translated
into updates on the underlying database. We study the
view update translation problem for a relational data
model in which the base relations may contain (indexed)
nulls.\par
The representative instance is considered to be the
correct representation of all data in the database; the
class of views that is studied consists of total
projections of the representative instance. Only
independent database schemes are considered, that is,
schemes for which global consistency is implied by
local consistency. A view update can be an insertion, a
deletion, or a modification of a single view tuple.
\par
It is proven that the constant complement method of
Bancilhon and Spyratos is too restrictive to be useful
in this context. Structural properties of extension
joins are derived that are important for understanding
views. On the basis of these properties, minimal
algorithms for translating a single view-tuple update
are given.",
acknowledgement = ack-nhfb,
affiliation = "Fac. of Inf., Twente Univ., Enschede, Netherlands",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; theory; views TODS, algorithms",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models. {\bf H.3.3}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Search
and Retrieval.",
}
@Article{Whang:1990:QOM,
author = "Kyu-Young Y. Whang and Ravi Krishnamurthy",
title = "Query Optimization in a Memory-Resident Domain
Relational Calculus Database System",
journal = j-TODS,
volume = "15",
number = "1",
pages = "67--95",
month = mar,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-1/p67-whang/p67-whang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-1/p67-whang/;
http://www.acm.org/pubs/toc/Abstracts/tods/77646.html",
abstract = "We present techniques for optimizing queries in
memory-resident database systems. Optimization
techniques in memory-resident database systems differ
significantly from those in conventional disk-resident
database systems. In this paper we address the
following aspects of query optimization in such systems
and present specific solutions for them: (1) a new
approach to developing a CPU-intensive cost model; (2)
new optimization strategies for main-memory query
processing; (3) new insight into join algorithms and
access structures that take advantage of memory
residency of data; and (4) the effect of the operating
system's scheduling algorithm on the memory-residency
assumption. We present an interesting result that a
major cost of processing queries in memory-resident
database systems is incurred by evaluation of
predicates. We discuss optimization techniques using
the Office-by-Example (OBE) that has been under
development at IBM Research. We also present the
results of performance measurements, which prove to be
excellent in the current state of the art. Despite
recent work on memory-resident database systems, query
optimization aspects in these systems have not been
well studied. We believe this paper opens the issues of
query optimization in memory-resident database systems
and presents practical solutions to them.",
acknowledgement = ack-nhfb,
affiliation = "IBM Thomas J. Watson Res. Center, Yorktown Heights,
NY, USA",
annote = "Office-by-example extends the concept of
query-by-example (QBE); disks are used only for
permanent storage of data and backup; The technique is
not a heuristic since it employs a systematic search,
but uses the branch-and-bound algorithm. Uses the
nested-loop join with use of indexes. An index is an
array of tuple identifiers. Assess uses binary search.
When an index entry is inserted, the upper half of the
index is block-copied. In a 3081 processor copying 1 MB
of memory takes less than 0.1 second. Queries in OBE
are in the canonical form, have no substructures. Pure
demand paging is not suitable, the system has a global
goal for paging activities. The set of virtual machines
on the dispatch list is determined.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Languages; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "experimentation; languages; Large Main Memory TODS,
algorithms; performance",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design, Access methods.",
}
@Article{Herlihy:1990:AVA,
author = "Maurice Herlihy",
title = "Apologizing Versus Asking Permission: Optimistic
Concurrency Control for Abstract Data Types",
journal = j-TODS,
volume = "15",
number = "1",
pages = "96--124",
month = mar,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68N25 (68P15 68Q65)",
MRnumber = "1 073 207",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-1/p96-herlihy/p96-herlihy.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-1/p96-herlihy/;
http://www.acm.org/pubs/toc/Abstracts/tods/77647.html",
abstract = "An optimistic concurrency control technique is one
that allows transactions to execute without
synchronization, relying on commit-time validation to
ensure serializability. Several new optimistic
concurrency control techniques for objects in
decentralized distributed systems are described here,
their correctness and optimality properties are proved,
and the circumstances under which each is likely to be
useful are characterized.\par
Unlike many methods that classify operations only as
Reads or Writes, these techniques systematically
exploit type-specific properties of objects to validate
more interleavings. Necessary and sufficient validation
conditions can be derived directly from an object's
data type specification. These techniques are also
modular: they can be applied selectively on a
per-object (or even per-operation) basis in conjunction
with standard pessimistic techniques such as two-phase
locking, permitting optimistic methods to be introduced
exactly where they will be most effective.\par
These techniques can be used to reduce the algorithmic
complexity of achieving high levels of concurrency,
since certain scheduling decisions that are NP-complete
for pessimistic schedulers can be validated after the
fact in time, independent of the level of concurrency.
These techniques can also enhance the availability of
replicated data, circumventing certain tradeoffs
between concurrency and availability imposed by
comparable pessimistic techniques.",
acknowledgement = ack-nhfb,
affiliation = "Carnegie Mellon Univ., Pittsburgh, PA, USA",
annote = "new optimistic techniques for objects; exploit
type-specific properties of objects to validate
interleavings. These techniques reduce the complexity
of achieving high levels of concurrency and enhance the
availability of replicated data. Deals with hot spots
such as counters, account balances, or queues.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Reliability; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "ADT TODS, algorithms; design; reliability;
verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency. {\bf D.3.3}: Software, PROGRAMMING
LANGUAGES, Language Constructs and Features, Abstract
data types. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Distributed systems. {\bf D.4.5}:
Software, OPERATING SYSTEMS, Reliability, Verification.
{\bf D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, Distributed file systems.",
}
@Article{Wald:1990:EAF,
author = "Joseph A. Wald and Paul G. Sorenson",
title = "Explaining Ambiguity in a Formal Query Language",
journal = j-TODS,
volume = "15",
number = "2",
pages = "125--161",
month = jun,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-2/p125-wald/p125-wald.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-2/p125-wald/;
http://www.acm.org/pubs/toc/Abstracts/tods/78923.html",
abstract = "The problem of generating reasonable natural
language-like responses to queries formulated in
nonnavigational query languages with logical data
independence is addressed. An extended ER model, the
Entity-Relationship-Involvement model, is defined which
assists in providing a greater degree of logical data
independence and the generation of natural language
explanations of a query processor's interpretation of a
query. These are accomplished with the addition of the
concept of an involvement to the model. Based on
involvement definitions in a formally defined data
definition language, DDL, an innovative strategy for
generating explanations is outlined and exemplified. In
the conclusion, possible extensions to the approach are
given.",
acknowledgement = ack-nhfb,
affiliation = "Schlumberger Lab. for Comput. Sci., Austin, TX, USA",
annote = "sorting out paths in the ER model.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models.",
}
@Article{Chakravarthy:1990:LBA,
author = "Upen S. Chakravarthy and John Grant and Jack Minker",
title = "Logic-Based Approach to Semantic Query Optimization",
journal = j-TODS,
volume = "15",
number = "2",
pages = "162--207",
month = jun,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-2/p162-chakravarthy/p162-chakravarthy.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-2/p162-chakravarthy/;
http://www.acm.org/pubs/toc/Abstracts/tods/78924.html",
abstract = "The purpose of semantic query optimization is to use
semantic knowledge (e.g., integrity constraints) for
transforming a query into a form that may be answered
more efficiently than the original version. In several
previous papers we described and proved the correctness
of a method for semantic query optimization in
deductive databases couched in first-order logic. This
paper consolidates the major results of these papers
emphasizing the techniques and their applicability for
optimizing relational queries. Additionally, we show
how this method subsumes and generalizes earlier work
on semantic query optimization. We also indicate how
semantic query optimization techniques can be extended
to databases that support recursion and integrity
constraints that contain disjunction, negation, and
recursion.",
acknowledgement = ack-nhfb,
annote = "consolidate results emphasizing the techniques and
their applicability for optimizing relational queries;
recursion and integrity constraints that contain
disjunction, negation, and recursion.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf I.2.3}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem Proving,
Logic programming. {\bf H.2.0}: Information Systems,
DATABASE MANAGEMENT, General, Security, integrity, and
protection. {\bf I.2.8}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Problem Solving, Control
Methods, and Search, Heuristic methods. {\bf I.2.8}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Problem Solving, Control Methods, and Search, Plan
execution, formation, generation.",
}
@Article{Whang:1990:LTP,
author = "Kyu-Young Whang and Brad T. {Vander-Zanden} and Howard
M. Taylor",
title = "A Linear-Time Probabilistic Counting Algorithm for
Database Applications",
journal = j-TODS,
volume = "15",
number = "2",
pages = "208--229",
month = jun,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib;
Theory/ProbAlgs.bib",
note = "A probabilistic technique called linear counting,
based on hashing, for counting the number of unique
values in the presence of duplicates is presented in
this paper.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-2/p208-whang/p208-whang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-2/p208-whang/;
http://www.acm.org/pubs/toc/Abstracts/tods/78925.html",
abstract = "We present a probabilistic algorithm for counting the
number of unique values in the presence of duplicates.
This algorithm has $O$ ($q$ ) time complexity, where
$q$ is the number of values including duplicates, and
produces an estimation with an arbitrary accuracy
prespecified by the user using only a small amount of
space. Traditionally, accurate counts of unique values
were obtained by sorting, which has $O$ ($q$ log $q$ )
time complexity. Our technique, called {\em linear
counting}, is based on hashing. We present a
comprehensive theoretical and experimental analysis of
linear counting. The analysis reveals an interesting
result: A load factor (number of unique values/hash
table size) much larger than 1.0 (e.g., 12) can be used
for accurate estimation (e.g., 1\% of error). We present
this technique with two important applications to
database problems: namely, (1) obtaining the column
cardinality (the number of unique values in a column of
a relation) and (2) obtaining the join selectivity (the
number of unique values in the join column resulting
from an unconditional join divided by the number of
unique join column values in the relation to he
joined). These two parameters are important statistics
that are used in relational query optimization and
physical database design.",
acknowledgement = ack-nhfb,
affiliation = "Korea Adv. Inst. of Sci. and Technol., Seoul, South
Korea",
annote = "Counting the number of unique values in the presence
of duplicates; $ O(n) $ time complexity based on
hashing.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance;
Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; experimentation; hashing sampling TODS,
algorithms; performance; theory",
subject = "{\bf G.3}: Mathematics of Computing, PROBABILITY AND
STATISTICS, Probabilistic algorithms (including Monte
Carlo). {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Access methods.",
}
@Article{Jajodia:1990:DVA,
author = "Sushil Jajodia and David Mutchler",
title = "Dynamic Voting Algorithms for Maintaining the
Consistency of a Replicated Database",
journal = j-TODS,
volume = "15",
number = "2",
pages = "230--280",
month = jun,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-2/p230-jajodia/p230-jajodia.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-2/p230-jajodia/;
http://www.acm.org/pubs/toc/Abstracts/tods/78926.html",
abstract = "There are several replica control algorithms for
managing replicated files in the face of network
partitioning due to site or communication link
failures. Pessimistic algorithms ensure consistency at
the price of reduced availability; they permit at most
one (distinguished) partition to process updates at any
given time. The best known pessimistic algorithm, {\em
voting}, is a ``static'' algorithm, meaning that all
potential distinguished partitions can be listed in
advance. We present a dynamic extension of voting
called {\em dynamic voting}. This algorithm permits
updates in a partition provided it contains more than
half of the {\em up-to-date\/} copies of the replicated
file. We also present an extension of dynamic voting
called {\em dynamic voting with linearly ordered
copies\/} (abbreviated as {\em dynamic-linear\/}).
These algorithms are dynamic because the order in which
past distinguished partitions were created plays a role
in the selection of the next distinguished partition.
Our algorithms have all the virtues of ordinary voting,
including its simplicity, and provide improved
availability as well. We provide two stochastic models
to support the latter claim. In the first (site) model,
sites may fail but communication links are infallible;
in the second (link) model the reverse is true. We
prove that under the site model, dynamic-linear has
greater availability than any static algorithm,
including weighted voting, if there are four or more
sites in the network. In the link model, we consider
all biconnected five-site networks and a wide variety
of failure and repair rates. In all cases considered,
dynamic-linear had greater availability than any static
algorithm.",
acknowledgement = ack-nhfb,
affiliation = "George Mason Univ., Fairfax, VA, USA",
annote = "mathematical analysis shows that dynamic-linear is
better than static voting algorithms",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; reliability",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf D.4.3}: Software, OPERATING
SYSTEMS, File Systems Management, Distributed file
systems. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Distributed systems. {\bf C.4}:
Computer Systems Organization, PERFORMANCE OF SYSTEMS,
Reliability, availability, and serviceability.",
}
@Article{Dasgupta:1990:FCC,
author = "Partha Dasgupta and Zvi M. Kedem",
title = "The Five-Color Concurrency Control Protocol:
Non-Two-Phase Locking in General Databases",
journal = j-TODS,
volume = "15",
number = "2",
pages = "281--307",
month = jun,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 156 124",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-2/p281-dasgupta/p281-dasgupta.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-2/p281-dasgupta/;
http://www.acm.org/pubs/toc/Abstracts/tods/78927.html",
abstract = "Concurrency control protocols based on two-phase
locking are a popular family of locking protocols that
preserve serializability in general (unstructured)
database systems. A concurrency control algorithm (for
databases with no inherent structure) is presented that
is practical, non two-phase, and allows varieties of
serializable logs not possible with any commonly known
locking schemes. All transactions are required to
predeclare the data they intend to read or write. Using
this information, the protocol anticipates the
existence (or absence) of possible conflicts and hence
can allow non-two-phase locking.\par
It is well known that serializability is characterized
by acyclicity of the conflict graph representation of
interleaved executions. The two-phase locking protocols
allow only {\em forward\/} growth of the paths in the
graph. The {\em Five Color\/} protocol allows the
conflict graph to grow in any direction (avoiding
two-phase constraints) and prevents cycles in the graph
by maintaining transaction access information in the
form of data-item markers. The read and write set
information can also be used to provide relative
immunity from deadlocks.",
acknowledgement = ack-nhfb,
affiliation = "Georgia Inst. of Technol., Atlanta, GA, USA",
annote = "allow varieties of serializable logs not possible with
known locking schemes; the protocol anticipates the
existence of possible conflicts and hence can allow
non-two-phase locking.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; predeclared lock sets
TODS",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency.",
}
@Article{Moore:1990:DTA,
author = "James C. Moore and William B. Richmond and Andrew B.
Whinston",
title = "A Decision-Theoretic Approach to Information
Retrieval",
journal = j-TODS,
volume = "15",
number = "3",
pages = "311--340",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "91h:68037",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p311-moore/p311-moore.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p311-moore/;
http://www.acm.org/pubs/toc/Abstracts/tods/88597.html",
abstract = "We present the file search problem in a
decision-theoretic framework, and discuss a variation
of it that we call the common index problem. The goal
of the common index problem is to return the best
available record in the file, where {\em best\/} is in
terms of a class of user preferences. We use dynamic
programming to construct an optimal algorithm using two
different optimality criteria, and we develop
sufficient conditions for obtaining complete
information.",
acknowledgement = ack-nhfb,
affiliation = "Purdue Univ., West Lafayette, IN, USA",
annote = "searching a file for a best record rather than a
specific one; the assumption is that the preferences of
the ith individual can be represented as a composite
where preferences are based on the same index for all
users",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Economics; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; approximate algorithms; design; economics;
economics of information; information retrieval;
theory",
subject = "{\bf E.5}: Data, FILES, Sorting/searching. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Search
process.",
}
@Article{Westland:1990:SOC,
author = "J. Christopher Westland",
title = "Scaling Up Output Capacity and Performance Results
from Information Systems Prototypes",
journal = j-TODS,
volume = "15",
number = "3",
pages = "341--358",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p341-westland/p341-westland.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p341-westland/;
http://www.acm.org/pubs/toc/Abstracts/tods/87943.html",
abstract = "The advantage of information system prototyping arises
from its predict problems and end-user satisfaction
with a system early in the development process, before
significant commitments of time and effort have been
made. Predictions of problems and end-user satisfaction
have risen in importance with the increasing complexity
of business information systems and the exponential
growth of database size. This research investigates the
reporting of information to an end user, and the
process of inferring from a prototype to a full-scale
information system. This inference is called {\em
scaling up}, and is an important part of the systems
development planning process. The research investigates
information systems reporting from a linguistic
perspective, where a database is used as a central
receptacle for information storage. It then
investigates the manner in which reporting statistics
from the prototype information system may be used to
infer the behavior and performance of the full-scale
system. An example is presented for the application of
the algorithm, and the final section discusses the
usefulness, application, and implications of the
algorithm developed in this research.",
acknowledgement = ack-nhfb,
affiliation = "Univ. of Southern California, Los Angeles, CA, USA",
annote = "a coarse introduction, mainly the recall of
information retrieval systems; the mathematics is wrong
and too simple.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; inclusion-exclusion principle;
performance",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval. {\bf
C.4}: Computer Systems Organization, PERFORMANCE OF
SYSTEMS, Measurement techniques.",
}
@Article{Alonso:1990:DCI,
author = "Rafael Alonso and Daniel Barbara and H{\'e}ctor
Garc{\'\i}a-Molina",
title = "Data Caching Issues in an Information Retrieval
System",
journal = j-TODS,
volume = "15",
number = "3",
pages = "359--384",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p359-alonso/p359-alonso.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p359-alonso/;
http://www.acm.org/pubs/toc/Abstracts/tods/87848.html",
abstract = "Currently, a variety of information retrieval systems
are available to potential users\ldots{}. While in many
cases these systems are accessed from personal
computers, typically no advantage is taken of the
computing resources of those machines (such as local
processing and storage). In this paper we explore the
possibility of using the user's local storage
capabilities to cache data at the user's site. This
would improve the response time of user queries albeit
at the cost of incurring the overhead required in
maintaining multiple copies. In order to reduce this
overhead it may be appropriate to allow copies to
diverge in a controlled fashion\ldots{}. Thus, we
introduce the notion of quasi-copies, which embodies
the ideas sketched above. We also define the types of
deviations that seem useful, and discuss the available
implementation strategies.",
acknowledgement = ack-nhfb,
affiliation = "Princeton Univ., NJ, USA",
annote = "focus: cache coherency in distributed information
retrieval systems one central server site, data cached
at client site. Less response time, but more overhead
in maintaining multiple copies. To reduce overhead,
allow copies to diverge in a controlled fashion -
notion of ``quasi copies'' and quasi-caching. - users
can precisely define limits for divergence of
quasi-copies. - reduces update propagation overhead -
main difference with materialized views is that here
user can establish degree of coherency - implementation
possibilities: invalidate/refresh out-of-date data,
include automatic expiration date etc. Paper surveys
various implementation strategies and their tradeoffs.
users give two types of conditions on quasi-caches:
selection and coherency. - selection conditions specify
which object images will be cached at the user site. -
modifiers: - Add/drop (add to cache or remove) -
compulsory or advisory (whether caching is to be
enforced or to be taken as a hint) - query optimizer
can take advantage if caching is compulsory - advisory
selection gives greater system flexibility - static /
dynamic (static => objects selected once when the
condition is issued by a user, dynamic => changes in
data cause objects to be added/dropped dynamically). -
triggering delay: specifies acceptable delay for
dynamic selections - coherency conditions define the
allowable deviations between an object and its images.
- default: image must have a valid value (though
out-of-date) - delay: how much time an image may lag
behind an object - version: acceptable lag of how many
versions - periodic: image to be refreshed periodically
- arithmetic: deviations limited by the difference
between the values of the object and its image. - can
also have inter-object consistency constraints.
implementation issues - transmission delays and
failures: ``null'' messages sent out by central site to
check if client is alive etc. - what to propagate: -
data message: contains new values to overwrite old ones
in cache - invalidation message: only identifies
invalid object to be purged from the cache, but does
not contain new values. - version number message:
provides new version numbers only - no new data -
implicit invalidation: no message from central site,
cache images automatically invalidated after a certain
time. - when to propagate: - last minute: delayed until
a selection/coherency condition is about to be
violated. - immediately: as soon as updates occur -
delayed update at central site, so no cache conditions
are violated. - collapsing conditions: - possible to
collapse several coherency conditions on same object
into one - load balancing: central site can partially
off-load enforcement of consistency to clients
describes a probabilistic performance model and
simulation results - simulation parameters are network
traffic, query processing time, update installation
time etc. conclusions: - quasi-caching can potentially
improve performance and availability - problems if: -
selection and consistency constraints are complex -
large number of updates at central site - open issues:
- how much data to cache - how does choice of when to
propagate updates affect performance etc.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Management; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cache coherency; data sharing; design; information
retrieval systems; management; performance",
subject = "{\bf H.3.5}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Online Information Services, Data bank
sharing. {\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf D.4.7}: Software, OPERATING
SYSTEMS, Organization and Design, Distributed systems.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems.",
}
@Article{Kifer:1990:CTQ,
author = "Michael Kifer and Eliezer L. Lozinskii",
title = "On Compile-Time Query Optimization In Deductive
Databases By Means of Static Filtering",
journal = j-TODS,
volume = "15",
number = "3",
pages = "385--426",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 081 178",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p385-kifer/p385-kifer.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p385-kifer/;
http://www.acm.org/pubs/toc/Abstracts/tods/87121.html",
abstract = "We extend the query optimization techniques known as
algebraic manipulations with relational expressions
[48] to work with deductive databases. In particular,
we propose a method for moving data-independent
selections and projections into recursive axioms, which
extends all other known techniques for performing that
task [2, 3, 9, 18, 20]. We also show that, in a
well-defined sense, our algorithm is optimal among the
algorithms that propagate data-independent selections
through recursion.",
acknowledgement = ack-nhfb,
affiliation = "State Univ. of New York, Stony Brook, NY, USA",
annote = "Discusses algebraic optimizations for logic
programs.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Management; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; dataflow; deductive databases; design;
filtering; fixpoint; graph representation; inference;
management; performance; projection; recursive rules;
selection; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.3.3}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval, Selection process. {\bf I.2.3}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Deduction and Theorem Proving, Deduction. {\bf I.2.8}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Problem Solving, Control Methods, and Search, Graph and
tree search strategies.",
}
@Article{Agrawal:1990:DTC,
author = "Rakesh Agrawal and Shaul Dar and H. V. Jagadish",
title = "Direct Transitive Closure Algorithms: Design and
Performance Evaluation",
journal = j-TODS,
volume = "15",
number = "3",
pages = "427--458",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68Q25 68R05)",
MRnumber = "91h:68029",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p427-agrawal/p427-agrawal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p427-agrawal/;
http://www.acm.org/pubs/toc/Abstracts/tods/88888.html",
abstract = "We present new algorithms for computing transitive
closure of large database relations. Unlike iterative
algorithms, such as the seminaive and logarithmic
algorithms, the termination of our algorithms does not
depend on the length of paths in the underlying graph
(hence the name {\em direct\/} algorithms). Besides
reachability computations, the proposed algorithms can
also be used for solving path problems. We discuss
issues related to the efficient implementation of these
algorithms, and present experimental results that show
the direct algorithms perform uniformly better than the
iterative algorithms. A side benefit of this work is
that we have proposed a new methodology for evaluating
the performance of recursive queries.",
acknowledgement = ack-nhfb,
affiliation = "AT\&T Bell Labs., Murray Hill, NJ, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "deductive databases; design; experimentation;
performance; query processing; recursive query
processing TODS, algorithms; transitive closure",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems. {\bf I.2.8}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Problem Solving, Control
Methods, and Search. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems.",
}
@Article{Zhang:1990:NSC,
author = "Weining Zhang and Clement T. Yu and Daniel Troy",
title = "Necessary and Sufficient Conditions to Linearize
Doubly Recursive Programs in Logic Databases",
journal = j-TODS,
volume = "15",
number = "3",
pages = "459--482",
month = sep,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68T15)",
MRnumber = "91h:68036",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-3/p459-zhang/p459-zhang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-3/p459-zhang/;
http://www.acm.org/pubs/toc/Abstracts/tods/89237.html",
abstract = "Linearization of nonlinear recursive programs is an
important issue in logic databases for both practical
and theoretical reasons. If a nonlinear recursive
program can be transformed into an equivalent linear
recursive program, then it may be computed more
efficiently than when the transformation is not
possible. We provide a set of necessary and sufficient
conditions for a simple doubly recursive program to be
equivalent to a simple linear recursive program. The
necessary and sufficient conditions can be verified
effectively.",
acknowledgement = ack-nhfb,
acmcrnumber = "9211-0888",
affiliation = "Illinois Univ., Chicago, IL, USA",
annote = "extends authors' previous results",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CTYU TODS, algorithms; design; logic database;
theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving, Logic programming.",
}
@Article{Can:1990:CEC,
author = "Fazli Can and Esen A. Ozkarahan",
title = "Concepts and Effectiveness of the
Cover-Coefficient-Based Clustering Methodology for Text
Databases",
journal = j-TODS,
volume = "15",
number = "4",
pages = "483--517",
month = dec,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-4/p483-can/p483-can.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-4/p483-can/;
http://www.acm.org/pubs/toc/Abstracts/tods/99938.html",
abstract = "A new algorithm for document clustering is introduced.
The base concept of the algorithm, the cover
coefficient (CC) concept, provides a means of
estimating the number of clusters within a document
database and related indexing and clustering
analytically. The CC concept is used also to identify
the cluster seeds and to form clusters with these
seeds. It is shown that the complexity of the
clustering process is very low. The retrieval
experiments show that the information-retrieval
effectiveness of the algorithm is compatible with a
very demanding complete linkage clustering method that
is known to have good retrieval performance. The
experiments also show that the algorithm is 15.1 to
63.5 (with an average of 47.5) percent better than four
other clustering algorithms in cluster-based
information retrieval. The experiments have validated
the indexing-clustering relationships and the
complexity of the algorithm and have shown improvements
in retrieval effectiveness. In the experiments two
document databases are used: TODS214 and INSPEC. The
latter is a common database with 12,684 documents.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Syst. Anal., Miami Univ., Oxford, OH, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cluster validity; clustering-indexing relationships;
cover coefficient; decoupling coefficient; design;
document retrieval; experimentation; Inf. retrieval
TODS, algorithms; retrieval effectiveness",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Clustering. {\bf H.3.1}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Content Analysis and
Indexing, Indexing methods. {\bf H.3.6}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Library
Automation, Large text archives. {\bf I.7.0}: Computing
Methodologies, TEXT PROCESSING, General.",
}
@Article{Nakano:1990:TOR,
author = "Ryohei Nakano",
title = "Translation with Optimization from Relational Calculus
to Relational Algebra Having Aggregate Functions",
journal = j-TODS,
volume = "15",
number = "4",
pages = "518--557",
month = dec,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "1 093 243",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-4/p518-nakano/p518-nakano.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-4/p518-nakano/;
http://www.acm.org/pubs/toc/Abstracts/tods/99943.html",
abstract = "Most of the previous translations of relational
calculus to relational algebra aimed at proving that
the two languages have the equivalent expressive power,
thereby generating very complicated relational algebra
expressions, especially when aggregate functions are
introduced. This paper presents a rule-based
translation method from relational calculus expressions
having both aggregate functions and null values to
optimized relational algebra expressions. Thus, logical
optimization is carried out through translation. The
translation method comprises two parts: the
translational of the relational calculus kernel and the
translation of aggregate functions. The former uses the
familiar step-wise rewriting strategy, while the latter
adopts a two-phase rewriting strategy via standard
aggregate expressions. Each translation proceeds by
applying a heuristic rewriting rule in preference to a
basic rewriting rule. After introducing SQL-type null
values, their impact on the translation is thoroughly
investigated, resulting in several extensions of the
translation. A translation experiment with many queries
shows that the proposed translation method generates
optimized relational algebra expressions. It is shown
that heuristic rewriting rules play an essential role
in the optimization. The correctness of the present
translation is also shown.\par
\ldots{} aggregate expressions. Each translation
proceeds by applying a heuristic rewriting rule in
preference to a basic rewriting rule. After introducing
SQL-type null values, their impact on the translation
is thoroughly investigated, resulting in several
extensions of the translation. A translation experiment
with many queries shows that the proposed translation
method generates optimized relational",
acknowledgement = ack-nhfb,
affiliation = "Knowledge Syst. Lab., NTT Commun. and Inf. Process.
Lab., Kanagawa, Japan",
annote = "a rule-based translation method from expressions
having aggregate functions being a two-phase rewriting
strategy; experiment with many queries shows that
heuristic rules are essential in optimization; the
translation will from the front end of a database
machine, MACH, developed by the author.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; languages; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing.",
}
@Article{Jagadish:1990:CTM,
author = "H. V. Jagadish",
title = "A Compression Technique to Materialize Transitive
Closure",
journal = j-TODS,
volume = "15",
number = "4",
pages = "558--598",
month = dec,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "1 093 244",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-4/p558-jagadish/p558-jagadish.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-4/p558-jagadish/;
http://www.acm.org/pubs/toc/Abstracts/tods/99944.html",
abstract = "An important feature of database support for expert
systems is the ability of the database to answer
queries regarding the existence of a path from one node
to another in the directed graph underlying some
database relation. Given just the database relation,
answering such a query is time-consuming, but given the
transitive closure of the database relation a table
look-up suffices. We present an indexing scheme that
permits the storage of the pre-computed transitive
closure of a database relation in a compressed form.
The existence of a specified tuple in the closure can
be determined from this compressed store by a single
look-up followed by an index comparison. We show how to
add nodes and arcs to the compressed closure
incrementally. We also suggest how this compression
technique can be used to reduce the effort required to
compute the transitive closure.",
acknowledgement = ack-nhfb,
affiliation = "AT\&T Bell Lab., Murray Hill, NJ, USA",
annote = "an indexing scheme that permits the storage of the
pre-computed transitive closure",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "performance; recursive query processing TODS,
algorithms",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf I.2.1}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Applications
and Expert Systems. {\bf I.2.8}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Problem
Solving, Control Methods, and Search.",
}
@Article{Omiecinski:1990:PAR,
author = "Edward Omiecinski and Peter Scheuermann",
title = "A Parallel Algorithm for Record Clustering",
journal = j-TODS,
volume = "15",
number = "4",
pages = "599--624",
month = dec,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (68Q25)",
MRnumber = "1 093 245",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-4/p599-omiecinski/p599-omiecinski.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-4/p599-omiecinski/;
http://www.acm.org/pubs/toc/Abstracts/tods/99947.html",
abstract = "We present an efficient heuristic algorithm for record
clustering that can run on a SIMD machine. We introduce
the P-tree, and its associated numbering scheme, which
in the split phase allows each processor independently
to compute the unique cluster number of a record
satisfying an arbitrary query. We show that by
restricting ourselves in the merge phase to combining
only sibling clusters, we obtain a parallel algorithm
whose speedup ratio is optimal in the number of
processors used. Finally, we report on experiments
showing that our method produces substantial savings in
an environment with relatively little overlap among the
queries.",
acknowledgement = ack-nhfb,
affiliation = "Sch. of Inf. and Comput. Sci., Georgia Inst. of
Technol., Atlanta, GA, USA",
annote = "for SIMD machine",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; experimentation; performance; Physical
database design TODS, algorithms",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Clustering. {\bf C.1.2}: Computer Systems Organization,
PROCESSOR ARCHITECTURES, Multiple Data Stream
Architectures (Multiprocessors),
Single-instruction-stream, multiple-data-stream
processors (SIMD). {\bf F.2.2}: Theory of Computation,
ANALYSIS OF ALGORITHMS AND PROBLEM COMPLEXITY,
Nonnumerical Algorithms and Problems, Sequencing and
scheduling. {\bf H.3.2}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Storage.
{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design.",
}
@Article{Lomet:1990:HTM,
author = "David B. Lomet and Betty Salzberg",
title = "The {hB-Tree}: a Multiattribute Indexing Method with
Good Guaranteed Performance",
journal = j-TODS,
volume = "15",
number = "4",
pages = "625--658",
month = dec,
year = "1990",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1990-15-4/p625-lomet/p625-lomet.pdf;
http://www.acm.org/pubs/citations/journals/tods/1990-15-4/p625-lomet/;
http://www.acm.org/pubs/toc/Abstracts/tods/99949.html",
abstract = "A new multiattribute index structure called the
hB-tree is introduced. It is derived from the
K-D-B-tree of Robinson [15] but has additional
desirable properties. The hB-tree internode search and
growth processes are precisely analogous to the
corresponding processes in B-trees [1]. The intranode
processes are unique. A k-d tree is used as the
structure within nodes for very efficient searching.
Node splitting requires that this k-d tree be split.
This produces nodes which no longer represent
brick-like regions in k-space, but that can be
characterized as holey bricks, bricks in which
subregions have been extracted. We present results that
guarantee hB-tree users decent storage utilization,
reasonable size index terms, and good search and insert
performance. These results guarantee that the hB-tree
copes well with arbitrary distributions of keys.",
acknowledgement = ack-nhfb,
annote = "multiattributable index; node splitting produces nodes
that can be characterized as holey bricks",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; multi dimensional range queries TODS;
performance",
subject = "{\bf E.1}: Data, DATA STRUCTURES, Trees. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Access methods. {\bf H.3.2}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Storage, File organization.",
}
@Article{Abiteboul:1991:RBL,
author = "Serge Abiteboul and St{\'e}phane Grumbach",
title = "A Rule-Based Language with Functions and Sets",
journal = j-TODS,
volume = "16",
number = "1",
pages = "1--30",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68Q45 (68N17 68P15)",
MRnumber = "92a:68067",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p1-abiteboul/p1-abiteboul.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p1-abiteboul/;
http://www.acm.org/pubs/toc/Abstracts/tods/103141.html",
abstract = "A logic based language for manipulating complex
objects constructed using set and tuple constructors is
introduced. A key feature of the COL language is the
use of base and derived data functions. Under some
stratification restrictions, the semantics of programs
is given by a minimal and justified model that can be
computed using a finite sequence of fixpoints. The
language is extended using external functions and
predicates. An implementation of COL in a functional
language is briefly discussed.",
acknowledgement = ack-nhfb,
affiliation = "INRIA, Le Chesnay, France",
annote = "the COL language uses base and derived data
functions",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "complex objects; deductive databases; deductive
knowledge TODS, design; fixpoint semantics; knowledge
bases; languages; object-oriented databases; rule
based; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving. {\bf F.4.1}: Theory of Computation,
MATHEMATICAL LOGIC AND FORMAL LANGUAGES, Mathematical
Logic, Logic programming.",
}
@Article{Mendelzon:1991:FDH,
author = "Alberto O. Mendelzon and Peter T. Wood",
title = "Functional dependencies in {Horn} clause queries",
journal = j-TODS,
volume = "16",
number = "1",
pages = "31--55",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (68N17)",
MRnumber = "92b:68028",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p31-mendelzon/p31-mendelzon.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p31-mendelzon/;
http://www.acm.org/pubs/toc/Abstracts/tods/103142.html",
abstract = "When a database query is expressed as a set of Horn
clauses whose execution is by top-down resolution of
goals, there is a need to improve the backtracking
behavior of the interpreter. Rather than putting on the
programmer the onus of using extra-logical operators
such as {\em cut\/} to improve performance, we show
that some uses of the cut can be automated by inferring
them from functional dependencies. This requires some
knowledge of which variables are guaranteed to be bound
at query execution time; we give a method for deriving
such information using data flow analysis.",
acknowledgement = ack-nhfb,
affiliation = "Comput. Syst. Res. Inst., Toronto Univ., Ont.,
Canada",
annote = "some uses of the cut can be automated by inferring
them; this requires knowledge of which variables are
bound at execution time",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data flow analysis; design; functional dependency;
logic programming; performance; relational database;
theory; theory deductive knowledge TODS, algorithms",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving, Deduction. {\bf I.2.3}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving, Logic programming.",
}
@Article{Meghini:1991:COF,
author = "C. Meghini and C. Thanos",
title = "The Complexity of Operations on a Fragmented
Relation",
journal = j-TODS,
volume = "16",
number = "1",
pages = "56--87",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68Q25)",
MRnumber = "92g:68036",
MRreviewer = "K. Marguerite Hafen",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p56-meghini/p56-meghini.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p56-meghini/;
http://www.acm.org/pubs/toc/Abstracts/tods/103143.html",
abstract = "Data fragmentation is an important aspect of
distributed database design, in which portions of
relations, tailored to the specific needs of local
applications, are defined to be further allocated to
the sites of the computer network supporting the
database system. In this paper we present a theory of
fragmentation with overlapping fragments to study the
complexity of the problems involved in checking the
completeness of a fragmentation schema and in querying
and updating a fragmented relation. We analyze these
problems from the complexity viewpoint and present
sound and complete algorithms for their solution.",
acknowledgement = ack-nhfb,
affiliation = "Istituto di Elaborazione della Inf., CNR, Pisa,
Italy",
annote = "Proposes a two-step process to reconstruct first
minimal horizontal, then vertical covers. When
fragments overlap, optimization becomes intractible.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory;
Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; completeness of fragmentation schemas;
design; NP-hardness; performance; query optimization;
relation fragmentation; theory; updates; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing. {\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems.
{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf F.1.3}:
Theory of Computation, COMPUTATION BY ABSTRACT DEVICES,
Complexity Classes.",
}
@Article{Rabitti:1991:MAN,
author = "Fausto Rabitti and Elisa Bertino and Won Kim and
Darrell Woelk",
title = "A Model of Authorization for Next-Generation Database
Systems",
journal = j-TODS,
volume = "16",
number = "1",
pages = "88--131",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p88-rabitti/p88-rabitti.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p88-rabitti/;
http://www.acm.org/pubs/toc/Abstracts/tods/103144.html",
abstract = "The conventional models of authorization have been
designed for database systems supporting the
hierarchical, network, and relational models of data.
However, these models are not adequate for
next-generation database systems that support richer
data models that include object-oriented concepts and
semantic data modeling concepts. Rabitti, Woelk, and
Kim [14] presented a preliminary model of authorization
for use as the basis of an authorization mechanism in
such database systems. In this paper we present a
fuller model of authorization that fills a few major
gaps that the conventional models of authorization
cannot fill for next-generation database systems. We
also further formalize the notion of implicit
authorization and refine the application of the notion
of implicit authorization to object-oriented and
semantic modeling concepts. We also describe a user
interface for using the model of authorization and
consider key issues in implementing the authorization
model.",
acknowledgement = ack-nhfb,
affiliation = "Microelectronics and Comput. Technol. Corp., CNR,
Pisa, Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Security; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "object-oriented database; security; security access
control TODS, design; semantic database; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf D.1.5}: Software,
PROGRAMMING TECHNIQUES, Object-oriented Programming.
{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection.",
}
@Article{Weikum:1991:PRS,
author = "Gerhard Weikum",
title = "Principles and Realization Strategies of Multilevel
Transaction Management",
journal = j-TODS,
volume = "16",
number = "1",
pages = "132--180",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p132-weikum/p132-weikum.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p132-weikum/;
http://www.acm.org/pubs/toc/Abstracts/tods/103145.html",
abstract = "One of the demands of database system transaction
management is to achieve a high degree of concurrency
by taking into consideration the semantics of
high-level operations. On the other hand, the
implementation of such operations must pay attention to
conflicts on the storage representation levels below.
To meet these requirements in a layered architecture,
we propose a multilevel transaction management
utilizing layer-specific semantics. Based on the
theoretical notion of multilevel serializability, a
family of concurrency control strategies is developed.
Suitable recovery protocols are investigated for
aborting single transactions and for restarting the
system after a crash. The choice of levels involved in
a multilevel transaction strategy reveals an inherent
trade-off between increased concurrency and growing
recovery costs. A series of measurements has been
performed in order to compare several strategies.
Preliminary results indicate considerable performance
gains of the multilevel transaction approach.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., ETH Zurich, Switzerland",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Management; Performance;
Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "atomicity persistence concurrency control; concurrency
control recovery atomicity nested transactions TODS,
algorithms; design; management; multilevel
transactions; performance; persistence; reliability;
serializability",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf D.4.1}: Software,
OPERATING SYSTEMS, Process Management, Concurrency.
{\bf H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration, Logging and recovery. {\bf
D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Synchronization.",
}
@Article{Wolfson:1991:MPR,
author = "Ouri Wolfson and Amir Milo",
title = "The Multicast Policy and its Relationship to
Replicated Data Placement",
journal = j-TODS,
volume = "16",
number = "1",
pages = "181--205",
month = mar,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68M10)",
MRnumber = "92a:68042",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See corrigendum in \cite{Wolfson:1991:CMP}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-1/p181-wolfson/p181-wolfson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-1/p181-wolfson/;
http://www.acm.org/pubs/toc/Abstracts/tods/103146.html",
abstract = "In this paper we consider the communication complexity
of maintaining the replicas of a logical data-item, in
a database distributed over a computer network. We
propose a new method, called the minimum spanning tree
write, by which a processor in the network should
multicast a write of a logical data-item, to all the
processors that store replicas of the items. Then we
show that the minimum spanning tree write is optimal
from the communication cost point of view. We also
demonstrate that the method by which a write is
multicast to all the replicas of a data-item affects
the optimal replication scheme of the item, i.e., at
which processors in the network the replicas should be
located. Therefore, next we consider the problem of
determining an optimal replication scheme for a data
item, assuming that each processor employs the minimum
spanning tree write at run-time. The problem for
general networks is shown NP-Complete, but we provide
efficient algorithms to obtain an optimal allocation
scheme for three common types of network topologies.
They are completely-connected, tree, and ring networks.
For these topologies, efficient algorithms are also
provided for the case in which reliability
considerations dictate a minimum number of replicas.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Columbia Univ., New York, NY,
USA",
annote = "mimumun spanning tree write and multicast to store
replicas",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "181 TODS, algorithms; complexity; computer network;
file allocation; message passing; NP-Complete;
performance; theory",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf C.4}: Computer Systems
Organization, PERFORMANCE OF SYSTEMS. {\bf C.2.1}:
Computer Systems Organization, COMPUTER-COMMUNICATION
NETWORKS, Network Architecture and Design. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Distributed systems.",
}
@Article{Casanova:1991:STM,
author = "M. A. Casanova and A. L. Furtado and L. Tucherman",
title = "A Software Tool for Modular Database Design",
journal = j-TODS,
volume = "16",
number = "2",
pages = "209--234",
month = jun,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-2/p209-casanova/p209-casanova.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-2/p209-casanova/;
http://www.acm.org/pubs/toc/Abstracts/tods/103711.html",
abstract = "A modularization discipline for database schemas is
first described. The discipline incorporates both a
strategy for enforcing integrity constraints and a
tactic for organizing large sets of database
structures, integrity constraints, and operations. A
software tool that helps the development and
maintenance of database schemas modularized according
to the discipline is then presented. It offers a
user-friendly interface that guides the designer
through the various stages of the creation of a new
module or through the process of changing objects of
existing modules. The tool incorporates, in a
declarative style, a description of the design and
redesign rules behind the modularization discipline,
hence facilitating the incremental addition of new
expertise about database design.",
acknowledgement = ack-nhfb,
affiliation = "Rio Sci. Center, IBM Brazil, Rio de Janeiro, Brazil",
annote = "first modularize, then use the tool to develop and
maintain schemas; functions declared to enforce
constraints",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data types; consistency preservation; design;
encapsulation; integrity constraints; languages;
logical database design; modular design; module
constructors",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf D.2.2}:
Software, SOFTWARE ENGINEERING, Tools and Techniques.
{\bf D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Modules, packages. {\bf
H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration.",
}
@Article{VanGelder:1991:STR,
author = "Allen {Van Gelder} and Rodney W. Topor",
title = "Safety and Translation of Relational Calculus
Queries",
journal = j-TODS,
volume = "16",
number = "2",
pages = "235--278",
month = jun,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "92c:68037",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-2/p235-van_gelder/p235-van_gelder.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-2/p235-van_gelder/;
http://www.acm.org/pubs/toc/Abstracts/tods/103712.html",
abstract = "Not all queries in relational calculus can be answered
sensibly when disjunction, negation, and universal
quantification are allowed. The class of relation
calculus queries or formulas that have sensible answers
is called the {\em domain independent\/} class which is
known to be undecidable. Subsequent research has
focused on identifying large decidable subclasses of
domain independent formulas. In this paper we
investigate the properties of two such classes: the
{\em evaluable\/} formulas and the {\em allowed\/}
formulas. Although both classes have been defined
before, we give simplified definitions, present short
proofs of their main properties, and describe a method
to incorporate equality.\par
Although evaluable queries have sensible answers, it is
not straightforward to compute them efficiently or
correctly. We introduce {\em relational algebra normal
form\/} for formulas from which form the correct
translation into relational algebra is trivial. We give
algorithms to transform an evaluable formula into an
equivalent {\em allowed\/} formula and from there into
relational algebra normal form. Our algorithms avoid
use of the so-called {\em Dom\/} relation, consisting
of all constants appearing in the database or the
query.\par
Finally, we describe a restriction under which every
domain independent formula is evaluable and argue that
the class of evaluable formulas is the largest
decidable subclass of the domain independent formulas
that can be efficiently recognized.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Santa Cruz, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "allowed formulas; domain independence; evaluable
formulas; existential normal; query translation;
relational algebra; relational calculus",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf F.4.1}: Theory of Computation,
MATHEMATICAL LOGIC AND FORMAL LANGUAGES, Mathematical
Logic, Model theory.",
}
@Article{Shasha:1991:OEQ,
author = "Dennis Shasha and Tsong-Li L. Wang",
title = "Optimizing Equijoin Queries in Distributed Databases
where Relations are Hash-Partitioned",
journal = j-TODS,
volume = "16",
number = "2",
pages = "279--308",
day = "1",
month = jun,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "92c:68036",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib; UnCover
library database",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-2/p279-shasha/p279-shasha.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-2/p279-shasha/;
http://www.acm.org/pubs/toc/Abstracts/tods/103713.html",
abstract = "Consider the class of distributed database systems
consisting of a set of nodes connected by a high
bandwidth network. Each node consists of a processor, a
random access memory, and a slower but much larger
memory such as a disk. There is no shared memory among
the nodes. The data are horizontally partitioned often
using a hash function. Such a description characterizes
many parallel or distributed database systems that have
recently been proposed, both commercial and academic.
We study the optimization problem that arises when the
query processor must repartition the relations and
intermediate results participating in a multijoin
query. Using estimates of the sizes of intermediate
relations, we show (1) optimum solutions for closed
chain queries; (2) the NP-completeness of the
optimization problem for star, tree, and general graph
queries; and (3) effective heuristics for these hard
cases.\par
Our general approach and many of our results extend to
other attribute partitioning schemes, for example,
sort-partitioning on attributes, and to partitioned
object databases.",
acknowledgement = ack-nhfb,
affiliation = "Courant Inst. of Math. Sci., New York Univ., NY, USA",
annote = "No shared memory so that processor must repartition
the relations and intermediate results in a multijoin
query for lost hashkeys (not dynamic optimization);
optimum solutions for closed chain queries,
NP-completeness of star, tree, and general graph
queries and effective heuristics.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; equijoin; hashing; NP-complete problems;
performance; relational data models; spanning trees;
systems; theory",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Distributed
systems. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf C.4}:
Computer Systems Organization, PERFORMANCE OF
SYSTEMS.",
}
@Article{Cesarini:1991:DHM,
author = "F. Cesarini and G. Soda",
title = "A Dynamic Hash Method with Signature",
journal = j-TODS,
volume = "16",
number = "2",
pages = "309--337",
day = "1",
month = jun,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib; UnCover
library database",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-2/p309-cesarini/p309-cesarini.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-2/p309-cesarini/;
http://www.acm.org/pubs/toc/Abstracts/tods/103714.html",
abstract = "We present a dynamic external hash method that allows
retrieval of a record by only one access to mass
storage while maintaining a high load factor. The hash
function is based on generalized spiral storage. Both
primary and overflow records are allocated to the same
file, and file expansion depends on being able to
allocate every overflow chain to one bucket. An in-core
index, built by means of a signature function,
discriminates between primary and overflow records and
assures one access to storage in the case of either
successful or unsuccessful searching. Simulation
results confirm the good expected performance.",
acknowledgement = ack-nhfb,
affiliation = "Dipartimento di Sistemi e Inf., Florence Univ.,
Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; dynamic hashing; external hashing;
generalized spiral storage; performance; signature
functions",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Retrieval models.
{\bf E.2}: Data, DATA STORAGE REPRESENTATIONS,
Hash-table representations. {\bf H.3.3}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval. {\bf E.5}: Data, FILES.",
}
@Article{King:1991:MRB,
author = "Richard P. King and Nagui Halim and H{\'e}ctor
Garc{\'\i}a-Molina and Christos A. Polyzois",
title = "Management of a Remote Backup Copy for Disaster
Recovery",
journal = j-TODS,
volume = "16",
number = "2",
pages = "338--368",
month = jun,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-2/p338-king/p338-king.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-2/p338-king/;
http://www.acm.org/pubs/toc/Abstracts/tods/103715.html",
abstract = "A remote backup database system tracks the state of a
primary system, taking over transaction processing when
disaster hits the primary site. The primary and backup
sites are physically isolated so that failures at one
site are unlikely to propagate to the other. For
correctness, the execution schedule at the backup must
be equivalent to that at the primary. When the primary
and backup sites contain a single processor, it is easy
to achieve this property. However, this is harder to do
when each site contains multiple processors and sites
are connected via multiple communication lines. We
present an efficient transaction processing mechanism
for multiprocessor systems that guarantees this and
other important properties. We also present a database
initialization algorithm that copies the database to a
backup site while transactions are being processed.",
acknowledgement = ack-nhfb,
affiliation = "IBM T.J. Watson Research Center, Yorktown Heights, NY,
USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; database initialization; hot spare; hot
standby; reliability; remote backup",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf D.4.5}: Software, OPERATING SYSTEMS,
Reliability, Backup procedures. {\bf H.2.7}:
Information Systems, DATABASE MANAGEMENT, Database
Administration, Logging and recovery.",
}
@Article{Gogolla:1991:TSV,
author = "Martin Gogolla and Uwe Hohenstein",
title = "Towards a Semantic View of an Extended
Entity-Relationship Model",
journal = j-TODS,
volume = "16",
number = "3",
pages = "369--416",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68Q55 (68P15 68Q60)",
MRnumber = "1 131 140",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
Distributed/gesturing.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p369-gogolla/p369-gogolla.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p369-gogolla/;
http://www.acm.org/pubs/toc/Abstracts/tods/111200.html",
abstract = "Nearly all query languages discussed recently for the
Entity-Relationship (ER) model do not possess a formal
semantics. Languages are often defined by means of
examples only. The reason for this phenomenon is the
essential gap between features of query languages and
theoretical foundations like algebras and calculi.
Known languages offer arithmetic capabilities and allow
for aggregates, but algebras and calculi defined for ER
models do not.\par
This paper introduces an extended ER model
concentrating nearly all concepts of known so-called
semantic data models in a few syntactical constructs.
Moreover, we provide our extended ER model with a
formal mathematical semantics. On this basis a
well-founded calculus is developed taking into account
data operations on arbitrary user-defined data types
and aggregate functions. We pay special attention to
arithmetic operations, as well as multivalued terms
allowing nested queries, in a uniform and consistent
manner. We prove our calculus only allows the
formulation of safe terms and queries yielding a finite
result, and to be (at least) as expressive as the
relational calculi.",
acknowledgement = ack-nhfb,
affiliation = "Tech. Univ. Braunschweig, Germany",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data type; aggregate function; calculus;
design; entity-relationship model; formal semantics;
languages; relational completeness; safeness; semantic
data model; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf F.3.1}: Theory of
Computation, LOGICS AND MEANINGS OF PROGRAMS,
Specifying and Verifying and Reasoning about Programs,
Specification techniques. {\bf F.3.2}: Theory of
Computation, LOGICS AND MEANINGS OF PROGRAMS, Semantics
of Programming Languages. {\bf D.3.1}: Software,
PROGRAMMING LANGUAGES, Formal Definitions and Theory,
Semantics. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Query languages.",
}
@Article{Sciore:1991:UAS,
author = "Edward Sciore",
title = "Using Annotations to Support Multiple Kinds of
Versioning in an Object- Oriented Database System",
journal = j-TODS,
volume = "16",
number = "3",
pages = "417--438",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p417-sciore/p417-sciore.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p417-sciore/;
http://www.acm.org/pubs/toc/Abstracts/tods/111205.html",
abstract = "The concept of {\em annotation\/} from object-oriented
languages is adapted to object-oriented databases. It
is shown how annotations can be used to model
activities such as constraint checking, default values,
and triggers. Annotations also are an appropriate way
to model different versioning concepts. This paper
discusses three kinds of versioning---histories,
revisions, and alternatives---and demonstrates how each
one can be modeled effectively using annotations. The
use of annotations also allows other kinds of
versioning to be defined extensibly, and arbitrary
combinations of versions can be handled easily.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Boston Coll., Chestnut Hill,
MA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "configuration management; design; languages;
object-oriented databases; versions",
subject = "{\bf D.3.2}: Software, PROGRAMMING LANGUAGES, Language
Classifications, Object-oriented languages. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf D.1.5}: Software, PROGRAMMING
TECHNIQUES, Object-oriented Programming.",
}
@Article{Karabeg:1991:SRC,
author = "Dino Karabeg and Victor Vianu",
title = "Simplification Rules and Complete Axiomatization for
Relational Update Transactions",
journal = j-TODS,
volume = "16",
number = "3",
pages = "439--475",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68P20)",
MRnumber = "92g:68033",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p439-karabeg/p439-karabeg.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p439-karabeg/;
http://www.acm.org/pubs/toc/Abstracts/tods/111208.html",
abstract = "Relational update transactions consisting of line
programs of inserts, deletes, and modifications are
studied with respect to equivalence and simplification.
A sound and complete set of axioms for proving
transaction equivalence is exhibited. The axioms yield
a set of simplification rules that can be used to
optimize efficiently a large class of transactions of
practical interest. The simplification rules are
particularly well suited to a dynamic environment where
transactions are presented in an on-line fashion, and
where the time available for optimization may consist
of arbitrarily short and sparse intervals.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., San Diego, La Jolla, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design. {\bf F.2.2}: Theory of Computation, ANALYSIS OF
ALGORITHMS AND PROBLEM COMPLEXITY, Nonnumerical
Algorithms and Problems. {\bf G.2.2}: Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Graph
algorithms.",
}
@Article{Yu:1991:RTR,
author = "Philip S. Yu and Avraham Leff and Yann-Hang Lee",
title = "On Robust Transaction Routing and Load Sharing",
journal = j-TODS,
volume = "16",
number = "3",
pages = "476--512",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p476-yu/p476-yu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p476-yu/;
http://www.acm.org/pubs/toc/Abstracts/tods/111210.html",
abstract = "In this paper we examine the issue of robust
transaction routing in a locally distributed database
environment where transaction characteristics such as
reference locality imply that certain processing
systems can be identified as being more suitable than
others for a given transaction class. A response time
based routing strategy can strike a balance between
indiscriminate sharing of the load and routing based
only on transaction affinity. Since response time
estimates depend on workload and system parameters that
may not be readily available, it is important to
examine the robustness of routing decisions to
information accuracy. We find that a strategy which
strictly tries to minimize the response time of
incoming transactions is sensitive to the accuracy of
certain parameter values. On the other hand, naive
strategies, that simply ignore the parameters in making
routing decisions, have even worse performance. Three
alternative strategies are therefore examined:
threshold, discriminatory, and adaptive. Instead of
just optimizing an incoming transaction's response
time, the first two strategies pursue a strategy that
is somewhat more oriented towards global optimization.
This is achieved by being more restrictive on either
the condition or the candidate for balancing the load.
The third strategy, while trying to minimize the
response time of individual incoming transactions,
employs a feedback process to adaptively adjust future
response time estimates. It monitors the discrepancy
between the actual and estimated response times and
introduces a correction factor based on regression
analysis. All three strategies are shown to be robust
with respect to the accuracy of workload and system
parameters used in the response time estimation.",
acknowledgement = ack-nhfb,
affiliation = "IBM Thomas J. Watson Res. Center, Yorktown Heights,
NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; distributed database; load balancing;
performance analysis; performance, PSYU TODS;
transaction routing",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Routing and layout. {\bf D.4.8}: Software, OPERATING
SYSTEMS, Performance. {\bf D.4.1}: Software, OPERATING
SYSTEMS, Process Management. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Distributed
systems.",
}
@Article{Negri:1991:FSS,
author = "M. Negri and G. Pelagatti and L. Sbattella",
title = "Formal Semantics of {SQL} Queries",
journal = j-TODS,
volume = "16",
number = "3",
pages = "513--534",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (03B50 03B70)",
MRnumber = "92i:68033",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p513-negri/p513-negri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p513-negri/;
http://www.acm.org/pubs/toc/Abstracts/tods/111212.html",
abstract = "The semantics of SQL queries is formally defined by
stating a set of rules that determine a syntax-driven
translation of an SQL query to a formal model. The
target model, called Extended Three Valued Predicate
Calculus (E3VPC), is largely based on a set of
well-known mathematical concepts. The rules which allow
the transformation of a general E3VPC expression to a
Canonical Form, which can be manipulated using
traditional, two-valued predicate calculus are also
given; in this way, problems like equivalence analysis
of SQL queries are completely solved. Finally, the fact
that reasoning about the equivalence of SQL queries
using two-valued predicate calculus, without taking
care of the real SQL semantics can lead to errors is
shown, and the reasons for this are analyzed.",
acknowledgement = ack-nhfb,
affiliation = "Brescia Univ., Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; query equivalence; query semantics;
SQL; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, SQL. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Query
formulation. {\bf F.3.2}: Theory of Computation, LOGICS
AND MEANINGS OF PROGRAMS, Semantics of Programming
Languages.",
}
@Article{Roussopoulos:1991:IAM,
author = "Nicholas Roussopoulos",
title = "An Incremental Access Method for {ViewCache}: Concept,
Algorithms, and Cost Analysis",
journal = j-TODS,
volume = "16",
number = "3",
pages = "535--563",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p535-roussopoulos/p535-roussopoulos.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p535-roussopoulos/;
http://www.acm.org/pubs/toc/Abstracts/tods/111215.html",
abstract = "A {\em ViewCache\/} is a stored collection of pointers
pointing to records of underlying relations needed to
materialize a view. This paper presents an {\em
Incremental Access Method (IAM)\/} that amortizes the
maintenance cost of ViewCaches over a long time period
or indefinitely. Amortization is based on {\em
deferred\/} and other update propagation strategies. A
deferred update strategy allows a ViewCache to remain
outdated until a query needs to selectively or
exhaustively materialize the view. At that point, an
incremental update of the ViewCache is performed. This
paper defines a set of conditions under which
incremental access to the ViewCache is cost effective.
The decision criteria are based on some dynamically
maintained cost parameters, which provide accurate
information but require inexpensive
bookkeeping.\par
The IAM capitalizes on the ViewCache storage
organization for performing the update and the
materialization of the ViewCaches in an interleaved
mode using one-pass algorithms. Compared to the
standard technique for supporting views that requires
reexecution of the definition of the view, the IAM
offers significant performance advantages. We will show
that under favorable conditions, most of which depend
on the size of the incremental update logs between
consecutive accesses of the views, the incremental
access method outperforms query modification.
Performance gains are higher for multilevel ViewCaches
because all the I/O and CPU for handling intermediate
results are avoided.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Maryland Univ., College Park,
MD, USA",
annote = "replicated data management",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; performance; Relational Precomputation TODS,
algorithms; terms",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.2.3}:
Information Systems, DATABASE MANAGEMENT, Languages,
Query languages.",
}
@Article{Mukkamala:1991:NEC,
author = "Ravi Mukkamala and Sushil Jajodia",
title = "A Note on Estimating the Cardinality of the Projection
of a Database Relation",
journal = j-TODS,
volume = "16",
number = "3",
pages = "564--566",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-3/p564-mukkamala/p564-mukkamala.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-3/p564-mukkamala/;
http://www.acm.org/pubs/toc/Abstracts/tods/111218.html",
abstract = "The paper by Ahad et al. [1] derives an analytical
expression to estimate the cardinality of the
projection of a database relation. In this note, we
propose to show that this expression is in error even
when all the parameters are assumed to be constant. We
derive the correct formula for this expression.",
acknowledgement = ack-nhfb,
affiliation = "Old Dominion Univ., Norfolk, VA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "block access estimation; design; performance; query
cost-estimation; relational databases",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design.",
}
@Article{Wolfson:1991:CMP,
author = "O. Wolfson and A. Milo",
title = "Corrigendum: {``The Multicast Policy and its
Relationship to Replicated Data Placement'' [ACM Trans.
Database Systems {\bf 16} (1991), no. 1, 181--205, by
O. Wolfson and A. Milo] (MR 92a:68042)}",
journal = j-TODS,
volume = "16",
number = "3",
pages = "567--567",
month = sep,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68M10)",
MRnumber = "1 131 143",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Wolfson:1991:MPR}.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hernandez:1991:CTM,
author = "H{\'e}ctor J. Hern{\'a}ndez and Edward P. F. Chan",
title = "Constant-Time-Maintainable {BCNF} Database Schemes",
journal = j-TODS,
volume = "16",
number = "4",
pages = "571--599",
month = dec,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-4/p571-hernandez/p571-hernandez.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-4/p571-hernandez/;
http://www.acm.org/pubs/toc/Abstracts/tods/115301.html",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., New Mexico State Univ., Las
Cruces, NM, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; boundedness; constraint enforcement; data
dependencies; design; query processing; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Normal forms. {\bf H.2.1}: Information Systems,
DATABASE MANAGEMENT, Logical Design, Data models. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing.",
}
@Article{Hou:1991:SEA,
author = "Wen-Chi Hou and Gultekin {\"O}zsoyo{\u{g}}lu",
title = "Statistical Estimators for Aggregate Relational
Algebra Queries",
journal = j-TODS,
volume = "16",
number = "4",
pages = "600--654",
month = dec,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-4/p600-hou/p600-hou.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-4/p600-hou/;
http://www.acm.org/pubs/toc/Abstracts/tods/115300.html",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. and Eng. Sci., Case Western Reserve
Univ., Cleveland, OH, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Management; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; management; performance; relational
algebra; sampling; selectivity; simple random sampling;
statistical estimators; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.3}: Mathematics of
Computing, PROBABILITY AND STATISTICS, Statistical
computing. {\bf G.2.m}: Mathematics of Computing,
DISCRETE MATHEMATICS, Miscellaneous. {\bf H.2.3}:
Information Systems, DATABASE MANAGEMENT, Languages,
Query languages.",
}
@Article{Negri:1991:DJN,
author = "M. Negri and G. Pelagatti",
title = "Distributive Join: a New Algorithm for Joining
Relations",
journal = j-TODS,
volume = "16",
number = "4",
pages = "655--669",
month = dec,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-4/p655-negri/p655-negri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-4/p655-negri/;
http://www.acm.org/pubs/toc/Abstracts/tods/115299.html",
abstract = "This paper describes a new algorithm for performing
joins in the absence of access paths. This algorithm is
shown to perform better than the merging scan
algorithm, which can be considered the paradigm of join
algorithms. Finally this algorithm is compared with
another recent sub-sort-merge algorithm.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano, Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Algorithm, Performance, buffer, hashing, join, merging
scan, nested scan, sort, algorithms; buffer; design;
experimentation; hashing; join; merging scan; nested
scan; performance; sort",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Sorting and searching. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods.",
}
@Article{Moerkotte:1991:RCC,
author = "Guido Moerkotte and Peter C. Lockemann",
title = "Reactive Consistency Control in Deductive Databases",
journal = j-TODS,
volume = "16",
number = "4",
pages = "670--702",
month = dec,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-4/p670-moerkotte/p670-moerkotte.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-4/p670-moerkotte/;
http://www.acm.org/pubs/toc/Abstracts/tods/115298.html",
acknowledgement = ack-nhfb,
affiliation = "Inst. fuer Programmstrukturen und Datenorganisation,
Karlsruhe Univ., Germany",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance;
Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; experimentation; performance;
theory",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Data description
languages (DDL). {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing. {\bf
I.2.3}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Deduction and Theorem Proving,
Deduction.",
}
@Article{Carey:1991:CDT,
author = "Michael J. Carey and Miron Livny",
title = "Conflict Detection Tradeoffs for Replicated Data",
journal = j-TODS,
volume = "16",
number = "4",
pages = "703--746",
month = dec,
year = "1991",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1991-16-4/p703-carey/p703-carey.pdf;
http://www.acm.org/pubs/citations/journals/tods/1991-16-4/p703-carey/;
http://www.acm.org/pubs/toc/Abstracts/tods/115289.html",
acknowledgement = ack-nhfb,
affiliation = "Wisconsin Univ., Madison, WI, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Measurement;
Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; concurrency control; experimentation;
measurement; performance; replicated data",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Concurrency. {\bf D.4.8}:
Software, OPERATING SYSTEMS, Performance, Modeling and
prediction. {\bf D.4.8}: Software, OPERATING SYSTEMS,
Performance, Simulation. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases.",
}
@Article{Cattell:1992:OOB,
author = "R. G. G. Cattell and J. Skeen",
title = "Object Operations Benchmark",
journal = j-TODS,
volume = "17",
number = "1",
pages = "1--31",
month = mar,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-1/p1-cattell/p1-cattell.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-1/p1-cattell/;
http://www.acm.org/pubs/toc/Abstracts/tods/128766.html",
abstract = "Performance is a major issue in the acceptance of
object-oriented and relational database systems aimed
at engineering applications such as computer-aided
software engineering (CASE) and computer-aided design
(CAD). Because traditional database systems benchmarks
are inappropriate to measure performance for operations
on engineering objects, we designed a new benchmark
Object Operations version 1 (OO1) to focus on important
characteristics of these applications. OO1 is descended
from an earlier benchmark for simple database
operations and is based on several years experience
with that benchmark. In this paper we describe the OO1
benchmark and results we obtained running it on a
variety of database systems. We provide a careful
specification of the benchmark, show how it can be
implemented on database systems, and present evidence
that more than an order of magnitude difference in
performance can result from a DBMS implementation quite
different from current products; minimizing overhead
per database call, offloading database server
functionality to workstations, taking advantage of
large main memories, and using link-based methods.",
acknowledgement = ack-nhfb,
affiliation = "Sun Microsyst., Mountain View, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Languages;
Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; CAD; CASE; client-server architecture;
design; engineering database benchmark;
experimentation; hypermodel; languages; measurement;
object operations benchmark; object-oriented DBMS's;
performance; relation of DBMS's; workstations",
subject = "{\bf K.6.2}: Computing Milieux, MANAGEMENT OF
COMPUTING AND INFORMATION SYSTEMS, Installation
Management, Benchmarks. {\bf D.1.5}: Software,
PROGRAMMING TECHNIQUES, Object-oriented Programming.
{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
description languages (DDL). {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML). {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Database
(persistent) programming languages. {\bf H.2.8}:
Information Systems, DATABASE MANAGEMENT, Database
applications. {\bf K.6.2}: Computing Milieux,
MANAGEMENT OF COMPUTING AND INFORMATION SYSTEMS,
Installation Management, Performance and usage
measurement.",
}
@Article{Weddell:1992:RAF,
author = "Grant E. Weddell",
title = "Reasoning About Functional Dependencies Generalized
for Semantic Data Models",
journal = j-TODS,
volume = "17",
number = "1",
pages = "32--64",
month = mar,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68Q55)",
MRnumber = "1 161 053",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-1/p32-weddell/p32-weddell.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-1/p32-weddell/;
http://www.acm.org/pubs/toc/Abstracts/tods/128767.html",
abstract = "We propose a more general form of functional
dependency for semantic data models that derives from
their common feature in which the separate notions of
{\em domain\/} and {\em relation\/} in the relational
model are combined into a single notion of {\em class}.
This usually results in a richer terminological
component for their query languages, whereby terms may
navigate through any number of properties, including
none. We prove the richer expressiveness of this more
general functional dependency, and exhibit a sound and
complete set of inference axioms. Although the general
problem of decidability of their logical implication
remains open at this time, we present decision
procedures for cases in which the dependencies included
in a schema correspond to keys, or in which the schema
itself is acyclic. The theory is then extended to
include a form of conjunctive query. Of particular
significance is that the query becomes an additional
source of functional dependency. Finally, we outline
several applications of the theory to various problems
in physical design and in query optimization. The
applications derive from an ability to predict when a
query can have at most one solution.",
acknowledgement = ack-nhfb,
affiliation = "Waterloo Univ., Ont., Canada",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; constraint theory; functional
dependencies; query optimization; semantic data models;
theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Query processing.",
}
@Article{Paredaens:1992:CNA,
author = "Jan Paredaens and Dirk {Van Gucht}",
title = "Converting Nested Algebra Expressions into Flat
Algebra Expressions",
journal = j-TODS,
volume = "17",
number = "1",
pages = "65--93",
month = mar,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P10",
MRnumber = "93c:68018",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-1/p65-paredaens/p65-paredaens.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-1/p65-paredaens/;
http://www.acm.org/pubs/toc/Abstracts/tods/128768.html",
abstract = "Nested relations generalize ordinary flat relations by
allowing tuple values to be either atomic or set
valued. The nested algebra is a generalization of the
flat relational algebra to manipulate nested relations.
In this paper we study the expressive power of the
nested algebra relative to its operation on flat
relational databases. We show that the flat relational
algebra is rich enough to extract the same ``flat
information'' from a flat database as the nested
algebra does. Theoretically, this result implies that
recursive queries such as the transitive closure of a
binary relation cannot be expressed in the nested
algebra. Practically, this result is relevant to (flat)
relational query optimization.",
acknowledgement = ack-nhfb,
affiliation = "Antwerp Univ., Belgium",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algebraic query transformation; algorithms; languages;
nested algebra; nested calculus; nested relations;
relational databases; theory, van Gucht relational data
model TODS",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.3.3}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval, Query formulation. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models.",
}
@Article{Mohan:1992:ATR,
author = "C. Mohan and Don Haderle and Bruce Lindsay and Hamid
Pirahesh and Peter Schwarz",
title = "{ARIES}: a Transaction Recovery Method Supporting
Fine-Granularity Locking and Partial Rollbacks Using
Write-Ahead Logging",
journal = j-TODS,
volume = "17",
number = "1",
pages = "94--162",
month = mar,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: IBM Almaden Res. Ctr, Res. R.
No. RJ-6649, Jan. 1989, 45 pp.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-1/p94-mohan/p94-mohan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-1/p94-mohan/;
http://www.acm.org/pubs/toc/Abstracts/tods/128770.html",
abstract = "DB2$^{\rm TM}$, IMS, and Tandem$^{\rm TM}$ systems.
ARIES is applicable not only to database management
systems but also to persistent object-oriented
languages, recoverable file systems and
transaction-based operating systems. ARIES has been
implemented, to varying degrees, in IBM's OS/2$^{\rm
TM}$ Extended Edition Database Manager, DB2,
Workstation Data Save Facility/VM, Starburst and
QuickSilver, and in the University of Wisconsin's
EXODUS and Gamma database machine.",
acknowledgement = ack-nhfb,
affiliation = "IBM Almaden Res. Center, San Jose, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; buffer management; design; latching;
locking; performance; reliability; space management;
write-ahead logging",
subject = "{\bf H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration, Logging and recovery. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Recovery and restart. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Concurrency.
{\bf E.5}: Data, FILES, Backup/recovery. {\bf D.4.5}:
Software, OPERATING SYSTEMS, Reliability, Backup
procedures.",
}
@Article{Badrinath:1992:SBC,
author = "B. R. Badrinath and Krithi Ramamritham",
title = "Semantics-Based Concurrency Control: Beyond
Commutativity",
journal = j-TODS,
volume = "17",
number = "1",
pages = "163--199",
month = mar,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "93b:68019",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-1/p163-badrinath/p163-badrinath.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-1/p163-badrinath/;
http://www.acm.org/pubs/toc/Abstracts/tods/128771.html",
abstract = "The concurrency of transactions executing on atomic
data types can be enhanced through the use of semantic
information about operations defined on these types.
Hitherto, commutativity of operations has been
exploited to provide enhanced concurrency while
avoiding cascading aborts. We have identified a
property known as {\em recoverability\/} which can be
used to decrease the delay involved in processing
noncommuting operations while still avoiding cascading
aborts. When an invoked operation is {\em
recoverable\/} with respect to an uncommitted
operation, the invoked operation can be executed by
forcing a commit dependency between the invoked
operation and the uncommitted operation; the
transaction invoking the operation will not have to
wait for the uncommitted operation to abort or commit.
Further, this commit dependency only affects the order
in which the operations should commit, if both commit;
if either operation aborts, the other can still commit
thus avoiding cascading aborts. To ensure the
serializability of transactions, we force the
recoverability relationship between transactions to be
acyclic. Simulation studies, based on the model
presented by Agrawal et al. [1], indicate that using
recoverability, the turnaround time of transactions can
be reduced. Further, our studies show enhancement in
concurrency even when {\em resource constraints\/} are
taken into consideration. The magnitude of enhancement
is dependent on the resource contention; the lower the
resource contention, the higher the improvement.",
acknowledgement = ack-nhfb,
affiliation = "Rutgers Univ., New Brunswick, NJ, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; concurrency control; performance; semantic
information",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.
{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Recovery and restart. {\bf D.2.1}:
Software, SOFTWARE ENGINEERING,
Requirements/Specifications.",
}
@Article{Wang:1992:CTM,
author = "Ke Wang and Marc H. Graham",
title = "Constant-Time Maintainability: a Generalization of
Independence",
journal = j-TODS,
volume = "17",
number = "2",
pages = "201--246",
month = jun,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-2/p201-wang/p201-wang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-2/p201-wang/;
http://www.acm.org/pubs/toc/Abstracts/tods/128904.html",
abstract = "The {\em maintenance problem\/} of a database scheme
is the following decision problem: Given a consistent
database state $ \rho $ and a new tuple $u$ over some
relation scheme of $ \rho $, is the modified state $
\rho \cup u $ still consistent? A database scheme is
said to be {\em constant-time-maintainable(ctm)\/} if
there exists an algorithm that solves its maintenance
problem by making a fixed number of tuple retrievals.
We present a practically useful algorithm, called the
{\em canonical maintenance algorithm}, that solves the
maintenance problem of all ctm database schemes within
a ``not too large'' bound. A number of interesting
properties are shown for ctm database schemes, among
them that non-ctm database schemes are not maintainable
in less than a linear time in the state size. A test
method is given when only cover embedded functional
dependencies (fds) appear. When the given dependencies
consist of fds and the join dependency (jd) $ \bowtie
{\bf R} $ of the database scheme, testing whether a
database scheme is ctm is reduced to the case of cover
embedded fds. When dependency-preserving database
schemes with only equality-generating dependencies
(egds) are considered, it is shown that every ctm
database scheme has a set of dependencies that is
equivalent to a set of embedded fds, and thus, our test
method for the case of embedded fds can be applied. In
particular, this includes the important case of
lossless database schemes with only egds.",
acknowledgement = ack-nhfb,
affiliation = "Chongqing Univ., Sichuan, China",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; chase; constraint enforcement; design;
functional dependency; independent database schemes;
join dependency; lossless join; relational database;
representative instance; tableau; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.0}:
Information Systems, DATABASE MANAGEMENT, General,
Security, integrity, and protection. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Normal forms. {\bf F.4.1}: Theory of
Computation, MATHEMATICAL LOGIC AND FORMAL LANGUAGES,
Mathematical Logic, Mechanical theorem proving.",
}
@Article{Becker:1992:RBO,
author = "Ludger Becker and Ralf Hartmut G{\"u}ting",
title = "Rule-Based Optimization and Query Processing in an
Extensible Geometric Database System",
journal = j-TODS,
volume = "17",
number = "2",
pages = "247--303",
month = jun,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-2/p247-becker/p247-becker.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-2/p247-becker/;
http://www.acm.org/pubs/toc/Abstracts/tods/128905.html",
abstract = "Gral is an extensible database system, based on the
formal concept of a many-sorted relational algebra.
Many-sorted algebra is used to define any application's
query language, its query execution language, and its
optimization rules. In this paper we describe Gral's
optimization component. It provides (1) a sophisticated
rule language --- rules are transformations of abstract
algebra expressions, (2) a general optimization
framework under which more specific optimization
algorithms can be implemented, and (3) several control
mechanisms for the application of rules. An
optimization algorithm can be specified as a series of
steps. Each step is defined by its own collection of
rules together with a selected control strategy.
\par
The general facilities are illustrated by the complete
design of an example optimizer --- in the form of a
rule file --- for a small nonstandard query language
and an associated execution language. The query
language includes selection, join, ordering, embedding
derived values, aggregate functions, and several
geometric operations. The example shows in particular
how the special processing techniques of a geometric
database systems, such as spatial join methods and
geometric index structures, can be integrated into
query processing and optimization of a relational
database system. A similar, though larger, optimizer is
fully functional within the geometric database system
implemented as a Gral prototype.",
acknowledgement = ack-nhfb,
affiliation = "Univ. Gesamthochschule Siegen, Germany",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; extensibility; geometric query processing;
languages, Guting Gral TODS; many-sorted algebra;
optimization; relational algebra; rule-based
optimization",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Query languages. {\bf F.2.0}:
Theory of Computation, ANALYSIS OF ALGORITHMS AND
PROBLEM COMPLEXITY, General. {\bf E.2}: Data, DATA
STORAGE REPRESENTATIONS, Hash-table representations.
{\bf I.3.5}: Computing Methodologies, COMPUTER
GRAPHICS, Computational Geometry and Object Modeling,
Geometric algorithms, languages, and systems.",
}
@Article{Franaszek:1992:CCH,
author = "Peter A. Franaszek and John T. Robinson and Alexander
Thomasian",
title = "Concurrency Control for High Contention Environments",
journal = j-TODS,
volume = "17",
number = "2",
pages = "304--345",
month = jun,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-2/p304-franaszek/p304-franaszek.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-2/p304-franaszek/;
http://www.acm.org/pubs/toc/Abstracts/tods/128906.html",
abstract = "Future transaction processing systems may have
substantially higher levels of concurrency due to
reasons which include: (1) increasing disparity between
processor speeds and data access latencies, (2) large
numbers of processors, and (3) distributed databases.
Another influence is the trend towards longer or more
complex transactions. A possible consequence is
substantially more data contention, which could limit
total achievable throughput. In particular, it is known
that the usual locking method of concurrency control is
not well suited to environments where data contention
is a significant factor.\par
Here we consider a number of concurrency control
concepts and transaction scheduling techniques that are
applicable to high contention environments, and that do
not rely on database semantics to reduce contention.
These include {\em access invariance\/} and its
application to prefetching of data, approximations to
{\em essential blocking\/} such as {\em wait depth
limited\/} scheduling, and {\em phase dependent\/}
control. The performance of various concurrency control
methods based on these concepts are studied using
detailed simulation models. The results indicate that
the new techniques can offer substantial benefits for
systems with high levels of data contention.",
acknowledgement = ack-nhfb,
affiliation = "Thomas J. Watson Res. Center, Yorktown Heights, NY,
USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; concurrency control; design; performance;
transaction processing",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf D.4.8}: Software,
OPERATING SYSTEMS, Performance. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design.",
}
@Article{Leng:1992:OWA,
author = "Chun-Wu Roger Leng and Dik Lun Lee",
title = "Optimal Weight Assignment for Signature Generation",
journal = j-TODS,
volume = "17",
number = "2",
pages = "346--373",
month = jun,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/bibdb.bib; Database/Graefe.bib;
Database/Wiederhold.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-2/p346-leng/p346-leng.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-2/p346-leng/;
http://www.acm.org/pubs/toc/Abstracts/tods/128907.html",
abstract = "Previous work on superimposed coding has been
characterized by two aspects. First, it is generally
assumed that signatures are generated from {\em
logical\/} text blocks of the same size; that is, each
block contains the same number of unique terms after
stopword and duplicate removal. We call this approach
the fixed-size block (FSB) method, since each text
block has the same size, as measured by the number of
unique terms contained in it. Second, with only a few
exceptions [6,7,8,9,17], most previous work has assumed
that each term in the text contributes the same number
of ones to the signature (i.e., the weight of the term
signatures is fixed). The main objective of this paper
is to derive an optimal weight assignment that assigns
weights to document terms according to their occurrence
and query frequencies in order to minimize the
false-drop probability. The optimal scheme can account
for both uniform and nonuniform occurrence and query
frequencies, and the signature generation method is
still based on hashing rather than on table lookup.
Furthermore, a new way of generating signatures, the
fixed-weight block (FWB) method, is introduced. FWB
controls the weight of {\em every\/} signature to a
constant, whereas in FSB, only the {\em expected\/}
signature weight is constant. We have shown that FWB
has a lower false-drop probability than that of the FSB
method, but its storage overhead is slightly higher.
Other advantages of FWB are that the optimal weight
assignment can be obtained analytically without making
unrealistic assumptions and that the formula for
computing the term signature weights is simple and
efficient.",
acknowledgement = ack-nhfb,
affiliation = "Ohio State Univ., Columbus, OH, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access method; coding methods; design; document
retrieval; information retrieval; optimization;
performance; signature file; superimposed coding; text
retrieval",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf H.2.2}: Information Systems,
DATABASE MANAGEMENT, Physical Design, Access methods.
{\bf H.3.6}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Library Automation. {\bf I.7.1}:
Computing Methodologies, TEXT PROCESSING, Text
Editing.",
}
@Article{Tansel:1992:MRH,
author = "Abdullah U. Tansel and Lucy Garnett",
title = "On {M. A. Roth, H. F. Korth and A. Silberschatz:
``Extended Algebra and Calculus for Nested Relational
Databases'' [ACM Trans. Database Systems {\bf 13}
(1988), no. 4, 389--417]}",
journal = j-TODS,
volume = "17",
number = "2",
pages = "374--383",
month = jun,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "1 167 047",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Roth:1988:EAC}.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-2/p374-tansel/p374-tansel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-2/p374-tansel/;
http://www.acm.org/pubs/toc/Abstracts/tods/128908.html",
abstract = "We discuss the issues encountered in the extended
algebra and calculus languages for nested relations
defined by Roth, Korth, and Silberschatz.[4]. Their
equivalence proof between algebra and calculus fails
because of the keying problems and the use of extended
set operations. Extended set operations also have
unintended side effects. Furthermore, their calculus
seems to allow the generation of power sets, thus
making it more powerful than their algebra.",
acknowledgement = ack-nhfb,
affiliation = "Bilkent Univ., Ankara, Turkey",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "equivalence of algebra and calculus; languages; nested
relations; relational algebra; relational calculus;
theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf F.4.1}: Theory of
Computation, MATHEMATICAL LOGIC AND FORMAL LANGUAGES,
Mathematical Logic. {\bf H.2.1}: Information Systems,
DATABASE MANAGEMENT, Logical Design, Normal forms. {\bf
H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Data manipulation languages (DML).",
}
@Article{Bergamaschi:1992:TRC,
author = "Sonia Bergamaschi and Claudio Sartori",
title = "On Taxonomic Reasoning in Conceptual Design",
journal = j-TODS,
volume = "17",
number = "3",
pages = "385--422",
month = sep,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-3/p385-bergamaschi/p385-bergamaschi.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-3/p385-bergamaschi/;
http://www.acm.org/pubs/toc/Abstracts/tods/132272.html",
abstract = "Taxonomic reasoning is a typical task performed by
many AI knowledge representation systems. In this
paper, the effectiveness of taxonomic reasoning
techniques as an active support to knowledge
acquisition and conceptual schema design is shown. The
idea developed is that by extending conceptual models
with {\em defined concepts\/} and giving them rigorous
logic semantics, it is possible to infer {\em isa\/}
relationships between concepts on the basis of their
descriptions. From a theoretical point of view, this
approach makes it possible to give a formal definition
for {\em consistency\/} and {\em minimality\/} of a
conceptual schema. From a pragmatic point of view it is
possible to develop an active environment that allows
automatic {\em classification\/} of a new concept in
the right position of a given taxonomy, ensuring the
consistency and minimality of a conceptual schema. A
formalism that includes the data semantics of models
giving prominence to type constructors (E/R, TAXIS,
GALILEO) and algorithms for taxonomic inferences are
presented: their soundness, completeness, and
tractability properties are proved. Finally, an
extended formalism and taxonomic inference algorithms
for models giving prominence to attributes (FDM, IFO)
are given.",
acknowledgement = ack-nhfb,
affiliation = "Bologna Univ., Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; schema consistency; schema
minimality; semantic models; taxonomic reasoning;
theory; verification",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf I.2.4}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Knowledge
Representation Formalisms and Methods, Representation
languages. {\bf I.2.4}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Knowledge Representation
Formalisms and Methods, Frames and scripts.",
}
@Article{Markowitz:1992:REE,
author = "Victor M. Markowitz and Arie Shoshani",
title = "Representing Extended Entity-Relationship Structures
in Relational Databases: a Modular Approach",
journal = j-TODS,
volume = "17",
number = "3",
pages = "423--464",
month = sep,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-3/p423-markowitz/p423-markowitz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-3/p423-markowitz/;
http://www.acm.org/pubs/toc/Abstracts/tods/132273.html",
abstract = "A common approach to database design is to describe
the structures and constraints of the database
application in terms of a semantic data model, and then
represent the resulting schema using the data model of
a commercial database management system. Often, in
practice, {\em Extended Entity-Relationship\/} (EER)
schemas are translated into equivalent relational
schemas. This translation involves different aspects:
representing the EER schema using relational
constructs, assigning names to relational attributes,
normalization, and merging relations. Considering these
aspects together, as is usually done in the design
methodologies proposed in the literature, is confusing
and leads to inaccurate results. We propose to treat
separately these aspects and split the translation into
four stages (modules) corresponding to the four aspects
mentioned above. We define criteria for both evaluating
the correctness of and characterizing the relationship
between alternative relational representations of EER
schemas.",
acknowledgement = ack-nhfb,
affiliation = "Lawrence Berkeley Lab., CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; database design; design; extended
entity-relationship model; relational data model;
schema translation; semantic data model",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Normal
forms. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Data description languages
(DDL).",
}
@Article{Date:1992:SCG,
author = "C. J. Date and Ronald Fagin",
title = "Simple Conditions for Guaranteeing Higher Normal Forms
in Relational Databases",
journal = j-TODS,
volume = "17",
number = "3",
pages = "465--476",
month = sep,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-3/p465-date/p465-date.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-3/p465-date/;
http://www.acm.org/pubs/toc/Abstracts/tods/132274.html",
abstract = "A key is {\em simple\/} if it consists of a single
attribute. It is shown that if a relation schema is in
third normal form and every key is simple, then it is
in projection-join normal form (sometimes called fifth
normal form), the ultimate normal form with respect to
projections and joins. Furthermore, it is shown that if
a relation schema is in Boyce-Codd normal form and {\em
some\/} key is simple, then it is in fourth normal form
(but not necessarily projection-join normal form).
These results give the database designer simple
sufficient conditions, defined in terms of functional
dependencies alone, that guarantee that the schema
being designed is automatically in higher normal
forms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "5NF; BCNF; Boyce-Codd normal form; database design;
design; fifth normal form; fourth normal form 4NF;
functional dependency; join dependency; multivalued
dependency; normalization; PJ/NF; projection-join
normal form; relational database; simple key; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms.",
}
@Article{Hsu:1992:PEC,
author = "Meichun Hsu and Bin Zhang",
title = "Performance Evaluation of Cautious Waiting",
journal = j-TODS,
volume = "17",
number = "3",
pages = "477--512",
month = sep,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-3/p477-hsu/p477-hsu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-3/p477-hsu/;
http://www.acm.org/pubs/toc/Abstracts/tods/132275.html",
abstract = "We study a deadlock-free locking-based concurrency
control algorithm, called {\em cautious waiting}, which
allows for a limited form of waiting. The algorithm is
very simple to implement. We present an analytical
solution to its performance evaluation based on the
mean-value approach proposed by Tay et al. [18]. From
the modeling point of view, we are able to do away with
a major assumption used in Tay's previous work, and
therefore capture more accurately both the restart and
the blocking rates in the system. We show that to solve
for this model we only need to solve for the root of a
polynomial. The analytical tools developed enable us to
see that the cautious waiting algorithm manages to
achieve a {\em delicate\/} balance between restart and
blocking, and therefore is superior (i.e., has higher
throughput to {\em both\/} the no-waiting (i.e.,
immediate restart) and the general waiting algorithms)
under a wide range of system parameters. The study
substantiates the argument that balancing restart and
blocking is important in locking systems.",
acknowledgement = ack-nhfb,
affiliation = "Digital Equipment Corp., Mountain View, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Management; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; cautious waiting; concurrency control;
management; performance, Concurrency control locking
TODS",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf D.4.1}: Software, OPERATING
SYSTEMS, Process Management, Concurrency.",
}
@Article{Abbott:1992:SRT,
author = "Robert K. Abbott and H{\'e}ctor Garc{\'\i}a-Molina",
title = "Scheduling Real-Time Transactions: a Performance
Evaluation",
journal = j-TODS,
volume = "17",
number = "3",
pages = "513--560",
month = sep,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-3/p513-abbott/p513-abbott.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-3/p513-abbott/;
http://www.acm.org/pubs/toc/Abstracts/tods/132276.html",
acknowledgement = ack-nhfb,
affiliation = "Digital Equipment Corp., Littleton, MA, USA",
annote = "real-time",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; deadlines; locking protocols; performance;
real-time systems",
subject = "{\bf D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Scheduling. {\bf D.4.1}: Software,
OPERATING SYSTEMS, Process Management, Concurrency.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.",
}
@Article{Siegel:1992:MAR,
author = "Michael Siegel and Edward Sciore and Sharon Salveter",
title = "A Method for Automatic Rule Derivation to Support
Semantic Query Optimization",
journal = j-TODS,
volume = "17",
number = "4",
pages = "563--600",
month = dec,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (68T05)",
MRnumber = "1 197 198",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-4/p563-siegel/p563-siegel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-4/p563-siegel/;
http://www.acm.org/pubs/toc/Abstracts/tods/146932.html",
abstract = "The use of inference rules to support intelligent data
processing is an increasingly important tool in many
areas of computer science. In database systems, rules
are used in semantic query optimization as a method for
reducing query processing costs. The savings is
dependent on the ability of experts to supply a set of
useful rules and the ability of the optimizer to
quickly find the appropriate transformations generated
by these rules. Unfortunately, the most useful rules
are not always those that would or could be specified
by an expert. This paper describes the architecture of
a system having two interrelated components: a combined
conventional/semantic query optimizer, and an automatic
rule deriver.\par
Our automatic rule derivation method uses intermediate
results from the optimization process to direct the
search for learning new rules. Unlike a system
employing only user-specified rules, a system with an
automatic capability can derive rules that may be true
only in the current state of the database and can
modify the rule set to reflect changes in the database
and its usage pattern.\par
This system has been implemented as an extension of the
EXODUS conventional query optimizer generator. We
describe the implementation, and show how semantic
query optimization is an extension of conventional
optimization in this context.",
acknowledgement = ack-nhfb,
affiliation = "Boston Univ., MA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "integrity constraint; languages; learning;
performance; transformation heuristic",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf I.2.6}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Learning,
Knowledge acquisition.",
}
@Article{Kamel:1992:IDC,
author = "Nabil Kamel and Roger King",
title = "Intelligent Database Caching Through the Use of Page
Answers and Page Traces",
journal = j-TODS,
volume = "17",
number = "4",
pages = "601--646",
month = dec,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "1 197 199",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-4/p601-kamel/p601-kamel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-4/p601-kamel/;
http://www.acm.org/pubs/toc/Abstracts/tods/146933.html",
abstract = "In this paper a new method to improve the utilization
of main memory systems is presented. The new method is
based on prestoring in main memory a number of query
answers, each evaluated out of a single memory page. To
this end, the ideas of page-answers and page-traces are
formally described and their properties analyzed. The
query model used here allows for selection, projection,
join, recursive queries as well as arbitrary
combinations. We also show how to apply the approach
under update traffic. This concept is especially useful
in managing the main memories of an important class of
applications. This class includes the evaluation of
triggers and alerters, performance improvement of
rule-based systems, integrity constraint checking, and
materialized views. These applications are
characterized by the existence at compile time of a
predetermined set of queries, by a slow but persistent
update traffic, and by their need to repetitively
reevaluate the query set. The new approach represents a
new type of intelligent database caching, which
contrasts with traditional caching primarily in that
the cache elements are derived data and as a
consequence, they overlap arbitrarily and do not have a
fixed length. The contents of the main memory cache are
selected based on the data distribution within the
database, the set of fixed queries to preprocess, and
the paging characteristics. Page-answers and
page-traces are used as the smallest indivisible units
in the cache. An efficient heuristic to select a near
optimal set of page-answers and page-traces to populate
the main memory has been developed, implemented, and
tested. Finally, quantitative measurements of
performance benefits are reported.",
acknowledgement = ack-nhfb,
affiliation = "Florida Univ., Gainesville, FL, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; artificial intelligence; databases;
design; page access; performance",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval. {\bf
H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Access methods. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Query processing. {\bf H.3.1}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Content Analysis and
Indexing, Indexing methods. {\bf H.3.2}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Storage, Record classification. {\bf I.1.3}: Computing
Methodologies, ALGEBRAIC MANIPULATION, Languages and
Systems, Evaluation strategies. {\bf I.2.8}: Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Problem
Solving, Control Methods, and Search, Plan execution,
formation, generation.",
}
@Article{Maiocchi:1992:ADT,
author = "Roberto Maiocchi and Barbara Pernici and Federico
Barbic",
title = "Automatic Deduction of Temporal Information",
journal = j-TODS,
volume = "17",
number = "4",
pages = "647--688",
month = dec,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20 (03B70 68T27)",
MRnumber = "93h:68038",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-4/p647-maiocchi/p647-maiocchi.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-4/p647-maiocchi/;
http://www.acm.org/pubs/toc/Abstracts/tods/146934.html",
abstract = "In many computer-based applications, temporal
information has to be stored, retrieved, and related to
other temporal information. Several time models have
been proposed to manage temporal knowledge in the
fields of conceptual modeling, database systems, and
artificial intelligence.\par
In this paper we present TSOS, a system for reasoning
about time that can be integrated as a time expert in
environments designed for broader problem-solving
domains. The main intended goal of TSOS is to allow a
user to infer further information on the temporal data
stored in the database through a set of deduction rules
handling various aspects of time. For this purpose,
TSOS provides the capability of answering queries about
the temporal specifications it has in its temporal
database.\par
Distinctive time-modeling features of TSOS are the
introduction of {\em temporal modalities}, i.e., the
possibility of specifying if a piece of information is
always true within a time interval, or if it is only
sometimes true, and the capability of answering about
the possibility and the necessity of the validity of
some information at a given time, the association of
temporal knowledge both to {\em instances of data\/}
and to {\em types of data}, and the development of a
{\em time calculus\/} for reasoning on temporal data.
Another relevant feature of TSOS is the capability to
reason about temporal data specified at different time
granularities.",
acknowledgement = ack-nhfb,
affiliation = "Politecnico di Milano, Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; events; languages; meta-level temporal
assertions; propositions; temporal database; temporal
modalities; theory; time calculus",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf I.2.3}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem Proving,
Deduction.",
}
@Article{Agrawal:1992:GTQ,
author = "D. Agrawal and A. {El Abbadi}",
title = "The Generalized Tree Quorum Protocol: An Efficient
Approach for Managing Replicated Data",
journal = j-TODS,
volume = "17",
number = "4",
pages = "689--717",
month = dec,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68M10",
MRnumber = "1 197 201",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-4/p689-agrawal/p689-agrawal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-4/p689-agrawal/;
http://www.acm.org/pubs/toc/Abstracts/tods/146935.html",
abstract = "In this paper, we present a low-cost fault-tolerant
protocol for managing replicated data. We impose a
logical tree structure on the set of copies of an
object and develop a protocol that uses the information
available in the logical structure to reduce the
communication requirements for read and write
operations. The tree quorum protocol is a
generalization of the static voting protocol with two
degrees of freedom for choosing quorums. In general,
this results in significantly lower communication costs
for comparable data availability. The protocol exhibits
the property of graceful degradation, i.e.,
communication costs for executing operations are
minimal in a failure-free environment but may increase
as failures occur. This approach in designing
distributed systems is desirable since it provides
fault-tolerance without imposing unnecessary costs on
the failure-free mode of operations.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Santa Barbara, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Economics; Experimentation; Measurement;
Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; economics; experimentation; measurement;
performance",
subject = "{\bf C.2.2}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Network Protocols.
{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design. {\bf
G.2.2}: Mathematics of Computing, DISCRETE MATHEMATICS,
Graph Theory, Network problems. {\bf G.2.2}:
Mathematics of Computing, DISCRETE MATHEMATICS, Graph
Theory, Trees.",
}
@Article{Atzeni:1992:URD,
author = "Paolo Atzeni and Riccardo Torlone",
title = "Updating Relational Databases Through Weak Instance
Interfaces",
journal = j-TODS,
volume = "17",
number = "4",
pages = "718--745",
month = dec,
year = "1992",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P20",
MRnumber = "93h:68035",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1992-17-4/p718-atzeni/p718-atzeni.pdf;
http://www.acm.org/pubs/citations/journals/tods/1992-17-4/p718-atzeni/;
http://www.acm.org/pubs/toc/Abstracts/tods/146936.html",
abstract = "The problem of updating databases through interfaces
based on the weak instance model is studied, thus
extending previous proposals that considered them only
from the query point of view. Insertions and deletions
of tuples are considered.\par
As a preliminary tool, a lattice on states is defined,
based on the information content of the various
states.\par
Potential results of an insertion are states that
contain at least the information in the original state
and that in the new tuple. Sometimes there is no
potential result, and in the other cases there may be
many of them. We argue that the insertion is
deterministic if the state that contains the
information common to all the potential results (the
greatest lower bound, in the lattice framework) is a
potential result itself. Effective characterizations
for the various cases exist.\par
A symmetric approach is followed for deletions, with
fewer cases, since there are always potential results;
determinism is characterized as a consequence.",
acknowledgement = ack-nhfb,
affiliation = "Roma Univ., Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Schema
and subschema. {\bf H.2.m}: Information Systems,
DATABASE MANAGEMENT, Miscellaneous. {\bf H.5.2}:
Information Systems, INFORMATION INTERFACES AND
PRESENTATION, User Interfaces, Theory and methods.",
}
@Article{Ishikawa:1993:MLI,
author = "Hiroshi Ishikawa and Fumio Suzuki and Fumihiko
Kozakura and Akifumi Makinouchi and Mika Miyagishima
and Yoshio Izumida and Masaaki Aoshima and Yasuo
Yamane",
title = "The Model, Language, and Implementation of an
Object-Oriented Multimedia Knowledge Base Management
System",
journal = j-TODS,
volume = "18",
number = "1",
pages = "1--50",
month = mar,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-1/p1-ishikawa/p1-ishikawa.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-1/p1-ishikawa/;
http://www.acm.org/pubs/toc/Abstracts/tods/151285.html",
abstract = "New applications such as CAD, AI, and hypermedia
require direct representation and flexible use of
complex objects, behavioral knowledge, and multimedia
data. To this end, we have devised a knowledge base
management system called Jasmine. An object-oriented
approach in a programming language also seems promising
for use in Jasmine. Jasmine extends the current
object-oriented approach and provides the following
features. Our object model is based on functional data
models and well-established set theory. Attributes or
functions composing objects can represent both
structural and behavioral knowledge. The object model
can represent incomplete and generic knowledge. The
model can support the basic storage and operations of
multimedia data. The facets of attributes can flexibly
represent constraints and triggers. The object
manipulation language can support associative access of
objects. The structural and behavioral knowledge can be
uniformly treated to allow the user to specify complex
object operations in a compact manner. The user-defined
and system-defined attributes can be uniformly
specified to ease user customization of the language.
The classes and instances can be uniformly accessed.
Incomplete knowledge can be flexibly accessed. The
system has a layered architecture. Objects are stored
in nested relations provided by extensive DBMS as a
sublayer. User query of objects is compiled into
relational operations such as select and join, which
can be efficiently processed using hashing. The
behavioral knowledge is compiled into predicate and
manipulation function interfaces that can directly
access tuples in a buffer.",
acknowledgement = ack-nhfb,
affiliation = "Fujitsu Labs., Ltd., Kawasaki, Japan",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages",
subject = "{\bf I.2.1}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Applications and Expert Systems. {\bf
I.2.4}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Knowledge Representation Formalisms and
Methods, Representations (procedural and rule-based).
{\bf H.4.2}: Information Systems, INFORMATION SYSTEMS
APPLICATIONS, Types of Systems. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Query languages. {\bf
H.5.1}: Information Systems, INFORMATION INTERFACES AND
PRESENTATION, Multimedia Information Systems.",
}
@Article{Johnson:1993:PCB,
author = "Theodore Johnson and Dennis Shasha",
title = "The Performance of Current {B-Tree} Algorithms",
journal = j-TODS,
volume = "18",
number = "1",
pages = "51--101",
month = mar,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "``Current'' in the title should be ``Concurrent''.",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-1/p51-johnson/p51-johnson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-1/p51-johnson/;
http://www.acm.org/pubs/toc/Abstracts/tods/151286.html",
acknowledgement = ack-nhfb,
affiliation = "Florida Univ., Gainesville, FL, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Measurement;
Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "B-trees; concurrent B-trees; concurrent data
structures; experimentation; measurement; performance;
performance of concurrent algorithms; TOC Concurrency
control simulations TODS, algorithms",
subject = "{\bf H.3.3}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Search and Retrieval,
Retrieval models. {\bf H.3.3}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Search
and Retrieval, Search process. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design. {\bf F.2.2}: Theory of
Computation, ANALYSIS OF ALGORITHMS AND PROBLEM
COMPLEXITY, Nonnumerical Algorithms and Problems,
Sorting and searching. {\bf I.6.6}: Computing
Methodologies, SIMULATION AND MODELING, Simulation
Output Analysis.",
}
@Article{Kumar:1993:CAT,
author = "Akhil Kumar and Arie Segev",
title = "Cost and Availability Tradeoffs in Replicated Data
Concurrency Control",
journal = j-TODS,
volume = "18",
number = "1",
pages = "102--131",
month = mar,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-1/p102-kumar/p102-kumar.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-1/p102-kumar/;
http://www.acm.org/pubs/toc/Abstracts/tods/151287.html",
acknowledgement = ack-nhfb,
affiliation = "Cornell Univ., Ithaca, NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; availability; performance; replicated
database",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases.",
}
@Article{Abdel-Ghaffar:1993:ODA,
author = "Khaled A. S. Abdel-Ghaffar and Amr {El Abbadi}",
title = "Optimal Disk Allocation for Partial Match Queries",
journal = j-TODS,
volume = "18",
number = "1",
pages = "132--156",
month = mar,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-1/p132-abdel-ghaffar/p132-abdel-ghaffar.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-1/p132-abdel-ghaffar/;
http://www.acm.org/pubs/toc/Abstracts/tods/151288.html",
abstract = "The problem of disk allocation addresses the issue of
how to distribute a file on several disks in order to
maximize concurrent disk accesses in response to a
partial match query. In this paper a coding-theoretic
analysis of this problem is presented, and both
necessary and sufficient conditions for the existence
of strictly optimal allocation methods are provided.
Based on a class of optimal codes, known as maximum
distance separable codes, strictly optimal allocation
methods are constructed. Using the necessary conditions
proved, we argue that the standard definition of strict
optimality is too strong and cannot be attained, in
general. Hence, we reconsider the definition of
optimality. Instead of basing it on an abstract
definition that may not be attainable, we propose a new
definition based on the best possible allocation
method. Using coding theory, allocation methods that
are optimal according to our proposed criterion are
developed.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Davis, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Abbadi TODS, algorithms; Cartesian product files;
coding theory; design; multiple disk systems; partial
match queries; theory",
subject = "{\bf H.3.2}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Information Storage, File organization.
{\bf D.4.3}: Software, OPERATING SYSTEMS, File Systems
Management, File organization. {\bf E.5}: Data, FILES,
Organization/structure. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.1.1}: Information Systems, MODELS AND
PRINCIPLES, Systems and Information Theory, Information
theory. {\bf E.4}: Data, CODING AND INFORMATION
THEORY.",
}
@Article{Matsliach:1993:PAF,
author = "Gabriel Matsliach",
title = "Performance Analysis of File Organizations that Use
Multibucket Data Leaves with Partial Expansions",
journal = j-TODS,
volume = "18",
number = "1",
pages = "157--180",
month = mar,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-1/p157-matsliach/p157-matsliach.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-1/p157-matsliach/;
http://www.acm.org/pubs/toc/Abstracts/tods/151289.html",
abstract = "We present an exact performance analysis, under random
insertions, of file organizations that use multibucket
data leaves and perform partial expansions before
splitting. We evaluate the expected disk space
utilization of the file and show how the expected
search and insert costs can be estimated. The
analytical results are confirmed by simulations. The
analysis can be used to investigate both the dynamic
and the asymptotic behaviors.",
acknowledgement = ack-nhfb,
affiliation = "Technion-Israel Inst. of Technol., Haifa, Israel",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bounded disorder files; multibucket data leaves;
partial expansion; performance; performance analysis;
search structures; theory; verification",
subject = "{\bf E.5}: Data, FILES, Organization/structure. {\bf
E.1}: Data, DATA STRUCTURES, Trees. {\bf H.3.2}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Storage, File organization. {\bf H.3.1}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Content Analysis and Indexing. {\bf H.3.3}: Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Information
Search and Retrieval.",
}
@Article{Chomicki:1993:FRI,
author = "Jan Chomicki and Tomasz Imieli{\'n}ski",
title = "Finite Representation of Infinite Query Answers",
journal = j-TODS,
volume = "18",
number = "2",
pages = "181--223",
month = jun,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-2/p181-chomicki/p181-chomicki.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-2/p181-chomicki/;
http://www.acm.org/pubs/toc/Abstracts/tods/151635.html",
abstract = "We define here a formal notion of finite
representation of infinite query answers in logic
programs. We apply this notion to Datalog$_{\rm nS}$
programs may be infinite and consequently queries may
have infinite answers.\par
We present a method to finitely represent infinite
least Herbrand models of Datalog$_{\rm nS}$ program
(and its underlying computational engine) can be
forgotten. Given a query to be evaluated, it is easy to
obtain from the relational specification finitely many
answer substitutions that represent infinitely many
answer substitutions to the query. The method involved
is a combination of a simple, unificationless,
computational mechanism (graph traversal, congruence
closure, or term rewriting) and standard relational
query evaluation methods. Second, a relational
specification is {\em effectively computable\/} and its
computation is no harder, in the sense of the
complexity class, than answering yes-no
queries.\par
Our method is applicable to every range-restricted
Datalog$_{\rm nS}$ program. We also show that for some
very simple non-Datalog$_{\rm nS}$ logic programs,
finite representations of query answers do not exist.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. and Inf. Sci., Kansas State Univ.,
Manhattan, KS, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; theory",
subject = "{\bf F.2.2}: Theory of Computation, ANALYSIS OF
ALGORITHMS AND PROBLEM COMPLEXITY, Nonnumerical
Algorithms and Problems. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Datalog. {\bf
I.2.3}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Deduction and Theorem Proving, Deduction.
{\bf F.4.1}: Theory of Computation, MATHEMATICAL LOGIC
AND FORMAL LANGUAGES, Mathematical Logic.",
}
@Article{Hou:1993:PTC,
author = "Wen-Chi Hou and Gultekin {\"O}zsoyo{\u{g}}lu",
title = "Processing Time-Constrained Aggregate Queries in
{CASE-DB}",
journal = j-TODS,
volume = "18",
number = "2",
pages = "224--261",
month = jun,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-2/p224-hou/p224-hou.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-2/p224-hou/;
http://www.acm.org/pubs/toc/Abstracts/tods/151636.html",
abstract = "In this paper, we present an algorithm to strictly
control the time to process an estimator for an
aggregate relational query. The algorithm implemented
in a prototype database management system, called
CASE-DB, iteratively samples from input relations, and
evaluates the associated estimator until the time quota
expires.\par
In order to estimate the time cost of a query, CASE-DB
uses adaptive time cost formulas. The formulas are
adaptive in that the parameters of the formulas can be
adjusted at runtime to better fit the characteristics
of a query. To control the use of time quota, CASE-DB
adopts the one-at-a-time-interval time control strategy
to make a tradeoff between the risks of overspending
and the overhead, finally, experimental evaluation of
the methodology is presented.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Southern Illinois Univ.,
Carbondale, IL, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; estimation; performance;
relational algebra; risk of overspending; sampling;
selectivity; theory; time constraints",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.3}: Mathematics of
Computing, PROBABILITY AND STATISTICS, Statistical
computing. {\bf H.2.8}: Information Systems, DATABASE
MANAGEMENT, Database applications. {\bf J.7}: Computer
Applications, COMPUTERS IN OTHER SYSTEMS, Real time.",
}
@Article{Drenick:1993:SQO,
author = "P. E. Drenick and E. J. Smith",
title = "Stochastic Query Optimization in Distributed
Databases",
journal = j-TODS,
volume = "18",
number = "2",
pages = "262--288",
month = jun,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-2/p262-drenick/p262-drenick.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-2/p262-drenick/;
http://www.acm.org/pubs/toc/Abstracts/tods/151637.html",
abstract = "Many algorithms have been devised for minimizing the
costs associated with obtaining the answer to a single,
isolated query in a distributed database system.
However, if more than one query may be processed by the
system at the same time and if the arrival times of the
queries are unknown, the determination of optimal
query-processing strategies becomes a stochastic
optimization problem. In order to cope with such
problems, a theoretical state-transition model is
presented that treats the system as one operating under
a stochastic load. Query-processing strategies may then
be distributed over the processors of a network as
probability distributions, in a manner which
accommodates many queries over time.\par
It is then shown that the model leads to the
determination of optimal query-processing strategies as
the solution of mathematical programming problems, and
analytical results for several examples are presented.
Furthermore, a divide-and-conquer approach is
introduced for decomposing stochastic query
optimization problems into distinct subproblems for
processing queries sequentially and in parallel.",
acknowledgement = ack-nhfb,
affiliation = "Polytech. Univ., Farmingdale, NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; distributed query processing; performance;
state-transition model; stochastic query optimization;
theory",
subject = "{\bf G.1.6}: Mathematics of Computing, NUMERICAL
ANALYSIS, Optimization, Linear programming. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Retrieval
models. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Distributed systems. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Query processing. {\bf C.2.4}: Computer Systems
Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases.",
}
@Article{Rothermel:1993:OCP,
author = "Kurt Rothermel and Stefan Pappe",
title = "Open Commit Protocols Tolerating Commission Failures",
journal = j-TODS,
volume = "18",
number = "2",
pages = "289--332",
month = jun,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-2/p289-rothermel/p289-rothermel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-2/p289-rothermel/;
http://www.acm.org/pubs/toc/Abstracts/tods/151638.html",
abstract = "To ensure atomicity of transactions in distributed
systems so-called 2-phase commit (2PC) protocols have
been proposed. The basic assumption of these protocols
is that the processing nodes involved in transactions
are ``sane,'' i.e., they only fail with omission
failures, and nodes eventually recover from failures.
Unfortunately, this assumption is not realistic for
so-called Open Distributed Systems (ODSs), in which
nodes may have totally different reliability
characteristics. In ODSs, nodes can be classified into
trusted nodes (e.g., a banking server) and nontrusted
nodes (e.g., a home PC requesting a remote banking
service). While trusted nodes are assumed to be sane,
nontrusted nodes may fail permanently and even cause
commission failures to occur.\par
In this paper, we propose a family of 2PC protocols
that tolerate any number of omission failures at
trusted nodes and any number of commission and omission
failures at nontrusted nodes. The proposed protocols
ensure that (at least) the trusted nodes participating
in a transaction {\em eventually\/} terminate the
transaction in a {\em consistent\/} manner. Unlike
Byzantine commit protocols, our protocols do {\em
not\/} incorporate mechanisms for achieving Byzantine
agreement, which has advantages in terms of complexity:
Our protocols have the same or only a slightly higher
message complexity than traditional 2PC protocols.",
acknowledgement = ack-nhfb,
affiliation = "Inst. of Parallel and Distributed High Performance
Syst., Stuttgart Univ., Germany",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; commit protocols; open systems;
performance; reliability",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Network operating systems. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf C.4}: Computer Systems Organization,
PERFORMANCE OF SYSTEMS, Reliability, availability, and
serviceability.",
}
@Article{Rahm:1993:EPE,
author = "Erhard Rahm",
title = "Empirical Performance Evaluation of Concurrency and
Coherency Control Protocols for Database Sharing
Systems",
journal = j-TODS,
volume = "18",
number = "2",
pages = "333--377",
month = jun,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; Database/Wiederhold.bib;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-2/p333-rahm/p333-rahm.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-2/p333-rahm/;
http://www.acm.org/pubs/toc/Abstracts/tods/151639.html",
abstract = "Database Sharing (DB-sharing) refers to a general
approach for building a distributed high performance
transaction system. The nodes of a DB-sharing system
are locally coupled via a high-speed interconnect and
share a common database at the disk level. This is also
known as a ``shared disk'' approach. We compare
database sharing with the database partitioning (shared
nothing) approach and discuss the functional DBMS
components that require new and coordinated solutions
for DB-sharing. The performance of DB-sharing systems
critically depends on the protocols used for
concurrency and coherency control. The frequency of
communication required for these functions has to be
kept as low as possible in order to achieve high
transaction rates and short response times. A
trace-driven simulation system for DB-sharing complexes
has been developed that allows a realistic performance
comparison of four different concurrency and coherency
control protocols. We consider two locking and two
optimistic schemes which operate either under central
or distributed control. For coherency control, we
investigate so-called on-request and broadcast
invalidation schemes, and employ buffer-to-buffer
communication to exchange modified pages directly
between different nodes. The performance impact of
random routing versus affinity-based load distribution
and different communication costs is also examined. In
addition, we analyze potential performance bottlenecks
created by hot spot pages.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Kaiserslautern Univ., Germany",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; coherency control; concurrency control;
database partitioning; database sharing; design;
performance; performance analysis; shared disk; shared
nothing; theory; trace-driven simulation",
subject = "{\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf C.4}: Computer Systems Organization,
PERFORMANCE OF SYSTEMS. {\bf D.4.8}: Software,
OPERATING SYSTEMS, Performance, Simulation. {\bf
D.4.1}: Software, OPERATING SYSTEMS, Process
Management, Concurrency.",
}
@Article{Kuper:1993:LDM,
author = "Gabriel M. Kuper and Moshe Y. Vardi",
title = "The Logical Data Model",
journal = j-TODS,
volume = "18",
number = "3",
pages = "379--413",
month = sep,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "96c:68035",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-3/p379-kuper/p379-kuper.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-3/p379-kuper/;
http://www.acm.org/pubs/toc/Abstracts/tods/155274.html",
abstract = "We propose an object-oriented data model that
generalizes the relational, hierarchical, and network
models. A database scheme in this model is a directed
graph, whose leaves represent data and whose internal
nodes represent connections among the data. Instances
are constructed from objects, which have separate names
and values. We define a logic for the model, and
describe a nonprocedural query language that is based
on the logic. We also describe an algebraic query
language and show that it is equivalent to the logical
language.",
acknowledgement = ack-nhfb,
affiliation = "IBM Thomas J. Watson Res. Center, Yorktown Heights,
NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Algebra; database schema; design; languages; logic;
relational database; theory; tuple calculus",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design, Schema and subschema.",
}
@Article{Levene:1993:SNE,
author = "Mark Levene and George Loizou",
title = "Semantics for Null Extended Nested Relations",
journal = j-TODS,
volume = "18",
number = "3",
pages = "414--459",
month = sep,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-3/p414-levene/p414-levene.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-3/p414-levene/;
http://www.acm.org/pubs/toc/Abstracts/tods/155275.html",
abstract = "The nested relational model extends the flat
relational model by relaxing the first normal form
assumption in order to allow the modeling of complex
objects. Much of the previous work on the nested
relational model has concentrated on defining the data
structures and query language for the model. The work
done on integrity constraints in nested relations has
mainly focused on characterizing subclasses of nested
relations and defining normal forms for nested
relations with certain desirable properties.\par
In this paper we define the semantics of nested
relations, which may contain null values, in terms of
integrity constraints, called {\em null extended data
dependencies}, which extend functional dependencies and
join dependencies encountered in flat relational
database theory. We formalize incomplete information in
nested relations by allowing only one unmarked {\em
generic null value}, whose semantics we do not further
specify. The motivation for the choice of a generic
null is our desire to investigate only fundamental
semantics which are common to all unmarked null types.
This lead us to define a preorder on nested relations,
which allows us to measure the relative information
content of nested relations. We also define a
procedure, called the {\em extended chase procedure},
for testing satisfaction of null extended data
dependencies and for making inferences by using these
null extended data dependencies. The extended chase
procedure is shown to generalize the classical chase
procedure, which is of major importance in flat
relational database theory. As a consequence of our
approach we are able to capture the novel notion of
losslessness in nested relations, called herein {\em
null extended lossless decomposition}. Finally, we show
that the semantics of nested relations are a natural
extension of the semantics of flat relations.",
acknowledgement = ack-nhfb,
affiliation = "Univ. Coll., London, UK",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; extended chase; languages; nested
relations; null extended algebra; null extended data
dependencies; nulls; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design, Normal forms.",
}
@Article{Agrawal:1993:COS,
author = "Divyakant Agrawal and Amr {El Abbadi} and Ambuj K.
Singh",
title = "Consistency and Orderability: Semantics-Based
Correctness Criteria for Databases",
journal = j-TODS,
volume = "18",
number = "3",
pages = "460--486",
month = sep,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-3/p460-agrawal/p460-agrawal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-3/p460-agrawal/;
http://www.acm.org/pubs/toc/Abstracts/tods/155276.html",
abstract = "The semantics of objects and transactions in database
systems are investigated. User-defined predicates
called {\em consistency assertions\/} are used to
specify user programs. Three new correctness criteria
are proposed. The first correctness criterion {\em
consistency\/} is based solely on the users'
specifications and admit nonserializable executions
that are acceptable to the users. Integrity constraints
of the database are maintained through consistency
assertions. The second correctness criterion {\em
orderability\/} is a generalization of view
serializability and represents a weak notion of
equivalence to a serial schedule. Finally, the third
correctness criterion {\em strong order-ability\/} is
introduced as a generalization of conflict
serializability. Unlike consistency, the notions of
orderability allow users to operate an isolation as
maintenance of the integrity constraint now becomes the
responsibility of the database system.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Santa Barbara, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Abbadi TODS, theory; concurrency control;
object-oriented databases; semantics; serializability
theory; verification",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Concurrency.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf D.2.4}: Software,
SOFTWARE ENGINEERING, Program Verification, Correctness
proofs. {\bf F.3.1}: Theory of Computation, LOGICS AND
MEANINGS OF PROGRAMS, Specifying and Verifying and
Reasoning about Programs, Assertions.",
}
@Article{Sagiv:1993:SQT,
author = "Yehoshua Sagiv and Oded Shmueli",
title = "Solving Queries by Tree Projections",
journal = j-TODS,
volume = "18",
number = "3",
pages = "487--511",
month = sep,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15",
MRnumber = "96c:68038",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-3/p487-sagiv/p487-sagiv.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-3/p487-sagiv/;
http://www.acm.org/pubs/toc/Abstracts/tods/155277.html",
abstract = "Suppose a database schema {\bf D} is extended to {\bf
D'} by adding new relation schemas, and states for {\bf
D} are extended to states for {\bf D'} by applying
joins and projections to existing relations. It is
shown that certain desirable properties that {\bf D'}
has with respect to {\bf D}. These properties amount to
the ability to compute efficiently the join of all
relations in a state for {\bf D} from an extension of
this state over {\bf D'}. The equivalence is proved for
unrestricted (i.e., both finite and infinite)
databases. If {\bf D'} is obtained from {\bf D} by
adding a set of new relation schemas that form a tree
schema, then the equivalence also holds for finite
databases. In this case there is also a polynomial time
algorithm for testing the existence of a tree
projection of {\bf D'} with respect to {\bf D}.",
acknowledgement = ack-nhfb,
affiliation = "Hebrew Univ., Jerusalem, Israel",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "acyclicity; algorithms; chase; database schema;
design; hypergraph; inclusion dependency; join;
monotone join expression; projection; qual graph;
relational database; semijoin; semijoin reduction;
tableau; theory; tree projection; tree schema",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Query processing.",
}
@Article{Ioannidis:1993:TCA,
author = "Yannis Ioannidis and Raghu Ramakrishnan and Linda
Winger",
title = "Transitive Closure Algorithms Based on Graph
Traversal",
journal = j-TODS,
volume = "18",
number = "3",
pages = "512--576",
month = sep,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-3/p512-ioannidis/p512-ioannidis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-3/p512-ioannidis/;
http://www.acm.org/pubs/toc/Abstracts/tods/155273.html",
abstract = "Several graph-based algorithms have been proposed in
the literature to compute the transitive closure of a
directed graph. We develop two new algorithms
(Basic\_TC and Gobal\_DFTC) and compare the performance
of their implementations in a disk-based environment
with a well-known graph-based algorithm proposed by
Schmitz. Our algorithms use depth-first search to
traverse a graph and a technique called {\em marking\/}
to avoid processing some of the arcs in the graph. They
compute the closure by processing nodes in reverse
topological order, building descendent sets by adding
the descendent sets of children. While the details of
these algorithms differ considerably, one important
difference among them is the time at which descendent
set additions are performed. Basic\_TC, results in
superior performance. The first reason is that early
additions result in larger descendent set sizes on the
average over the duration of the execution, thereby
causing more I/O; very often this turns out to more
than offset the gains of not having to fetch certain
sets again to add them. The second reason is that
information collected in the first pass can be used to
apply several optimizations in the second pass. To the
extent possible, we also adapt these algorithms to
perform path computations. Again, our performance
comparison confirms the trends seen in reachability
queries. Taken in conjunction with another performance
study our results indicate that all graph-based
algorithms significantly outperform other types of
algorithms such as Seminaive and Warren.",
acknowledgement = ack-nhfb,
affiliation = "Wisconsin Univ., Madison, WI, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; depth-first search; node reachability;
path computations; performance; transitive closure",
subject = "{\bf D.3.4}: Software, PROGRAMMING LANGUAGES,
Processors. {\bf F.2.2}: Theory of Computation,
ANALYSIS OF ALGORITHMS AND PROBLEM COMPLEXITY,
Nonnumerical Algorithms and Problems, Computations on
discrete structures. {\bf D.3.3}: Software, PROGRAMMING
LANGUAGES, Language Constructs and Features, Recursion.
{\bf D.4.2}: Software, OPERATING SYSTEMS, Storage
Management, Main memory. {\bf D.4.2}: Software,
OPERATING SYSTEMS, Storage Management, Secondary
storage. {\bf D.4.2}: Software, OPERATING SYSTEMS,
Storage Management, Swapping. {\bf E.1}: Data, DATA
STRUCTURES, Graphs. {\bf E.1}: Data, DATA STRUCTURES,
Trees. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing.",
}
@Article{Thomasian:1993:TPL,
author = "Alexander Thomasian",
title = "Two-Phase Locking Performance and Its Thrashing
Behavior",
journal = j-TODS,
volume = "18",
number = "4",
pages = "579--625",
month = dec,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-4/p579-thomasian/p579-thomasian.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-4/p579-thomasian/;
http://www.acm.org/pubs/toc/Abstracts/tods/169720.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; data contention; load control;
performance; theory; thrashing; two-phase locking",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Deadlock avoidance. {\bf D.4.8}:
Software, OPERATING SYSTEMS, Performance, Modeling and
prediction. {\bf D.4.8}: Software, OPERATING SYSTEMS,
Performance, Operational analysis. {\bf D.4.8}:
Software, OPERATING SYSTEMS, Performance, Simulation.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.",
}
@Article{Qian:1993:DSD,
author = "Xiaolei Qian",
title = "The Deductive Synthesis of Database Transactions",
journal = j-TODS,
volume = "18",
number = "4",
pages = "626--677",
month = dec,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-4/p626-qian/p626-qian.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-4/p626-qian/;
http://www.acm.org/pubs/toc/Abstracts/tods/169716.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database programming; deductive tableau; design;
integrity constraints; search control; theory;
transaction logic; transaction synthesis;
verification",
subject = "{\bf I.2.2}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Automatic Programming, Program synthesis.
{\bf D.1.2}: Software, PROGRAMMING TECHNIQUES,
Automatic Programming. {\bf F.3.1}: Theory of
Computation, LOGICS AND MEANINGS OF PROGRAMS,
Specifying and Verifying and Reasoning about Programs,
Logics of programs. {\bf H.2.0}: Information Systems,
DATABASE MANAGEMENT, General, Security, integrity, and
protection. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Database (persistent)
programming languages. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing.",
}
@Article{Malvestuto:1993:USA,
author = "Francesco M. Malvestuto",
title = "A Universal-Scheme Approach to Statistical Databases
Containing Homogeneous Summary Tables",
journal = j-TODS,
volume = "18",
number = "4",
pages = "678--708",
month = dec,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-4/p678-malvestuto/p678-malvestuto.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-4/p678-malvestuto/;
http://www.acm.org/pubs/toc/Abstracts/tods/169712.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bipartite graph; category relation; design;
query-answering system; statistical database; summary
table; theory; universal classification scheme",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.1.3}: Mathematics of
Computing, NUMERICAL ANALYSIS, Numerical Linear
Algebra, Linear systems (direct and iterative methods).
{\bf G.1.6}: Mathematics of Computing, NUMERICAL
ANALYSIS, Optimization, Integer programming. {\bf
G.1.6}: Mathematics of Computing, NUMERICAL ANALYSIS,
Optimization, Linear programming. {\bf G.2.2}:
Mathematics of Computing, DISCRETE MATHEMATICS, Graph
Theory, Graph algorithms. {\bf G.2.2}: Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Network
problems. {\bf G.2.2}: Mathematics of Computing,
DISCRETE MATHEMATICS, Graph Theory, Trees. {\bf H.2.1}:
Information Systems, DATABASE MANAGEMENT, Logical
Design, Data models. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Query languages.",
}
@Article{Ioannidis:1993:OHL,
author = "Yannis E. Ioannidis and Stavros Christodoulakis",
title = "Optimal Histograms for Limiting Worst-Case Error
Propagation in the Size of Join Results",
journal = j-TODS,
volume = "18",
number = "4",
pages = "709--748",
month = dec,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1993-18-4/p709-ioannidis/p709-ioannidis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1993-18-4/p709-ioannidis/;
http://www.acm.org/pubs/toc/Abstracts/tods/169708.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "histograms; join size estimation; performance; query
optimization; theory; vector majorization",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.1.0}: Mathematics of
Computing, NUMERICAL ANALYSIS, General, Error analysis.
{\bf H.1.1}: Information Systems, MODELS AND
PRINCIPLES, Systems and Information Theory.",
}
@Article{Anonymous:1993:AI,
author = "Anonymous",
title = "1993 Author Index",
journal = j-TODS,
volume = "18",
number = "4",
pages = "749--750",
month = dec,
year = "1993",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 12:59:37 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kim:1994:CS,
author = "Won Kim",
title = "Charter and Scope",
journal = j-TODS,
volume = "19",
number = "1",
pages = "1--??",
month = mar,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Dec 6 18:01:56 MST 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Olivier:1994:TSO,
author = "Martin S. Olivier and Sebastiaan H. {von Solms}",
title = "A Taxonomy for Secure Object-Oriented Databases",
journal = j-TODS,
volume = "19",
number = "1",
pages = "3--46",
month = mar,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib;
http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-1/p3-olivier/p3-olivier.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-1/p3-olivier/;
http://www.acm.org/pubs/toc/Abstracts/tods/174640.html",
abstract = "This paper proposes a taxonomy for secure
object-oriented databases in order to clarify the
issues in modeling and implementing such databases. It
also indicates some implications of the various choices
one may make when designing such a database.\par
Most secure database models have been designed for
relational databases. The object-oriented database
model is more complex than the relational model. For
these reasons, models for secure object-oriented
databases are more complex than their relational
counterparts. Furthermore, since views of the
object-oriented model differ, each security model has
to make some assumptions about the object-oriented
model used for its particular database.\par
A number of models for secure object-oriented databases
have been proposed. These models differ in many
respects, because they focus on different aspects of
the security problem, or because they make different
assumptions about what constitutes a secure database or
because they make different assumptions about the
object-oriented model.\par
The taxonomy proposed in this paper may be used to
compare the various models: Models that focus on
specific issues may be positioned in the broader
context with the aid of the taxonomy. The taxonomy also
identifies the major aspects where security models may
differ and indicates some alternatives available to the
system designer for each such design choice. We show
some implications of using specific
alternatives.\par
Since differences between models for secure
object-oriented databases are often subtle, a formal
notation is necessary for a proper comparison. Such a
formal notation also facilitates the formal derivation
of restrictions that apply under specific conditions.
The formal approach also gives a clear indication about
the assumptions made by us---given as axioms---and the
consequences of those assumptions (and of design
choices made by the model designer)---given as
theorems.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; formal security models; information security;
multilevel secure databases; object-orientation;
security",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
D.4.6}: Software, OPERATING SYSTEMS, Security and
Protection. {\bf K.6.5}: Computing Milieux, MANAGEMENT
OF COMPUTING AND INFORMATION SYSTEMS, Security and
Protection. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design.",
}
@Article{Tendick:1994:MRP,
author = "Patrick Tendick and Norman Matloff",
title = "A Modified Random Perturbation Method for Database
Security",
journal = j-TODS,
volume = "19",
number = "1",
pages = "47--63",
month = mar,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-1/p47-tendick/p47-tendick.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-1/p47-tendick/;
http://www.acm.org/pubs/toc/Abstracts/tods/174641.html",
abstract = "The random data perturbation (RDP) method of
preserving the privacy of individual records in a
statistical database is discussed. In particular, it is
shown that if confidential attributes are allowed as
query-defining variables, severe biases may result in
responses to queries. It is also shown that even if
query definition through confidential variables is {\em
not\/} allowed, biases can still occur in responses to
queries such as those involving proportions or counts.
In either case, serious distortions may occur in user
statistical analyses. A modified version of RDP is
presented, in the form of a query adjustment procedure
and specialized perturbation structure which will
produce unbiased results.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bias; correlation; design; noise addition; random
perturbation method; security",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
D.4.6}: Software, OPERATING SYSTEMS, Security and
Protection, Access controls. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing.",
}
@Article{Clifford:1994:CHR,
author = "James Clifford and Albert Croker and Alexander
Tuzhilin",
title = "On Completeness of Historical Relational Query
Languages",
journal = j-TODS,
volume = "19",
number = "1",
pages = "64--116",
month = mar,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-1/p64-clifford/p64-clifford.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-1/p64-clifford/;
http://www.acm.org/pubs/toc/Abstracts/tods/174642.html",
abstract = "Numerous proposals for extending the relational data
model to incorporate the temporal dimension of data
have appeared in the past several years. These
proposals have differed considerably in the way that
the temporal dimension has been incorporated both into
the {\em structure\/} of the extended relations of
these temporal models and into the extended relational
{\em algebra\/} or {\em calculus\/} that they define.
Because of these differences, it has been difficult to
compare the proposed models and to make judgments as to
which of them might in some sense be equivalent or even
{\em better}. In this paper we define {\em temporally
grouped\/} and {\em temporally ungrouped\/} historical
data models and propose two notions of {\em historical
relational completeness}, analogous to Codd's notion of
relational completeness, one for each type of model. We
show that the temporally ungrouped models are less
expressive than the grouped models, but demonstrate a
technique for extending the ungrouped models with a
grouping mechanism to capture the additional semantic
power of temporal grouping. For the ungrouped models,
we define three different languages, a logic with
explicit reference to time, a temporal logic, and a
temporal algebra, and motivate our choice for the first
of these as the basis for completeness for these
models. For the grouped models, we define a many-sorted
logic with variables over ordinary values, historical
values, and times. Finally, we demonstrate the
equivalence of this grouped calculus and the ungrouped
calculus extended with a grouping mechanism. We believe
the classification of historical data models into
grouped and ungrouped models provides a useful
framework for the comparison of models in the
literature, and furthermore, the exposition of
equivalent languages for each type provides reasonable
standards for common, and minimal, notions of
historical relational completeness.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "completeness; historical databases; languages; query
languages; relational model; temporal databases;
temporal grouping; temporal logic; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models.",
}
@Article{Salem:1994:AL,
author = "Kenneth Salem and H{\'e}ctor Garc{\'\i}a-Molina and
Jeannie Shands",
title = "Altruistic Locking",
journal = j-TODS,
volume = "19",
number = "1",
pages = "117--165",
month = mar,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "Database/Graefe.bib; http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-1/p117-salem/p117-salem.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-1/p117-salem/;
http://www.acm.org/pubs/toc/Abstracts/tods/174639.html",
abstract = "Long-lived transactions (LLTs) hold on to database
resources for relatively long periods of time,
significantly delaying the completion of shorter and
more common transactions. To alleviate this problem we
propose an extension to two-phase locking, called
altruistic locking, whereby LLTs can release their
locks early. Transactions that access this released
data are said to run in the wake of the LLT and must
follow special locking rules. Like two-phase locking,
altruistic locking is easy to implement and guarantees
serializability.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; atomicity; locking; performance;
scheduling; serializability; theory, concurrency
control ``wake'' of a single transaction TODS",
subject = "{\bf H.2.2}: Information Systems, DATABASE MANAGEMENT,
Physical Design, Deadlock avoidance. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Transaction processing.",
}
@Article{Rosenthal:1994:TTR,
author = "Arnon Rosenthal and David Reiner",
title = "Tools and Transformations --- Rigorous and Otherwise
--- for Practical Database Design",
journal = j-TODS,
volume = "19",
number = "2",
pages = "167--211",
month = jun,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-2/p167-rosenthal/p167-rosenthal.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-2/p167-rosenthal/;
http://www.acm.org/pubs/toc/Abstracts/tods/176568.html",
abstract = "We describe the tools and theory of a comprehensive
system for database design, and show how they work
together to support multiple conceptual and logical
design processes. The Database Design and Evaluation
Workbench (DDEW) system uses a rigorous,
information-content-preserving approach to schema
transformation, but combines it with heuristics, guess
work, and user interactions. The main contribution lies
in illustrating how theory was adapted to a practical
system, and how the consistency and power of a design
system can be increased by use of theory.\par
First, we explain why a design system needs multiple
data models, and how implementation over a unified
underlying model reduces redundancy and inconsistency.
Second, we present a core set of small but fundamental
algorithms that rearrange a schema without changing its
information content. From these reusable components, we
easily built larger tools and transformations that were
still formally justified. Third, we describe heuristic
tools that attempt to improve a schema, often by adding
missing information. In these tools, unreliable
techniques such as normalization and relationship
inference are bolstered by system-guided user
interactions to remove errors. We present a rigorous
criterion for identifying unnecessary relationships,
and discuss an interactive view integrator. Last, we
examine the relevance of database theory to building
these practically motivated tools and contrast the
paradigms of system builders with those of
theoreticians.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "applications of database theory; computer-aided
software engineering; data model translation; database
design; database equivalence; design; design
heuristics; entity-relationship model; heuristics;
normalization; theory; view integration",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf D.2.2}:
Software, SOFTWARE ENGINEERING, Tools and Techniques,
Programmer workbench. {\bf D.2.2}: Software, SOFTWARE
ENGINEERING, Tools and Techniques, Software libraries.
{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Normal
forms.",
}
@Article{Bright:1994:ARS,
author = "M. W. Bright and A. R. Hurson and S. Pakzad",
title = "Automated Resolution of Semantic Heterogeneity in
Multidatabases",
journal = j-TODS,
volume = "19",
number = "2",
pages = "212--253",
month = jun,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-2/p212-bright/p212-bright.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-2/p212-bright/;
http://www.acm.org/pubs/toc/Abstracts/tods/176569.html",
abstract = "A multidatabase system provides integrated access to
heterogeneous, autonomous local databases in a
distributed system. An important problem in current
multidatabase systems is identification of semantically
similar data in different local databases. The Summary
Schemas Model (SSM) is proposed as an extension to
multidatabase systems to aid in semantic
identification. The SSM uses a global data structure to
abstract the information available in a multidatabase
system. This abstracted form allows users to use their
own terms (imprecise queries) when accessing data
rather than being forced to use system-specified terms.
The system uses the global data structure to match the
user's terms to the semantically closest available
system terms. A simulation of the SSM is presented to
compare imprecise-query processing with corresponding
query-processing costs in a standard multidatabase
system. The costs and benefits of the SSM are
discussed, and future research directions are
presented.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; federated database; imprecise queries;
multidatabase; performance; schemas; semantic
heterogeneity; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
H.2.5}: Information Systems, DATABASE MANAGEMENT,
Heterogeneous Databases.",
}
@Article{Sciore:1994:USV,
author = "Edward Sciore and Michael Siegel and Arnon Rosenthal",
title = "Using Semantic Values to Facilitate Interoperability
Among Heterogeneous Information Systems",
journal = j-TODS,
volume = "19",
number = "2",
pages = "254--290",
month = jun,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-2/p254-sciore/p254-sciore.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-2/p254-sciore/;
http://www.acm.org/pubs/toc/Abstracts/tods/176570.html",
abstract = "Large organizations need to exchange information among
many separately developed systems. In order for this
exchange to be useful, the individual systems must
agree on the meaning of their exchanged data. That is,
the organization must ensure {\em semantic
interoperability}. This paper provides a theory of {\em
semantic values\/} as a unit of exchange that
facilitates semantic interoperability between
heterogeneous information systems. We show how semantic
values can either be stored explicitly or be defined by
{\em environments}. A system architecture is presented
that allows autonomous components to share semantic
values. The key component in this architecture is
called the {\em context mediator}, whose job is to
identify and construct the semantic values being sent,
to determine when the exchange is meaningful, and to
convert the semantic values to the form required by the
receiver.\par
Our theory is then applied to the relational model. We
provide an interpretation of standard SQL queries in
which context conversions and manipulations are
transparent to the user. We also introduce an extension
of SQL, called Context-SQL (C-SQL), in which the {\em
context\/} of a semantic value can be explicitly
accessed and updated. Finally, we describe the
implementation of a prototype context mediator for a
relational C-SQL system.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Management",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; languages; management",
subject = "{\bf H.2.5}: Information Systems, DATABASE MANAGEMENT,
Heterogeneous Databases, Data translation. {\bf H.2.3}:
Information Systems, DATABASE MANAGEMENT, Languages,
Query languages. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Distributed systems.",
}
@Article{Subrahmanian:1994:AKB,
author = "V. S. Subrahmanian",
title = "Amalgamating Knowledge Bases",
journal = j-TODS,
volume = "19",
number = "2",
pages = "291--331",
month = jun,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-2/p291-subrahmanian/p291-subrahmanian.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-2/p291-subrahmanian/;
http://www.acm.org/pubs/toc/Abstracts/tods/176571.html",
abstract = "The integration of knowledge for multiple sources is
an important aspect of automated reasoning systems.
When different knowledge bases are used to store
knowledge provided by multiple sources, we are faced
with the problem of integrating multiple knowledge
bases: Under these circumstances, we are also
confronted with the prospect of inconsistency. In this
paper we present a uniform theoretical framework, based
on annotated logics, for amalgamating multiple
knowledge bases when these knowledge bases (possibly)
contain inconsistencies, uncertainties, and
nonmonotonic modes of negation. We show that annotated
logics may be used, with some modifications, to mediate
between different knowledge bases. The multiple
knowledge bases are amalgamated by a transformation of
the individual knowledge bases into new annotated logic
programs, together with the addition of a new axiom
scheme. We characterize the declarative semantics of
such amalgamated knowledge bases and study how the
semantics of the amalgam is related to the semantics of
the individual knowledge bases being combined.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "amalgamated knowledge bases; annotated logics;
languages",
subject = "{\bf I.2.4}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Knowledge Representation Formalisms and
Methods, Representations (procedural and rule-based).
{\bf H.2.5}: Information Systems, DATABASE MANAGEMENT,
Heterogeneous Databases, Data translation. {\bf I.2.4}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Knowledge Representation Formalisms and Methods,
Representation languages.",
}
@Article{Yan:1994:ISS,
author = "Tak W. Yan and H{\'e}ctor Garc{\'\i}a-Molina",
title = "Index Structures for Selective Dissemination of
Information Under the {Boolean} Model",
journal = j-TODS,
volume = "19",
number = "2",
pages = "332--364",
month = jun,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-2/p332-yan/p332-yan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-2/p332-yan/;
http://www.acm.org/pubs/toc/Abstracts/tods/176573.html",
abstract = "The number, size, and user population of bibliographic
and full-text document databases are rapidly growing.
With a high document arrival rate, it becomes essential
for users of such databases to have access to the very
latest documents; yet the high document arrival rate
also makes it difficult for users to keep themselves
updated. It is desirable to allow users to submit
profiles, i.e., queries that are constantly evaluated,
so that they will be automatically informed of new
additions that may be of interest. Such service is
traditionally called Selective Dissemination of
Information (SDI).\par
The high document arrival rate, the huge number of
users, and the timeliness requirement of the service
pose a challenge in achieving efficient SDL. In this
article, we propose several index structures for
indexing profiles and algorithms that efficiently match
documents against large number of profiles. We also
present analysis and simulation results to compare
their performance under different scenarios.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; performance",
subject = "{\bf H.3.1}: Information Systems, INFORMATION STORAGE
AND RETRIEVAL, Content Analysis and Indexing, Indexing
methods. {\bf H.2.2}: Information Systems, DATABASE
MANAGEMENT, Physical Design, Access methods. {\bf
H.3.4}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Systems and Software, Current awareness
systems (selective dissemination of information ---
SDI).",
}
@Article{Ceri:1994:AGP,
author = "Stefano Ceri and Piero Fraternali and Stefano
Paraboschi and Letizia Tanca",
title = "Automatic Generation of Production Rules for Integrity
Maintenance",
journal = j-TODS,
volume = "19",
number = "3",
pages = "367--422",
month = sep,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-3/p367-ceri/p367-ceri.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-3/p367-ceri/;
http://www.acm.org/pubs/toc/Abstracts/tods/185828.html",
abstract = "In this article we present an approach to integrity
maintenance, consisting of automatically generating
production rules for integrity enforcement. Constraints
are expressed as particular formulas of Domain
Relational Calculus; they are automatically translated
into a set of repair actions, encoded as production
rules of an active database system. Production rules
may be redundant (they enforce the same constraint in
different ways) and conflicting (because repairing one
constraint may cause the violation of another
constraint). Thus, it is necessary to develop
techniques for analyzing the properties of the set of
active rules and for ensuring that any computation of
production rules after any incorrect transaction
terminates and produces a consistent database
state.\par
Along these guidelines, we describe a specific
architecture for constraint definition and enforcement.
The components of the architecture include a {\em Rule
Generator}, for producing all possible repair actions,
and a {\em Rule Analyzer and Selector}, for producing a
collection of production rules such that their
execution after an incorrect transaction always
terminates in a consistent state (possibly by rolling
back the transaction); moreover, the needs of
applications are modeled, so that integrity-enforcing
rules reach the final state that better represents the
original intentions of the transaction's supplier.
Specific input from the designer can also drive the
process and integrate or modify the rules generated
automatically by the method. Experimental results of a
prototype implementation of the proposed architecture
are also described.",
acknowledgement = ack-nhfb,
affiliation = "Dipartimento di Elettronica, Politecnico di Milano,
Italy",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Experimentation; Management",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "automatic generation of production rules;
experimentation; management",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
I.2.2}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Automatic Programming.",
}
@Article{Polyzois:1994:ERB,
author = "Christos A. Polyzois and H{\'e}ctor
Garc{\'\i}a-Molina",
title = "Evaluation of Remote Backup Algorithms for
Transaction-Processing Systems",
journal = j-TODS,
volume = "19",
number = "3",
pages = "423--449",
month = sep,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-3/p423-polyzois/p423-polyzois.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-3/p423-polyzois/;
http://www.acm.org/pubs/toc/Abstracts/tods/185836.html",
abstract = "A remote backup is a copy of a primary database
maintained at a geographically separate location and is
used to increase data availability. Remote backup
systems are typically log-based and can be classified
into 2-safe and 1-safe, depending on whether
transactions commit at both sites simultaneously or
first commit at the primary and are later propagated to
the backup. We have built an experimental database
system on which we evaluated the performance of the
epoch and the dependency reconstruction algorithms, two
1-safe algorithms we have developed. We compared the
1-safe with the 2-safe approach under various
conditions.",
acknowledgement = ack-nhfb,
affiliation = "IBM Thomas J. Watson Res. Center, Yorktown Heights,
NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; disaster recovery; hot spare; hot standby;
performance; reliability; remote backup",
subject = "{\bf H.2.7}: Information Systems, DATABASE MANAGEMENT,
Database Administration, Logging and recovery. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed applications. {\bf D.4.5}: Software,
OPERATING SYSTEMS, Reliability, Backup procedures. {\bf
D.4.5}: Software, OPERATING SYSTEMS, Reliability,
Fault-tolerance.",
}
@Article{Chrysanthis:1994:SET,
author = "Panos K. Chrysanthis and Krithi Ramamritham",
title = "Synthesis of Extended Transaction Models Using
{ACTA}",
journal = j-TODS,
volume = "19",
number = "3",
pages = "450--491",
month = sep,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-3/p450-chrysanthis/p450-chrysanthis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-3/p450-chrysanthis/;
http://www.acm.org/pubs/toc/Abstracts/tods/185843.html",
abstract = "ACTA is a comprehensive transaction framework that
facilitates the formal description of properties of
extended transaction models. Specifically, using ACTA,
one can specify and reason about (1) the effects of
transactions on objects and (2) the interactions
between transactions. This article presents ACTA {\em
as a tool for the synthesis of extended transaction
models}, one which supports the development and
analysis of new extended transaction models in a
systematic manner. Here, this is demonstrated by
deriving new transaction definitions (1) by modifying
the specifications of existing transaction models, (2)
by combining the specifications of existing models, and
(3) by starting from first principles. To exemplify the
first, new models are synthesized from {\em atomic
transactions\/} and {\em join transactions}. To
illustrate the second, we synthesize a model that
combines aspect of the {\em nested\/}- and {\em
split-transaction\/} models. We demonstrate the latter
by deriving the specification of an {\em
open-nested-transaction\/} model from high-level
requirements.",
acknowledgement = ack-nhfb,
affiliation = "Pittsburgh Univ., PA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Reliability; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; correctness criteria; design;
reliability; semantics; serializability theory; theory;
transaction models; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed databases. {\bf
D.2.4}: Software, SOFTWARE ENGINEERING, Program
Verification, Correctness proofs. {\bf D.3.3}:
Software, PROGRAMMING LANGUAGES, Language Constructs
and Features, Abstract data types. {\bf D.4.1}:
Software, OPERATING SYSTEMS, Process Management,
Concurrency. {\bf F.3.1}: Theory of Computation, LOGICS
AND MEANINGS OF PROGRAMS, Specifying and Verifying and
Reasoning about Programs, Assertions. {\bf H.2.4}:
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Distributed systems.",
}
@Article{Korth:1994:FAC,
author = "Henry F. Korth and Greg Speegle",
title = "Formal Aspects of Concurrency Control in Long-Duration
Transaction Systems Using the {NT\slash PV} model",
journal = j-TODS,
volume = "19",
number = "3",
pages = "492--535",
month = sep,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-3/p492-korth/p492-korth.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-3/p492-korth/;
http://www.acm.org/pubs/toc/Abstracts/tods/185854.html",
abstract = "In the typical database system, an execution is
correct if it is equivalent to some serial execution.
This criterion, called serializability, is unacceptable
for new database applications which require
long-duration transactions. We present a new
transaction model which allows correctness criteria
more suitable for these applications. This model
combines three enhancements to the standard model:
nested transactions, explicit predicates, and multiple
versions. These features yield the name of the new
model, nested transactions with predicates and
versions, or NT/PV.\par
The modular nature of the NT/PV model allows a
straightforward representation of simple systems. It
also provides a formal framework for describing complex
interactions. The most complex interactions the model
allows can be captured by a protocol which exploits all
of the semantics available to the NT/PV model. An
example of these interactions is shown in a CASE
application. The example shows how a system based on
the NT/PV model is superior to both standard database
techniques and unrestricted systems in both correctness
and performance.",
acknowledgement = ack-nhfb,
affiliation = "Matsushita Inf. Technol. Lab., Panasonic Technol.
Inc., Princeton, NJ, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control protocol; semantic information;
theory; transaction processing",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Transaction processing.",
}
@Article{Goldman:1994:QCN,
author = "Kenneth J. Goldman and Nancy Lynch",
title = "Quorum Consensus in Nested-Transaction Systems",
journal = j-TODS,
volume = "19",
number = "4",
pages = "537--585",
month = dec,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-4/p537-goldman/p537-goldman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-4/p537-goldman/;
http://www.acm.org/pubs/toc/Abstracts/tods/195666.html",
abstract = "Gifford's Quorum Consensus algorithm for data
replication is studied in the context of nested
transactions and transaction failures (aborts), and a
fully developed reconfiguration strategy is presented.
A formal description of the algorithm is presented
using the Input/Output automaton model for
nested-transaction systems due to Lynch and Merritt. In
this description, the algorithm itself is described in
terms of nested transactions. The formal description is
used to construct a complete proof of correctness that
uses standard assertional techniques, is based on a
natural correctness condition, and takes advantage of
modularity that arises from describing the algorithm as
nested transactions. The proof is accomplished
hierarchically, showing that a fully replicated
reconfigurable system ``simulates'' an intermediate
replicated system, and that the intermediate system
simulates an unreplicated system. The presentation and
proof treat issues of data replication entirely
separately from issues of concurrency control and
recovery.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Washington Univ., St. Louis,
MO, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; concurrency control; data replication;
hierarchical proofs; I/O automata; nested transactions;
quorum consensus; theory; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4}: Information Systems,
DATABASE MANAGEMENT, Systems, Distributed systems.",
}
@Article{Krishnakumar:1994:BIT,
author = "Narayanan Krishnakumar and Arthur J. Bernstein",
title = "Bounded Ignorance: a Technique for Increasing
Concurrency in a Replicated System",
journal = j-TODS,
volume = "19",
number = "4",
pages = "586--625",
month = dec,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-4/p586-krishnakumar/p586-krishnakumar.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-4/p586-krishnakumar/;
http://www.acm.org/pubs/toc/Abstracts/tods/195670.html",
abstract = "Databases are replicated to improve performance and
availability. The notion of correctness that has
commonly been adopted for concurrent access by
transactions to shared, possibly replicated, data is
serializability. However, serializability may be
impractical in high-performance applications since it
imposes too stringent a restriction on concurrency.
When serializability is relaxed, the integrity
constraints describing the data may be violated. By
allowing bounded violations of the integrity
constraints, however, we are able to increase the
concurrency of transactions that execute in a
replicated environment. In this article, we introduce
the notion of an {\em N-ignorant\/} transaction, which
is a transaction that may be ignorant of the results of
at most $N$ prior transactions, which is a transaction
that may be ignorant of the results of at most $N$
prior transactions. A system in which all transactions
are {\em N-ignorant\/} can have an $N$ + 1-fold
increase in concurrency over serializable systems, at
the expense of bounded violations of its integrity
constraints. We present algorithms for implementing
replicated databases in {\em N-ignorant\/} systems. We
then provide constructive methods for calculating the
reachable states in such systems, given the value of
$N$, so that one may assess the maximum liability that
is incurred in allowing constraint violation. Finally,
we generalize the notion of {\em N-ignorance\/} to a
matrix of ignorance for the purpose of higher
concurrency.",
acknowledgement = ack-nhfb,
affiliation = "State Univ. of New York, Stony Brook, NY, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; concurrency control; integrity
constraints; performance; reachability analysis;
replication; serializability; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf C.2.4}: Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed applications. {\bf
C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Concurrency.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Distributed systems.",
}
@Article{Winslett:1994:FQL,
author = "Marianne Winslett and Kenneth Smith and Xiaolei Qian",
title = "Formal Query Languages for Secure Relational
Databases",
journal = j-TODS,
volume = "19",
number = "4",
pages = "626--662",
month = dec,
year = "1994",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1994-19-4/p626-winslett/p626-winslett.pdf;
http://www.acm.org/pubs/citations/journals/tods/1994-19-4/p626-winslett/;
http://www.acm.org/pubs/toc/Abstracts/tods/195675.html",
abstract = "The addition of stringent security specifications to
the list of requirements for an application poses many
new problems in DBMS design and implementation, as well
as database design, use, and maintenance. Tight
security requirements, such as those that result in
silent masking of withholding of true information from
a user or the introduction of false information into
query answers, also raise fundamental questions about
the meaning of the database and the semantics of
accompanying query languages. In this paper, we propose
a belief-based semantics for secure databases, which
provides a semantics for databases that can ``lie''
about the state of the world, or about their knowledge
about the state of the world, in order to preserve
security. This kind of semantics can be used as a
helpful retrofit for the proposals for a ``multilevel
secure'' database model (a particularly stringent form
of security), and may be useful for less restrictive
security policies as well. We also propose a family of
query languages for multilevel secure relational
database applications, and base the semantics of those
languages on our semantics for secure databases. Our
query languages are free of the semantic problems
associated with use of ordinary SQL in a multilevel
secure context, and should be easy for users to
understand and employ.",
acknowledgement = ack-nhfb,
affiliation = "Dept. of Comput. Sci., Illinois Univ., Urbana, IL,
USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "formal security models; information security;
multilevel secure databases; security",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
K.6.5}: Computing Milieux, MANAGEMENT OF COMPUTING AND
INFORMATION SYSTEMS, Security and Protection. {\bf
H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages.",
}
@Article{Kim:1995:CS,
author = "Won Kim",
title = "Charter and scope",
journal = j-TODS,
volume = "20",
number = "1",
pages = "1--2",
month = mar,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 10 13:00:12 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Aiken:1995:SAT,
author = "Alexander Aiken and Joseph M. Hellerstein and Jennifer
Widom",
title = "Static Analysis Techniques for Predicting the Behavior
of Active Database Rules",
journal = j-TODS,
volume = "20",
number = "1",
pages = "3--41",
month = mar,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-1/p3-aiken/p3-aiken.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-1/p3-aiken/;
http://www.acm.org/pubs/toc/Abstracts/tods/202107.html",
abstract = "This article gives methods for statically analyzing
sets of active database rules to determine if the rules
are (1) guaranteed to terminate, (2) guaranteed to
produce a unique final database state, and (3)
guaranteed to produce a unique stream of observable
actions. If the analysis determines that one of these
properties is not guaranteed, it isolates the rules
responsible for the problem and determines criteria
that, if satisfied, guarantee the property. The
analysis methods are presented in the context of the
{\em Starburst Rule System}.",
acknowledgement = ack-nhfb,
affiliation = "California Univ., Berkeley, CA, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Management; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active database systems; algorithms; confluence;
database rule processing; design; management; static
analysis; termination; verification",
subject = "{\bf H.2.m}: Information Systems, DATABASE MANAGEMENT,
Miscellaneous. {\bf D.2.4}: Software, SOFTWARE
ENGINEERING, Program Verification, Validation. {\bf
I.2.5}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Programming Languages and Software.",
}
@Article{Chen:1995:DUR,
author = "Weidong Chen",
title = "Declarative Updates of Relational Databases",
journal = j-TODS,
volume = "20",
number = "1",
pages = "42--70",
month = mar,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-1/p42-chen/p42-chen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-1/p42-chen/;
http://www.acm.org/pubs/toc/Abstracts/tods/202110.html",
abstract = "This article presents a declarative language, called
{\em update calculus}, of relational database updates.
A formula in update calculus involves conditions for
the current database, as well as assertions about a new
database. Logical connectives and quantifiers become
constructors of complex updates, offering flexible
specifications of database transformations. Update
calculus can express all nondeterministic database
transformations that are polynomial time.\par
For set-at-a-time evaluation of updates, we present a
corresponding {\em update algebra}. Existing techniques
of query processing can be incorporated into update
evaluation. We show that updates in update calculus can
be translated into expressions in update algebra and
vice versa.",
acknowledgement = ack-nhfb,
affiliation = "Southern Methodist Univ., Dallas, TX, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database languages; database updates; expressive
power; languages; theory; update algebra; update
calculus",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Data manipulation languages (DML).",
}
@Article{Jagadish:1995:IDM,
author = "H. V. Jagadish",
title = "The {INCINERATE} data model",
journal = j-TODS,
volume = "20",
number = "1",
pages = "71--110",
month = mar,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-1/p71-jagadish/p71-jagadish.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-1/p71-jagadish/;
http://www.acm.org/pubs/toc/Abstracts/tods/202113.html",
abstract = "In this article, we present an extended relational
algebra with universally or existentially quantified
classes as attribute values. The proposed extension can
greatly enhance the expressive power of relational
systems, and significantly reduce the size of a
database, at small additional computational cost. We
also show how the proposed extensions can be built on
top of a standard relational database system.",
acknowledgement = ack-nhfb,
affiliation = "AT\&T Bell Labs., Murray Hill, NJ, USA",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models.",
}
@Article{Baekgaard:1995:ICN,
author = "Lars Baekgaard and Leo Mark",
title = "Incremental Computation of Nested Relational Query
Expressions",
journal = j-TODS,
volume = "20",
number = "2",
pages = "111--148",
month = jun,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-2/p111-baekgaard/p111-baekgaard.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-2/p111-baekgaard/;
http://www.acm.org/pubs/toc/Abstracts/tods/210198.html",
abstract = "Efficient algorithms for incrementally computing
nested query expressions do not exist. Nested query
expressions are query expressions in which
selection/join predicates contain subqueries. In order
to respond to this problem, we propose a two-step
strategy for incrementally computing nested query
expressions. In step (1), the query expression is
transformed into an equivalent unnested flat query
expression. In step (2), the flat query expression is
incrementally computed. To support step (1), we have
developed a very concise algebra-to-algebra
transformation algorithm, and we have formally proved
its correctness. The flat query expressions resulting
from the transformation make intensive use of the
relational set-difference operator. To support step
(2), we present and analyze an efficient algorithm for
incrementally computing set differences based on view
pointer caches. When combined with existing incremental
algorithms for SPJ queries, our incremental
set-difference algorithm can be used to compute the
unnested flat query expressions efficiently. It is
important to notice that without our incremental
set-difference algorithm the existing incremental
algorithms for SPJ queries are useless for any query
involving the set-difference operator, including
queries that are not the result of unnesting nested
queries.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; incremental computation; nested query
expressions; performance; set differences; unnesting;
view pointer caches",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.2}: Information
Systems, DATABASE MANAGEMENT, Physical Design, Access
methods. {\bf H.2.3}: Information Systems, DATABASE
MANAGEMENT, Languages, Query languages. {\bf H.3.3}:
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval, Search process. {\bf
H.3.3}: Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval, Query
formulation. {\bf E.5}: Data, FILES,
Sorting/searching.",
}
@Article{Chomicki:1995:ECT,
author = "Jan Chomicki",
title = "Efficient Checking of Temporal Integrity Constraints
Using Bounded History Encoding",
journal = j-TODS,
volume = "20",
number = "2",
pages = "149--186",
month = jun,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-2/p149-chomicki/p149-chomicki.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-2/p149-chomicki/;
http://www.acm.org/pubs/toc/Abstracts/tods/210200.html",
abstract = "We present an efficient implementation method for
temporal integrity constraints formulated in Past
Temporal Logic. Although the constraints can refer to
past states of the database, their checking does not
require that the entire database history be stored.
Instead, every database state is extended with
auxiliary relations that contain the historical
information necessary for checking constraints.
Auxiliary relations can be implemented as materialized
relational views.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active databases; algorithms; database integrity;
integrity constraints; real-time databases; temporal
databases; temporal logic; theory; triggers",
subject = "{\bf H.2.0}: Information Systems, DATABASE MANAGEMENT,
General, Security, integrity, and protection. {\bf
F.4.1}: Theory of Computation, MATHEMATICAL LOGIC AND
FORMAL LANGUAGES, Mathematical Logic. {\bf H.2.3}:
Information Systems, DATABASE MANAGEMENT, Languages,
Data description languages (DDL).",
}
@Article{Graefe:1995:FAU,
author = "Goetz Graefe and Richard L. Cole",
title = "Fast Algorithms for Universal Quantification in large
Databases",
journal = j-TODS,
volume = "20",
number = "2",
pages = "187--236",
month = jun,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-2/p187-graefe/p187-graefe.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-2/p187-graefe/;
http://www.acm.org/pubs/toc/Abstracts/tods/210202.html",
abstract = "Universal quantification is not supported directly in
most database systems despite the fact that it adds
significant power to a system's query processing and
inference capabilities, in particular for the analysis
of many-to-many relationships and of set-valued
attributes. One of the main reasons for this omission
has been that universal quantification algorithms and
their performance have not been explored for large
databases. In this article, we describe and compare
three known algorithms and one recently proposed
algorithm for relational division, the algebra operator
that embodies universal quantification. For each
algorithm, we investigate the performance effects of
explicit duplicate removal and referential integrity
enforcement, variants for inputs larger than memory,
and parallel execution strategies. Analytical and
experimental performance comparisons illustrate the
substantial differences among the algorithms. Moreover,
comparisons demonstrate that the recently proposed
division algorithm evaluates a universal quantification
predicate over two relations as fast as hash (semi-)
join evaluates an existential quantification predicate
over the same relations. Thus, existential and
universal quantification can be supported with equal
efficiency by adding the recently proposed algorithm to
a query evaluation system. A second result of our study
is that universal quantification should be expressed
directly in a database query language, because most
query optimizers do not recognize the rather indirect
formulations available in SQL as relational division
and therefore produce very poor evaluation plans for
many universal quantification queries.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; experimentation",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf E.5}: Data, FILES.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML).",
}
@Article{Chen:1995:QED,
author = "Weidong Chen",
title = "Query Evaluation in Deductive Databases with
Alternating Fixpoint Semantics",
journal = j-TODS,
volume = "20",
number = "3",
pages = "239--287",
month = sep,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
MRclass = "68P15 (68P20)",
MRnumber = "96g:68024",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-3/p239-chen/p239-chen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-3/p239-chen/;
http://www.acm.org/pubs/toc/Abstracts/tods/211416.html",
abstract = "First-order formulas allow natural descriptions of
queries and rules. Van Gelder's alternating fixpoint
semantics extends the well-founded semantics of normal
logic programs to general logic programs with arbitrary
first-order formulas in rule bodies. However, an
implementation of general logic programs through the
standard translation into normal logic programs does
not preserve the alternating fixpoint semantics. This
paper presents a direct method for goal-oriented query
evaluation of general logic programs. Every general
logic program is first transformed into a normal form
where the body of each rule is either an existential
conjunction of literals or a universal disjunction of
literals. Techniques of memoing and loop checking are
incorporated so that termination and polynomial-time
data complexity are guaranteed for deductive databases
(or function-free programs). Results of the soundness
and search space completeness are established.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "alternating fixpoint; deductive databases; negation;
predicate logic; query evaluations; SLG resolution;
theory; verification",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing. {\bf I.2.3}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem Proving,
Logic programming.",
}
@Article{Ioannidis:1995:CCQ,
author = "Yannis E. Ioannidis and Raghu Ramakrishnan",
title = "Containment of Conjunctive Queries: Beyond Relations
as Sets",
journal = j-TODS,
volume = "20",
number = "3",
pages = "288--324",
month = sep,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-3/p288-ioannidis/p288-ioannidis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-3/p288-ioannidis/;
http://www.acm.org/pubs/toc/Abstracts/tods/211419.html",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; conjunctive queries; equivalence;
languages; multisets; query containment; query
optimization; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf F.0}: Theory of
Computation, GENERAL. {\bf H.2.3}: Information Systems,
DATABASE MANAGEMENT, Languages, Query languages. {\bf
H.1.1}: Information Systems, MODELS AND PRINCIPLES,
Systems and Information Theory.",
}
@Article{Shasha:1995:TCA,
author = "Dennis Shasha and Fran{\c{c}}ois Llirbat and Eric
Simon and Patrick Valduriez",
title = "Transaction Chopping: Algorithms and Performance
Studies",
journal = j-TODS,
volume = "20",
number = "3",
pages = "325--363",
month = sep,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-3/p325-shasha/p325-shasha.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-3/p325-shasha/;
http://www.acm.org/pubs/toc/Abstracts/tods/211427.html",
abstract = "Chopping transactions into pieces is good for
performance but may lead to nonserializable executions.
Many researchers have reacted to this fact by either
inventing new concurrency-control mechanisms, weakening
serializability, or both. We adopt a different
approach. We assume a user who\par
---has access only to user-level tools such as (1)
choosing isolation degrees 1ndash;4, (2) the ability to
execute a portion of a transaction using multiversion
read consistency, and (3) the ability to reorder the
instructions in transaction programs; and\par
---knows the set of transactions that may run during a
certain interval (users are likely to have such
knowledge for on-line or real-time transactional
applications).\par
Given this information, our algorithm finds the finest
chopping of a set of transactions TranSet with the
following property: {\em If the pieces of the chopping
execute serializably, then TranSet executes
serializably}. This permits users to obtain more
concurrency while preserving correctness. Besides
obtaining more intertransaction concurrency, chopping
transactions in this way can enhance intratransaction
parallelism.\par
The algorithm is inexpensive, running in $ O(n x(e +
m)) $ time, once conflicts are identified, using a
naive implementation, where $n$ is the number of
concurrent transactions in the interval $e$ is the
number of edges in the conflict graph among the
transactions, and $m$ is the maximum number of accesses
of any transaction. This makes it feasible to add as a
tuning knob to real systems.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; locking; multidatabase; performance;
serializability; tuning",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf D.4.8}: Software,
OPERATING SYSTEMS, Performance, Simulation. {\bf
H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf I.6.8}: Computing
Methodologies, SIMULATION AND MODELING, Types of
Simulation, Discrete event.",
}
@Article{Chen:1995:EML,
author = "I.-Min A. Chen and Richard Hull and Dennis McLeod",
title = "An Execution Model for Limited Ambiguity Rules and its
Application to Derived Data Update",
journal = j-TODS,
volume = "20",
number = "4",
pages = "365--413",
month = dec,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-4/p365-chen/p365-chen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-4/p365-chen/;
http://www.acm.org/pubs/toc/Abstracts/tods/219039.html",
abstract = "A novel execution model for rule application in active
databases is developed and applied to the problem of
updating derived data in a database represented using a
semantic, object-based database model. The execution
model is based on the use of ``limited ambiguity
rules'' (LARs), which permit disjunction in rule
actions. The execution model essentially performs a
breadth-first exploration of alternative extensions of
a user-requested update. Given an object-based database
schema, both integrity constraints and specifications
of derived classes and attributes are compiled into a
family of limited ambiguity rules. A theoretical
analysis shows that the approach is sound: the
execution model returns all valid ``completions'' of a
user-requested update, or terminates with an
appropriate error notification. The complexity of the
approach in connection with derived data update is
considered.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Languages; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active database systems; algorithms; deltas on
database states; derived data; design; languages;
limited ambiguity rules; management; semantic data
models; theory; update propagation",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.m}: Information
Systems, DATABASE MANAGEMENT, Miscellaneous.",
}
@Article{Fraternali:1995:SAD,
author = "Piero Fraternali and Letizia Tanca",
title = "A Structured Approach for the Definition of the
Semantics of Active Databases",
journal = j-TODS,
volume = "20",
number = "4",
pages = "414--471",
month = dec,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-4/p414-fraternali/p414-fraternali.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-4/p414-fraternali/;
http://www.acm.org/pubs/toc/Abstracts/tods/219042.html",
abstract = "Active DBMSs couple database technology with
rule-based programming to achieve the capability of
reaction to database (and possibly external) stimuli,
called {\em events}. The reactive capabilities of
active databases are useful for a wide spectrum of
applications, including security, view materialization,
integrity checking and enforcement, or heterogeneous
database integration, which makes this technology very
promising for the near future. An active database
system consists of a (passive) database and a set of
{\em active rules\/}; the most popular form of active
rule is the so-called {\em event-condition-action\/}
(ECA) rule, which specifies an action to be executed
upon the occurrence of one or more events, provided
that a condition holds. Several active database systems
and prototypes have been designed and partially or
completely implemented. Unfortunately, they have been
designed in a totally independent way, without the
support of a common theory dictating the semantics of
ECA rules, and thus often show different behaviors for
rules with a similar form. In this article we consider
a number of different possible options in the behavior
of an active DBMS, based on a broad analysis of some of
the best known implemented systems and prototypes. We
encode these options in a user-readable form, called
{\em Extended ECA}. A rule from any existing system can
be rewritten in this formalism making all the semantic
choices apparent. Then an EECA rule can be
automatically translated into an internal (less
readable) format, based on a logical style, which is
called {\em core\/} format: the execution semantics of
core rules is specified as the fixpoint of a simple
transformation involving core rules. As an important
premise to this research, a semantics for database
updates and transactions has also been established,
with respect to a notion of state that comprises both
data and events. The article also presents an extensive
bibliography on the subject of active databases.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active database systems; database rule processing;
events; fixpoint semantics; languages; rules;
semantics; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf F.3.2}: Theory of Computation,
LOGICS AND MEANINGS OF PROGRAMS, Semantics of
Programming Languages, Operational semantics. {\bf
H.2.m}: Information Systems, DATABASE MANAGEMENT,
Miscellaneous. {\bf I.2.5}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Programming Languages and
Software.",
}
@Article{Srivastava:1995:SOD,
author = "Divesh Srivastava and S. Sudarshan and Raghu
Ramakrishnan and Jeffrey F. Naughton",
title = "Space Optimization in Deductive Databases",
journal = j-TODS,
volume = "20",
number = "4",
pages = "472--516",
month = dec,
year = "1995",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1995-20-4/p472-srivastava/p472-srivastava.pdf;
http://www.acm.org/pubs/citations/journals/tods/1995-20-4/p472-srivastava/;
http://www.acm.org/pubs/toc/Abstracts/tods/219056.html",
abstract = "In the bottom-up evaluation of logic programs and
recursively defined views on databases, all generated
facts are usually assumed to be stored until the end of
the evaluation. Discarding facts during the evaluation,
however, can considerably improve the efficiency of the
evaluation: the space needed to evaluate the program,
the I/O costs, the costs of maintaining and accessing
indices, and the cost of eliminating duplicates may all
be reduced. Given an evaluation method that is sound,
complete, and does not repeat derivation steps, we
consider how facts can be discarded during the
evaluation without compromising these properties. We
show that every such space optimization method has
certain components, the first to ensure soundness and
completeness, the second to avoid redundancy (i.e.,
repetition of derivations), and the third to reduce
``fact lifetimes'' (i.e., the time period for which
each fact must be retained during evaluation). We
present new techniques based on providing bounds on the
number of derivations and uses of facts, and using
monotonicity constraints for each of the first two
components, and provide novel synchronization
techniques for the third component of a space
optimization method. We describe how techniques for
each of the three components can be combined in
practice to obtain a space optimization method for a
program. Our results are also of importance in
applications such as sequence querying, and in active
databases where triggers are defined over multiple
``events.''",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; bottom-up query evaluation deductive
database systems; discarding facts; languages; logic
programming; theory",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages.",
}
@Article{Baralis:1996:MTA,
author = "Elena Baralis and Stefano Ceri and Stefano
Paraboschi",
title = "Modularization Techniques for Active Rules Design",
journal = j-TODS,
volume = "21",
number = "1",
pages = "1--29",
month = mar,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-1/p1-baralis/p1-baralis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-1/p1-baralis/;
http://www.acm.org/pubs/toc/Abstracts/tods/227605.html",
abstract = "Active database systems can be used to establish and
enforce data management policies. A large amount of the
semantics that normally needs to be coded in
application programs can be abstracted and assigned to
active rules. This trend is sometimes called
``knowledge independence'' a nice consequence of
achieving full knowledge independence is that data
management policies can then effectively evolve just by
modifying rules instead of application programs. Active
rules, however, may be quite complex to understand and
manage: rules react to arbitrary event sequences, they
trigger each other, and sometimes the outcome of rule
processing may depend on the order in which events
occur or rules are scheduled. Although reasoning on a
large collection of rules is very difficult, the task
becomes more manageable when the rules are few.
Therefore, we are convinced that modularization,
similar to what happens in any software development
process, is the key principle for designing active
rules; however, this important notion has not been
addressed so far. This article introduces a
modularization technique for active rules called
stratification; it presents a theory of stratification
and indicates how stratification can be practically
applied. The emphasis of this article is on providing a
solution to a very concrete and practical problem;
therefore, our approach is illustrated by several
examples.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active database systems; database rule processing;
design; modularization; static analysis; termination",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Schema and subschema. {\bf D.2.1}:
Software, SOFTWARE ENGINEERING,
Requirements/Specifications, Methodologies. {\bf
D.2.2}: Software, SOFTWARE ENGINEERING, Tools and
Techniques, Modules and interfaces. {\bf H.2.8}:
Information Systems, DATABASE MANAGEMENT, Database
applications.",
}
@Article{Buneman:1996:PTI,
author = "Peter Buneman and Atsushi Ohori",
title = "Polymorphism and Type Inference in Database
Programming",
journal = j-TODS,
volume = "21",
number = "1",
pages = "30--76",
month = mar,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-1/p30-buneman/p30-buneman.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-1/p30-buneman/;
http://www.acm.org/pubs/toc/Abstracts/tods/227609.html",
abstract = "In order to find a static type system that adequately
supports database languages, we need to express the
most general type of a program that involves database
operations. This can be achieved through an extension
to the type system of ML that captures the polymorphic
nation of field selection, together with a techniques
that generalizes relational operators to arbitrary data
structures. The combination provides a statically typed
language in which generalized relational databases may
be cleanly represented as typed structures. As in ML
types are inferred, which relieves the programmer of
making the type assertions that may be required in a
complex database environment.\par
These extensions may also be used to provide static
polymorphic typechecking in object-oriented languages
and databases. A problem that arises with
object-oriented databases is the apparent need for
dynamic typechecking when dealing queries on
heterogeneous collections of objects. An extension of
the type system needed for generalized relational
operations can also be used for manipulating
collections of dynamically typed values in a statically
typed language. A prototype language based on these
ideas has been implemented. While it lacks a proper
treatment of persistent data, it demonstrates that a
wide variety of database structures can be cleanly
represented in a polymorphic programming language.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "generalized relational algebra; inheritance;
object-oriented databases; polymorphism; record
calculus; theory; type inference",
subject = "{\bf D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features, Data types and structures.
{\bf D.3.1}: Software, PROGRAMMING LANGUAGES, Formal
Definitions and Theory. {\bf D.3.2}: Software,
PROGRAMMING LANGUAGES, Language Classifications,
Applicative languages. {\bf D.3.3}: Software,
PROGRAMMING LANGUAGES, Language Constructs and
Features, Abstract data types. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models. {\bf H.2.1}: Information Systems, DATABASE
MANAGEMENT, Logical Design, Schema and subschema. {\bf
H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Database (persistent) programming languages.
{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Query languages.",
}
@Article{Mok:1996:NFP,
author = "Wai Yin Mok and Yiu-Kai Ng and David W. Embley",
title = "A Normal Form for Precisely Characterizing Redundancy
in Nested Relations",
journal = j-TODS,
volume = "21",
number = "1",
pages = "77--106",
month = mar,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-1/p77-mok/p77-mok.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-1/p77-mok/;
http://www.acm.org/pubs/toc/Abstracts/tods/227612.html",
abstract = "We give a straightforward definition for redundancy in
individual nested relations and define a new normal
form that precisely characterizes redundancy for nested
relations. We base our definition of redundancy on an
arbitrary set of functional and multivalued
dependencies, and show that our definition of nested
normal form generalizes standard relational
normalization theory. In addition, we give a condition
that can prevent an unwanted structural anomaly in
nested relations, namely, embedded nested relations
with at most one tuple. Like other normal forms, our
nested normal form can serve as a guide for database
design.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data redundancy; database design; design; functional
and multivalued dependencies; nested normal form;
nested relations; normalization theory; scheme trees;
theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms. {\bf H.2.1}: Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models.",
}
@Article{Mumick:1996:MC,
author = "Inderpal Singh Mumick and Sheldon J. Finkelstein and
Hamid Pirahesh and Raghu Ramakrishnan",
title = "Magic conditions",
journal = j-TODS,
volume = "21",
number = "1",
pages = "107--155",
month = mar,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-1/p107-mumick/p107-mumick.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-1/p107-mumick/;
http://www.acm.org/pubs/toc/Abstracts/tods/227624.html",
abstract = "Much recent work has focused on the bottom-up
evaluation of Datalog programs [Bancilhon and
Ramakrishnan 1988]. One approach, called magic-sets, is
based on rewriting a logic program so that bottom-up
fixpoint evaluation of the program avoids generation of
irrelevant facts [Bancilhon et al. 1986; Beeri and
Ramakrishnan 1987; Ramakrishnan 1991]. It was widely
believed for some time that the principal application
of the magic-sets technique is to restrict computation
in recursive queries using equijoin predicates. We
extend the magic-sets transformation to use predicates
other than equality ($ X > 10 $, for example) in
restricting computation. The resulting {\em ground
magic-sets transformation\/} is an important step in
developing an extended magic-sets transformation that
has practical utility in ``real'' relational databases,
not only for recursive queries, but for nonrecursive
queries as well [Mumick et al. 1990b; Mumick 1991].",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Measurement; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; bottom-up evaluation; constraint logic
programming; constraints; deductive databases; magic
sets; measurement; query optimization; relational
databases; Starburst; theory; verification",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing.",
}
@Article{Liu:1996:BBS,
author = "Ling Liu and Robert Meersman",
title = "The Building Blocks for Specifying Communication
Behavior of Complex Objects: An Activity-Driven
Approach",
journal = j-TODS,
volume = "21",
number = "2",
pages = "157--207",
month = jun,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-2/p157-liu/p157-liu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-2/p157-liu/;
http://www.acm.org/pubs/toc/Abstracts/tods/232622.html",
abstract = "Communication behavior represents dynamic evolution
and cooperation of a group of objects in accomplishing
a task. It is an important feature in object-oriented
systems. We propose the concept of activity as a basic
building block for declarative specification of
communication behavior in object-oriented database
systems, including the temporal ordering of message
exchanges within object communication and the
behavioral relationships between activity executions.
We formally introduce two kinds of activity composition
mechanisms: {\em activity specialization\/} and
activity {\em aggregation\/} for abstract
implementation of communication behavior. The former is
suited for behavioral refinement of existing activities
into specialized activities. The latter is used for
behavioral composition of simpler activities into
complex activities, and ultimately, into the envisaged
database system. We use first-order temporal logic as
an underlying formalism for specification of
communication constraints. The well known
Air-traffic-control case is used as a running example
to highlight the underlying concepts, to illustrate the
usefulness, and to assess the effectiveness of the
activity model for declarative specification of
communication behavior in the relevant universe of
discourse. We also propose a methodological framework
for integrating activity schema with entity schema in
an object-oriented design environment.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "activity aggregation; activity patterns; activity
specialization; communication behavior; design;
first-order temporal logic; languages; object-oriented
databases; synchronization schemes; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf D.3.1}: Software, PROGRAMMING
LANGUAGES, Formal Definitions and Theory, Semantics.
{\bf F.3.1}: Theory of Computation, LOGICS AND MEANINGS
OF PROGRAMS, Specifying and Verifying and Reasoning
about Programs, Specification techniques. {\bf H.2.3}:
Information Systems, DATABASE MANAGEMENT, Languages.
{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems. {\bf C.2.4}: Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases.",
}
@Article{Ross:1996:TRE,
author = "Kenneth A. Ross",
title = "Tail Recursion Elimination in Deductive Databases",
journal = j-TODS,
volume = "21",
number = "2",
pages = "208--237",
month = jun,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-2/p208-ross/p208-ross.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-2/p208-ross/;
http://www.acm.org/pubs/toc/Abstracts/tods/232628.html",
abstract = "We consider an optimization technique for deductive
and relational databases. The optimization technique is
an extension of the magic templates rewriting, and it
can improve the performance of query evaluation by not
materializing the extension of intermediate views.
Standard relational techniques, such as unfolding
embedded view definitions, do not apply to recursively
defined views, and so alternative techniques are
necessary. We demonstrate the correctness of our
rewriting. We define a class of ``nonrepeating'' view
definitions, and show that for certain queries our
rewriting performs at least as well as magic templates
on nonrepeating views, and often much better. A
syntactically recognizable property, called ``weak
right-linearity'', is proposed. Weak right-linearity is
a sufficient condition for nonrepetition and is more
general than right-linearity. Our technique gives the
same benefits as right-linear evaluation of
right-linear views, while applying to a significantly
more general class of views.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; deductive databases; magic sets; query
optimization; tail recursion",
subject = "{\bf H.2.4}: Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf I.2.3}: Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem Proving,
Logic programming.",
}
@Article{Bell:1996:IDD,
author = "Colin Bell and Anil Nerode and Raymond T. Ng and V. S.
Subrahmanian",
title = "Implementing Deductive Databases by Mixed Integer
Programming",
journal = j-TODS,
volume = "21",
number = "2",
pages = "238--269",
month = jun,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-2/p238-bell/p238-bell.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-2/p238-bell/;
http://www.acm.org/pubs/toc/Abstracts/tods/232691.html",
abstract = "Existing and past generations of Prolog compilers have
left deduction to run-time and this may account for the
poor run-time performance of existing Prolog systems.
Our work tries to minimize run-time deduction by
shifting the deductive process to compile-time. In
addition, we offer an alternative inferencing procedure
based on translating logic to mixed integer
programming. This makes available for research and
implementation in deductive databases, all the
theorems, algorithms, and software packages developed
by the operations research community over the past 50
years. The method keeps the same query language as for
disjunctive deductive databases, only the inferencing
procedure changes. The language is purely declarative,
independent of the order of rules in the program, and
independent of the order in which literals occur in
clause bodies. The technique avoids Prolog's problem of
infinite looping. It saves run-time by doing primary
inferencing at compile-time. Furthermore, it is
incremental in nature. The first half of this article
translates disjunctive clauses, integrity constraints,
and database facts into Boolean equations, and develops
procedures to use mixed integer programming methods to
compute equations, and develops procedures to use mixed
integer programming methods to compute equations, and
develops procedures to use mixed integer programming
methods to compute equations, and develops procedures
to use mixed integer programming methods to
compute\par
---least models of definite deductive databases,
and\par
---minimal models and the Generalized Closed World
Assumption of disjunctive databases.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; minimal models; negation and disjunction in
deductive databases; theory",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages. {\bf F.4.1}: Theory of Computation,
MATHEMATICAL LOGIC AND FORMAL LANGUAGES, Mathematical
Logic. {\bf I.2.4}: Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Knowledge Representation Formalisms and
Methods.",
}
@Article{Guo:1996:SSI,
author = "Sha Guo and Wei Sun and Mark A. Weiss",
title = "Solving Satisfiability and Implication Problems in
Database Systems",
journal = j-TODS,
volume = "21",
number = "2",
pages = "270--293",
month = jun,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-2/p270-guo/p270-guo.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-2/p270-guo/;
http://www.acm.org/pubs/toc/Abstracts/tods/232692.html",
abstract = "Satisfiability, implication, and equivalence problems
involving conjunctive inequalities are important and
widely encountered database problems that need to be
efficiently and effectively processed. In this article
we consider two popular types of arithmetic
inequalities, ({\em X{\bf op\/}Y}) and ({\em X {\bf
op\/} C}), where $X$ and $Y$ are attributes, $C$ is a
constant of the domain or $X$, and {\bf op}[epsilon]
$<$, $ < = $, $=$, ***, $>$, $ > = $. These
inequalities are most frequently used in a database
system, inasmuch as the former type of inequality
represents a 0-join, and the latter is a selection. We
study the satisfiability and implication problems under
the integer domain and the real domain, as well as
under two different operator sets ({$<$, $ < = $, =, $
> = $, $>$} and {$<$, $ < = $, =, ***, $ > = $, $>$}).
Our results show that solutions under different domains
and/or different operator sets are quite different. Out
of these eight cases, excluding two cases that had been
shown to be NP-hard, we either report the first
necessary and sufficient conditions for these problems
as well as their efficient algorithms with complexity
analysis (for four cases), or provide an improved
algorithm (for two cases). These iff conditions and
algorithms are essential to database designers,
practitioners, and researchers. These algorithms have
been implemented and an experimental study comparing
the proposed algorithms and those previously known is
conducted. Our experiments show that the proposed
algorithms are more efficient than previously known
algorithms even for small input. The C++ code can be
obtained by an anonymous ftp from
\path=archive.fiu.edu=.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; deduction; equivalence; implication;
languages; reasoning; satisfiabilty; theory",
subject = "{\bf F.2.2}: Theory of Computation, ANALYSIS OF
ALGORITHMS AND PROBLEM COMPLEXITY, Nonnumerical
Algorithms and Problems, Complexity of proof
procedures. {\bf H.2.4}: Information Systems, DATABASE
MANAGEMENT, Systems, Query processing. {\bf I.2.3}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Deduction and Theorem Proving, Deduction. {\bf I.1.2}:
Computing Methodologies, ALGEBRAIC MANIPULATION,
Algorithms, Analysis of algorithms.",
}
@Article{Ciaccia:1996:DKB,
author = "Paolo Ciaccia and Paolo Tiberio and Pavel Zezula",
title = "Declustering of Key-Based Partitioned Signature
Files",
journal = j-TODS,
volume = "21",
number = "3",
pages = "295--338",
month = sep,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-3/p295-ciaccia/p295-ciaccia.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-3/p295-ciaccia/;
http://www.acm.org/pubs/toc/Abstracts/tods/232755.html",
abstract = "Access methods based on signature files can largely
benefit from possibilities offered by parallel
environments. To this end, an effective {\em
declustering\/} strategy that would distribute
signatures over a set of parallel independent disks has
to be combined with a synergic {\em clustering\/} which
is employed to avoid searching the whole signature file
while executing a query. This article proposes two
parallel signature file organizations, Hamming Filter
({\em HF\/}) and Hamming$^+$ Filter ($ H^+F $ ), whose
common declustering strategy is based on {\em error
correcting codes}, and where clustering is achieved by
organizing signatures into fixed-size buckets, each
containing signatures sharing the same {\em key\/}
value. {\em HF\/} allocates signatures on disks in a
static way and works well if a correct relationship
holds between the parameters of the code and the size
of the file. $ H^+F $ is a generalization of $ H F $
suitable to manage highly dynamic files. It uses a
dynamic declustering, obtained through a {\em
sequence\/} of codes, and organizes a smooth migration
of signatures between disks so that high performance
levels are retained regardless of current file size.
Theoretical analysis characterizes the best-case,
expected, and worst-case behaviors of these
organizations. Analytical results are verified by
experiments on prototype systems.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "design; error correcting codes; information retrieval;
parallel independent disks; partial match queries;
performance; performance evaluation; superimposed
coding",
subject = "{\bf E.4}: Data, CODING AND INFORMATION THEORY. {\bf
E.5}: Data, FILES, Organization/structure. {\bf H.2.2}:
Information Systems, DATABASE MANAGEMENT, Physical
Design, Access methods. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing. {\bf H.3.2}: Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Information Storage,
File organization.",
}
@Article{Dey:1996:PRM,
author = "Debabrata Dey and Sumit Sarkar",
title = "A Probabilistic Relational Model and Algebra",
journal = j-TODS,
volume = "21",
number = "3",
pages = "339--369",
month = sep,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-3/p339-dey/p339-dey.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-3/p339-dey/;
http://www.acm.org/pubs/toc/Abstracts/tods/232796.html",
abstract = "Although the relational model for databases provides a
great range of advantages over other data models, it
lacks a comprehensive way to handle incomplete and
uncertain data. Uncertainty in data values, however, is
pervasive in all real-world environments and has
received much attention in the literature. Several
methods have been proposed for incorporating uncertain
data into relational databases. However, the current
approaches have many shortcomings and have not
established an acceptable extension of the relational
model. In this paper, we propose a consistent extension
of the relational model. We present a revised
relational structure and extend the relational algebra.
The extended algebra is shown to be closed, a
consistent extension of the conventional relational
algebra, and reducible to the latter.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data incompleteness; data uncertainty; languages;
probabilistic relation; probability calculus;
relational algebra; relational model; theory",
subject = "{\bf H.2.1}: Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf F.4.3}: Theory of
Computation, MATHEMATICAL LOGIC AND FORMAL LANGUAGES,
Formal Languages, Algebraic language theory. {\bf G.3}:
Mathematics of Computing, PROBABILITY AND STATISTICS,
Statistical computing. {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Data
manipulation languages (DML). {\bf H.2.3}: Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.8}: Information Systems, DATABASE
MANAGEMENT, Database applications. {\bf I.2.3}:
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Deduction and Theorem Proving, Uncertainty, ``fuzzy,''
and probabilistic reasoning.",
}
@Article{Ghandeharizadeh:1996:HED,
author = "Shahram Ghandeharizadeh and Richard Hull and Dean
Jacobs",
title = "{Heraclitus}: Elevating Deltas to be First-Class
Citizens in a Database Programming Language",
journal = j-TODS,
volume = "21",
number = "3",
pages = "370--426",
month = sep,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-3/p370-ghandeharizadeh/p370-ghandeharizadeh.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-3/p370-ghandeharizadeh/;
http://www.acm.org/pubs/toc/Abstracts/tods/232801.html",
abstract = "Traditional database systems provide a user with the
ability to query and manipulate one database state,
namely the current database state. However, in several
emerging applications, the ability to analyze
``what-if'' scenarios in order to reason about the
impact of an update (before committing that update) is
of paramount importance. Example applications include
hypothetical database access, active database
management systems, and version management, to name a
few. The central thesis of the Heraclitus paradigm is
to provide flexible support for applications such as
these by elevating {\em deltas}, which represent
updates proposed against the current database state, to
be first-class citizens. Heraclitus[Alg,C] is a
database programming language that extends C to
incorporate the relational algebra and deltas.
Operators are provided that enable the programmer to
explicitly construct, combine, and access deltas. Most
interesting is the when operator, that supports
hypothetical access to a delta: the expression {\bf E}
when [sigma] yields the value that side effect free
expression E would have if the value of delta
expression [sigma] were applied to the current database
state. This article presents a broad overview of the
philosophy underlying the Heraclitus paradigm, and
describes the design and prototype implementation of
Heraclitus[Alg, C]. A model-independent formalism for
the Heraclitus paradigm is also presented. To
illustrate the utility of Heraclitus, the article
presents an in-depth discussion of how Heraclitus[Alg,
C] can be used to specify, and thereby implement, a
wide range of execution models for rule application in
active databases; this includes both prominent
execution models presented in the literature, and more
recent ``customized'' execution models with novel
features.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active databases; deltas; design; execution model for
rule application; hypothetical access; hypothetical
database state; languages",
subject = "{\bf H.2.3}: Information Systems, DATABASE MANAGEMENT,
Languages, Database (persistent) programming languages.
{\bf D.3.3}: Software, PROGRAMMING LANGUAGES, Language
Constructs and Features. {\bf H.2.4}: Information
Systems, DATABASE MANAGEMENT, Systems, Query
processing. {\bf H.2.m}: Information Systems, DATABASE
MANAGEMENT, Miscellaneous.",
}
@Article{Kuo:1996:MVD,
author = "Dean Kuo",
title = "Model and verification of a data manager based on
{ARIES}",
journal = j-TODS,
volume = "21",
number = "4",
pages = "427--479",
month = dec,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-4/p427-kuo/p427-kuo.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-4/p427-kuo/",
abstract = "In this article, we model and verify a data manager
whose algorithm is based on ARIES. The work uses the
I/O automata method as the formal model and the
definition of correctness is defined on the interface
between the scheduler and the data manager.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Reliability; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "ARIES; I/O automata; reliability; system failures;
theory; verification",
subject = "{\bf F.3.1} Theory of Computation, LOGICS AND MEANINGS
OF PROGRAMS, Specifying and Verifying and Reasoning
about Programs, Assertions. {\bf H.2.2} Information
Systems, DATABASE MANAGEMENT, Physical Design, Recovery
and restart. {\bf H.2.4} Information Systems, DATABASE
MANAGEMENT, Systems, Transaction processing.",
}
@Article{Litwin:1996:LSD,
author = "Witold Litwin and Marie-Anna Neimat and Donovan A.
Schneider",
title = "{LH*} --- a scalable, distributed data structure",
journal = j-TODS,
volume = "21",
number = "4",
pages = "480--525",
month = dec,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-4/p480-litwin/p480-litwin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-4/p480-litwin/",
abstract = "We present a scalable distributed data structure
called LH*. LH* generalizes Linear Hashing (LH) to
distributed RAM and disk files. An LH* file can be
created from records with primary keys, or objects with
OIDs, provided by any number of distributed and
autonomous clients. It does not require a central
directory, and grows gracefully, through splits of one
bucket at a time, to virtually any number of servers.
The number of messages per random insertion is one in
general, and three in the worst case, regardless of the
file size. The number of messages per key search is two
in general, and four in the worst case. The file
supports parallel operations, e.g., hash joins and
scans. Performing a parallel operation on a file of $M$
buckets costs at most 2 $M$ + 1 messages, and between 1
and $O$ (log 2 $M$ ) rounds of messages.\par
We first describe the basic LH* scheme where a
coordinator site manages abucket splits, and splits a
bucket every time a collision occurs. We show that the
average load factor of an LH* file is 65\%--70\%
regardless of file size, and bucket capacity. We then
enhance the scheme with load control, performed at no
additional message cost. The average load factor then
increases to 80--95\%. These values are about that of
LH, but the load factor for LH* varies more.\par
We nest define LH* schemes without a coordinator. We
show that insert and search costs are the same as for
the basic scheme. The splitting cost decreases on the
average, but becomes more variable, as cascading splits
are needed to prevent file overload. Next, we briefly
describe two variants of splitting policy, using
parallel splits and presplitting that should enhance
performance for high-performance applications.\par
All together, we show that LH* files can efficiently
scale to files that are orders of magnitude larger in
size than single-site files. LH* files that reside in
main memory may also be much faster than single-site
disk files. Finally, LH* files can be more efficient
than any distributed file with a centralized directory,
or a static parallel or distributed hash file.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; data structures; design; distributed
access methods; extensible hashing; linear hashing;
performance",
subject = "{\bf E.2} Data, DATA STORAGE REPRESENTATIONS,
Hash-table representations. {\bf E.1} Data, DATA
STRUCTURES. {\bf H.2.1} Information Systems, DATABASE
MANAGEMENT, Logical Design",
}
@Article{Raschid:1996:SUR,
author = "Louiqa Raschid and Jorge Lobo",
title = "Semantics for update rule programs and implementation
in a relational database management system",
journal = j-TODS,
volume = "21",
number = "4",
pages = "526--572",
month = dec,
year = "1996",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1996-21-4/p526-raschid/p526-raschid.pdf;
http://www.acm.org/pubs/citations/journals/tods/1996-21-4/p526-raschid/",
abstract = "In this paper, we present our research on defining a
correct semantics for a class of update rule (UR)
programs, and discuss implementing these programs in a
DBMS environment. Update rules execute by updating
relations in a database which may cause the further
execution of rules. A correct semantics must guarantee
that the execution of the rules will terminate and that
it will produce a minimal updated database. The class
of UR programs is syntactically identified, based upon
a concept that is similar to stratification. We extend
that strict definition of stratification and allow a
relaxed criterion for partitioning of the rules in the
UR program. This relaxation allows a limited degree of
nondeterminism in rule execution. We define an
execution semantics based upon a monotonic fixpoint
operator TUR, resulting in a set of fixpoints for UR.
The monotonicity of the operator is maintained by
explicitly representing the effect of asserting and
retracting tuples in the database. A declarative
semantics for the update rule program is obtained by
associating a normal logic program UR to represent the
UR program. We use the stable model semantics which
characterize a normal logic program by a set of minimal
models which are called stable models. We show the
equivalence between the set of fixpoints for UR and the
set of stable models for UR. We briefly discuss
implementing the fixpoint semantics of the UR program
in a DBMS environment. Relations that can be updated by
the rules are {\em updatable\/} relations and they are
extended with two flags. An update rule is represented
by a database query, which queries the updatable
relations as well as database relations, i.e., those
relations which are not update by rules. We describe an
algorithm to process the queries and compute a fixpoint
in the DBMS environment and obtain a final database.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Experimentation; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "constant maintenance; deductive database; fixpoint
semantics; rule-based systems; stable model semantics;
update rules",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems. {\bf F.4.1} Theory of Computation,
MATHEMATICAL LOGIC AND FORMAL LANGUAGES, Mathematical
Logic, Model theory. {\bf H.2.3} Information Systems,
DATABASE MANAGEMENT, Languages, Data description
languages (DDL). {\bf I.2.4} Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Knowledge Representation
Formalisms and Methods, Predicate logic. {\bf I.2.4}
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Knowledge Representation Formalisms and Methods,
Representations (procedural and rule-based). {\bf
H.2.7} Information Systems, DATABASE MANAGEMENT,
Database Administration",
}
@Article{Keen:1997:EEL,
author = "John S. Keen and William J. Dally",
title = "Extended ephemeral logging: log storage management for
applications with long lived transactions",
journal = j-TODS,
volume = "22",
number = "1",
pages = "1--42",
month = mar,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-1/p1-keen/p1-keen.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-1/p1-keen/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; disk management; logging; long
transactions; OLTP; performance; reliability",
subject = "{\bf H.2.7} Information Systems, DATABASE MANAGEMENT,
Database Administration, Logging and recovery. {\bf
H.2.2} Information Systems, DATABASE MANAGEMENT,
Physical Design, Recovery and restart. {\bf H.2.4}
Information Systems, DATABASE MANAGEMENT, Systems,
Transaction processing",
}
@Article{Galindo-Legaria:1997:OSR,
author = "C{\'e}sar Galindo-Legaria and Arnon Rosenthal",
title = "Outerjoin simplification and reordering for query
optimization",
journal = j-TODS,
volume = "22",
number = "1",
pages = "43--74",
month = mar,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-1/p43-galindo-legaria/p43-galindo-legaria.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-1/p43-galindo-legaria/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; outerjoins; query optimization; query
reordering; theory; verification",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Query processing. {\bf G.2.2} Mathematics of
Computing, DISCRETE MATHEMATICS, Graph Theory, Graph
algorithms",
}
@Article{Peters:1997:AMD,
author = "Randel J. Peters and M. Tamer {\"O}zsu",
title = "An axiomatic model of dynamic schema evolution in
objectbase systems",
journal = j-TODS,
volume = "22",
number = "1",
pages = "75--114",
month = mar,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-1/p75-peters/p75-peters.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-1/p75-peters/",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Management; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; dynamic schema evolution;
management; object database management systems;
theory",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.2.1} Information Systems,
DATABASE MANAGEMENT, Logical Design, Schema and
subschema",
}
@Article{Wang:1997:LDT,
author = "X. Sean Wang and Claudio Bettini and Alexander Brodsky
and Sushil Jajodia",
title = "Logical design for temporal databases with multiple
granularities",
journal = j-TODS,
volume = "22",
number = "2",
pages = "115--170",
month = jun,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-2/p115-wang/p115-wang.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-2/p115-wang/",
abstract = "The purpose of good database logical design is to
eliminate data redundancy and insertion and deletion
anomalies. In order to achieve this objective for
temporal databases, the notions of {\em temporal
types}, which formalize time granularities, and {\em
temporal functional dependencies\/} (TFDs) are
introduced. A temporal type is a monotonic mapping from
ticks of time (represented by positive integers) to
time sets (represented by subsets of reals) and is used
to capture various standard and user-defined calendars.
A TFD is a proper extension of the traditional
functional dependency and takes the form $ X**Y $
meaning that there is a unique value for $Y$ during one
tick of the temporal type [mu] for one particular $X$
value. An axiomatization for TFDs is given. Because a
finite set TFDs usually implies an infinite number of
TFDs, we introduce the notion of and give an
axiomatization for a {\em finite closure\/} to
effectively capture a finite set of implied TFDs that
are essential of the logical design. Temporal
normalization procedures with respect to TFDs are
given. Specifically, temporal Boyce-Codd normal form
(TBCNF) that avoids all data redundancies due to TFDs,
and temporal third normal form (T3NF) that allows
dependency preservation, are defined. Both normal forms
are proper extensions of their traditional
counterparts, BCNF and 3NF. Decomposition algorithms
are presented that give lossless TBCNF decompositions
and lossless, dependency-preserving, T3NF
decompositions.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; Boyce-Codd normal form; design;
granularity; normalization; temporal databases;
temporal modules; temporal relations; theory; third
normal form",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design, Normal forms. {\bf H.2.4} Information
Systems, DATABASE MANAGEMENT, Systems",
}
@Article{Clifford:1997:SND,
author = "James Clifford and Curtis Dyreson and Tom{\'a}s
Isakowitz and Christian S. Jensen and Richard T.
Snodgrass",
title = "On the semantics of ``now'' in databases",
journal = j-TODS,
volume = "22",
number = "2",
pages = "171--214",
month = jun,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-2/p171-clifford/p171-clifford.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-2/p171-clifford/",
abstract = "Although ``{\em now\/}'' is expressed in SQL and
CURRENT\_TIMESTAMP within queries, this value cannot be
stored in the database. However, this notion of an
ever-increasing current-time value has been reflected
in some temporal data models by inclusion of
database-resident variables, such as ``{\em now\/}''
``{\em until-changed},'' ``**,'' ``@,'' and ``-''. Time
variables are very desirable, but their used also leads
to a new type of database, consisting of tuples with
variables, termed a {\em variable database}.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "indeterminacy; languages; Now; now-relative value;
performance; SQL; temporal query language; TSQL2",
subject = "{\bf H.2.3} Information Systems, DATABASE MANAGEMENT,
Languages, SQL. {\bf H.2.3} Information Systems,
DATABASE MANAGEMENT, Languages, Data description
languages (DDL). {\bf H.2.4} Information Systems,
DATABASE MANAGEMENT, Systems, Query processing",
}
@Article{Ammann:1997:AFM,
author = "Paul Ammann and Sushil Jajodia and Indrakshi Ray",
title = "Applying formal methods to semantic-based
decomposition of transactions",
journal = j-TODS,
volume = "22",
number = "2",
pages = "215--254",
month = jun,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-2/p215-ammann/p215-ammann.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-2/p215-ammann/",
abstract = "In some database applications the traditional approach
of serializability, in which transactions appear to
execute atomically and in isolation on a consistent
database state, fails to satisfy performance
requirements. Although many researchers have
investigated the process of decomposing transactions
into steps to increase concurrency, such research
typically focuses on providing algorithms necessary to
implement a decomposition supplied by the database
application developer and pays relatively little
attention to what constitutes a desirable decomposition
or how the developer should obtain one. We focus on the
decomposition itself. A decomposition generates proof
obligations whose discharge ensures desirable
properties with respect to the original collection of
transactions. We introduce the notion of semantic
histories to formulate and prove the necessary
properties, and the notion of successor sets to
describe efficiently the correct interleavings of
steps. The successor set constraints use information
about conflicts between steps so as to take full
advantage of conflict serializability at the level of
steps. We propose a mechanism based on two-phase
locking to generate correct stepwise serializable
histories.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "concurrency control; database management systems;
theory; transaction processing; verification",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf D.2.1} Software,
SOFTWARE ENGINEERING, Requirements/Specifications,
Methodologies. {\bf F.3.1} Theory of Computation,
LOGICS AND MEANINGS OF PROGRAMS, Specifying and
Verifying and Reasoning about Programs, Invariants.
{\bf F.3.1} Theory of Computation, LOGICS AND MEANINGS
OF PROGRAMS, Specifying and Verifying and Reasoning
about Programs, Pre- and post-conditions. {\bf F.3.1}
Theory of Computation, LOGICS AND MEANINGS OF PROGRAMS,
Specifying and Verifying and Reasoning about Programs,
Specification techniques",
}
@Article{Wolfson:1997:ADR,
author = "Ouri Wolfson and Sushil Jajodia and Yixiu Huang",
title = "An adaptive data replication algorithm",
journal = j-TODS,
volume = "22",
number = "2",
pages = "255--314",
month = jun,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-2/p255-wolfson/p255-wolfson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-2/p255-wolfson/",
abstract = "This article addresses the performance of distributed
database systems. Specifically, we present an algorithm
for dynamic replication of an object in distributed
systems. The algorithm is adaptive in the sense that it
changes the replication scheme of the object (i.e., the
set of processors at which the object is replicated) as
changes occur in the read-write pattern of the object
(i.e., the number of reads and writes issued by each
processor). The algorithm continuously moves the
replication scheme towards an optimal one. We show that
the algorithm can be combined with the concurrency
control and recovery mechanisms of ta distributed
database management system. The performance of the
algorithm is analyzed theoretically and experimentally.
On the way we provide a lower bound on the performance
of any dynamic replication algorithm.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; computer networks; dynamic data
allocation; file allocation; performance; replicated
data",
subject = "{\bf C.2.4} Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf H.2.4} Information Systems,
DATABASE MANAGEMENT, Systems, Distributed systems. {\bf
H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing. {\bf C.2.4} Computer
Systems Organization, COMPUTER-COMMUNICATION NETWORKS,
Distributed Systems, Distributed applications. {\bf
C.4} Computer Systems Organization, PERFORMANCE OF
SYSTEMS, Design studies. {\bf C.4} Computer Systems
Organization, PERFORMANCE OF SYSTEMS, Measurement
techniques. {\bf C.4} Computer Systems Organization,
PERFORMANCE OF SYSTEMS, Modeling techniques. {\bf C.4}
Computer Systems Organization, PERFORMANCE OF SYSTEMS,
Reliability, availability, and serviceability",
}
@Article{Franklin:1997:TCS,
author = "Michael J. Franklin and Michael J. Carey and Miron
Livny",
title = "Transactional client-server cache consistency:
alternatives and performance",
journal = j-TODS,
volume = "22",
number = "3",
pages = "315--363",
month = sep,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-3/p315-franklin/p315-franklin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-3/p315-franklin/;
http://www.acm.org:80/pubs/citations/journals/tods/1997-22-3/p315-franklin/",
abstract = "Client-server database systems based on a data
shipping model can exploit client memory resources by
caching copies of data items across transaction
boundaries. Caching reduces the need to obtain data
from servers or other sites on the network. In order to
ensure that such caching does not result in the
violation of transaction semantics, a transactional
cache consistency maintenance algorithm is required.
Many such algorithms have been proposed in the
literature and, as all provide the same functionality,
performance is a primary concern in choosing among
them. In this article we present a taxonomy that
describes the design space for transactional cache
consistency maintenance algorithms and show how
proposed algorithms relate to one another. We then
investigate the performance of six of these algorithms,
and use these results to examine the tradeoffs inherent
in the design choices identified in the taxonomy. The
results show that the interactions among dimensions of
the design space impact performance in many ways, and
that classifications of algorithms as simply
``pessimistic'' or ``optimistic'' do not accurately
characterize the similarities and differences among the
many possible cache consistency algorithms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; design; performance",
subject = "{\bf C.2.4} Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases. {\bf C.4} Computer Systems
Organization, PERFORMANCE OF SYSTEMS. {\bf D.4.8}
Software, OPERATING SYSTEMS, Performance. {\bf H.2.4}
Information Systems, DATABASE MANAGEMENT, Systems,
Concurrency.",
}
@Article{Eiter:1997:DD,
author = "Thomas Eiter and Georg Gottlob and Heikki Mannila",
title = "Disjunctive {Datalog}",
journal = j-TODS,
volume = "22",
number = "3",
pages = "364--418",
month = sep,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-3/p364-eiter/p364-eiter.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-3/p364-eiter/;
http://www.acm.org:80/pubs/citations/journals/tods/1997-22-3/p364-eiter/",
abstract = "We consider disjunctive Datalog, a powerful database
query language based on disjunctive logic programming.
Briefly, disjunctive Datalog is a variant of Datalog
where disjunctions may appear in the rule heads;
advanced versions also allow for negation in the bodies
which can be handled according to a semantics for
negation in disjunctive logic programming. In
particular, we investigate three different semantics
for disjunctive Datalog: the minimal model semantics
the perfect model semantics, and the stable model
semantics. For each of these semantics, the expressive
power and complexity are studied. We show that the
possibility variants of these semantics express the
same set of queries. In fact, they precisely capture
the complexity class {\em P2}. Thus, unless the
Polynomial Hierarchy collapses, disjunctive Datalog is
more expressive that normal logic programming with
negation. These results are not only of theoretical
interest; we demonstrate that problems relevant in
practice such as computing the optimal tour value in
the Traveling Salesman Problem and eigenvector
computations can be handled in disjunctive Datalog, but
not Datalog with negation (unless the Polynomial
Hierarchy collapses). In addition, we study modularity
properties of disjunctive Datalog and investigate
syntactic restrictions of the formalisms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "languages; theory",
subject = "{\bf H.2.3} Information Systems, DATABASE MANAGEMENT,
Languages, Datalog. {\bf H.2.3} Information Systems,
DATABASE MANAGEMENT, Languages, Query languages. {\bf
D.1.6} Software, PROGRAMMING TECHNIQUES, Logic
Programming. {\bf I.2.3} Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Deduction and Theorem Proving.
{\bf I.2.4} Computing Methodologies, ARTIFICIAL
INTELLIGENCE, Knowledge Representation Formalisms and
Methods. {\bf F.2.2} Theory of Computation, ANALYSIS OF
ALGORITHMS AND PROBLEM COMPLEXITY, Nonnumerical
Algorithms and Problems. {\bf F.4.1} Theory of
Computation, MATHEMATICAL LOGIC AND FORMAL LANGUAGES,
Mathematical Logic, Logic and constraint programming.",
}
@Article{Lakshmanan:1997:PFP,
author = "Laks V. S. Lakshmanan and Nicola Leone and Robert Ross
and V. S. Subrahmanian",
title = "{ProbView}: a flexible probabilistic database system",
journal = j-TODS,
volume = "22",
number = "3",
pages = "419--469",
month = sep,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-3/p419-lakshmanan/p419-lakshmanan.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-3/p419-lakshmanan/;
http://www.acm.org:80/pubs/citations/journals/tods/1997-22-3/p419-lakshmanan/",
abstract = "Probability theory is mathematically the best
understood paradigm for modeling and manipulating
uncertain information. Probabilities of complex events
can be computed from those of basic events on which
they depend, using any of a number of strategies. Which
strategy is appropriate depends very much on the known
interdependencies among the events involved. Previous
work on probabilistic databases has assumed a {\em
fixed\/} and {\em restrictive\/} combination strategy
(e.g., assuming all events are pairwise independent).
In this article, we characterize, using postulates,
whole classes of strategies for conjunction,
disjunction, and negation, meaningful from the
viewpoint of probability theory. (1) We propose a
probabilistic relational data model and a {\em
generic\/}probabilistic relational algebra that neatly
captures {\em various strategies\/} satisfying the
postulates, within a {\em single unified framework.}
(2) We show that as long as the chosen strategies can
be computed in polynomial time, queries in the positive
fragment of the probabilistic relational algebra have
essentially the same data complexity as classical
relational algebra. (3) We establish various
containments and equivalences between algebraic
expressions, similar in spirit to those in classical
algebra. (4) We develop algorithms for maintaining
materialized probabilistic views. (5) Based on these
ideas, we have developed a prototype probabilistic
database system called ProbView on top of Dbase V.0. We
validate our complexity results with experiments and
show that rewriting certain types of queries to other
equivalent forms often yields substantial savings.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; languages; performance; probabilistic
databases; theory; view maintenance",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems. {\bf H.2.3} Information Systems, DATABASE
MANAGEMENT, Languages. {\bf I.2.3} Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Deduction and
Theorem Proving.",
}
@Article{Storey:1997:DDC,
author = "Veda C. Storey and Roger H. L. Chiang and Debabrata
Dey and Robert C. Goldstein and Shankar Sundaresan",
title = "Database design with common sense business reasoning
and learning",
journal = j-TODS,
volume = "22",
number = "4",
pages = "471--512",
month = dec,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-4/p471-storey/p471-storey.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-4/p471-storey/;
http://www.acm.org:80/pubs/citations/journals/tods/1997-22-4/p471-storey/",
abstract = "Automated database design systems embody knowledge
about the database design process. However, their lack
of knowledge about the domains for which databases are
being developed significantly limits their usefulness.
A methodology for acquiring and using general world
knowledge about business for database design has been
developed and implemented in a system called the Common
Sense Business Reasoner, which acquires facts about
application domains and organizes them into a
hierarchical, context-dependent knowledge base. This
knowledge is used to make intelligent suggestions to a
user about the entities, attributes, and relationships
to include in a database design. A distance function
approach is employed for integrating specific facts,
obtained from individual design sessions, into the
knowledge base (learning) and for applying the
knowledge to subsequent design problems (reasoning).",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "common sense business reasoner; common sense learning;
common sense reasoning; database design; design;
entity-relationship model; theory",
subject = "{\bf D.2.1} Software, SOFTWARE ENGINEERING,
Requirements/Specifications. {\bf H.2.1} Information
Systems, DATABASE MANAGEMENT, Logical Design. {\bf
H.2.8} Information Systems, DATABASE MANAGEMENT,
Database Applications. {\bf I.2.4} Computing
Methodologies, ARTIFICIAL INTELLIGENCE, Knowledge
Representation Formalisms and Methods. {\bf I.2.6}
Computing Methodologies, ARTIFICIAL INTELLIGENCE,
Learning. {\bf I.2.1} Computing Methodologies,
ARTIFICIAL INTELLIGENCE, Applications and Expert
Systems.",
}
@Article{Tari:1997:ONF,
author = "Zahir Tari and John Stokes and Stefano Spaccapietra",
title = "Object normal forms and dependency constraints for
object-oriented schemata",
journal = j-TODS,
volume = "22",
number = "4",
pages = "513--569",
month = dec,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-4/p513-tari/p513-tari.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-4/p513-tari/",
abstract = "We address the development of a normalization theory
for object-oriented data models that have common
features to support objects. We first provide an
extension of functional dependencies to cope with the
richer semantics of relationships between objects,
called {\em path dependency}, {\em local dependency},
and {\em global dependency\/} constraints. Using these
dependency constraints, we provide normal forms for
object-oriented data models based on the notions of
{\em user interpretation\/} (user-specified dependency
constraints) and {\em object model}. In contrast to
conventional data models in which a normalized object
has a unique interpretation, in object-oriented data
models, an object may have many multiple
interpretations that form the model for that object. An
object will then be in a normal form if and only if the
user's interpretation is derivable from the model of
the object. Our normalization process is by nature
iterative, in which objects are restructured until
their models reflect the user's interpretation.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data model; functional and multivalued dependencies;
normal forms; object-oriented paradigm",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Normal forms}; Information
Systems --- Database Management --- Systems (H.2.4)",
}
@Article{Zaharioudakis:1997:AFG,
author = "Markos Zaharioudakis and Michael J. Carey and Michael
J. Franklin",
title = "Adaptive, fine-grained sharing in a client-server
{OODBMS}: a callback-based approach",
journal = j-TODS,
volume = "22",
number = "4",
pages = "570--627",
month = dec,
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1997-22-4/p570-zaharioudakis/p570-zaharioudakis.pdf;
http://www.acm.org/pubs/citations/journals/tods/1997-22-4/p570-zaharioudakis/",
abstract = "For reasons of simplicity and communication
efficiency, a number of existing object-oriented
database management systems are based on page server
architectures; data pages are their minimum unit of
transfer and client caching. Despite their efficiency,
page servers are often criticized as being too
restrictive when it comes to concurrency, as existing
systems use pages as the minimum locking unit as well.
In this paper we show how to support object-level
locking in a page-server context. Several approaches
are described, including an adaptive granularity
approach that uses page-level locking for most pages
but switches to object-level locking when finer-grained
sharing is demanded. Each of the approaches is based on
extending the idea of callback locking. We study the
performance of these approaches, comparing them to both
a pure page server and a pure object server. For the
range of workload that we have examined, our results
indicate that the adaptive page server provides very
good performance, usually outperforming the pure page
server and the other page-server variants as well. In
addition, the adaptive page server is often preferable
to the pure object server; our results provides insight
into when each approach is likely to perform better.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cache coherency; cache consistency; client-server
database; design; fine-grained sharing; object-oriented
databases; performance; performance analysis",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency; {\bf H.3.4} Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Systems and
Software, Distributed systems; {\bf H.2.4} Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing",
}
@Article{Anonymous:1997:AI,
author = "Anonymous",
title = "1997 Author Index",
journal = j-TODS,
volume = "22",
number = "4",
pages = "628--??",
month = "????",
year = "1997",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 7 10:36:24 MST 1998",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dyreson:1998:SVT,
author = "Curtis E. Dyreson and Richard T. Snodgrass",
title = "Supporting valid-time indeterminacy",
journal = j-TODS,
volume = "23",
number = "1",
pages = "1--57",
month = mar,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-1/p1-dyreson/p1-dyreson.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-1/p1-dyreson/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-1/p1-dyreson/",
abstract = "In {\em valid-time indeterminacy\/} it is known that
an event stored in a database did in fact occur, but it
is not known exactly {\em when}. In this paper we
extend the SQL data model and query language to support
valid-time indeterminacy. We represent the occurrence
time of an event with a set of possible instants,
delimiting when the event might have occurred, and a
probability distribution over that set. We also
describe query language constructs to retrieve
information in the presence of indeterminacy. These
constructs enable users to specify their {\em
credibility\/} in the underlying data and their {\em
plausibility\/} in the relationships among that data. A
denotational semantics for SQL's select statement with
optional credibility and plausibility constructs is
given. We show that this semantics is {\em reliable},
in that it never produces incorrect information, is
{\em maximal}, in that if it were extended to be more
informative, the results may not be reliable, and {\em
reduces\/} to the previous semantics when there is no
indeterminacy. Although the extended data model and
query language provide needed modeling capabilities,
these extensions appear initially to carry a
significant execution cost. A contribution of this
paper is to demonstrate that our approach is useful and
practical. An efficient representation of valid-time
indeterminacy and efficient query processing algorithms
are provided. The cost of support for indeterminacy is
empirically measured, and is shown to be modest.
Finally, we show that the approach is general, by
applying it to the temporal query language constructs
being proposed for SQL3.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; incomplete information; indeterminacy;
languages; probabilistic information; SQL; temporal
database; TSQL2; valid-time database",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design, Data models. {\bf H.2.3} Information
Systems, DATABASE MANAGEMENT, Languages, Query
languages. {\bf H.2.4} Information Systems, DATABASE
MANAGEMENT, Systems, Query processing.",
}
@Article{Revesz:1998:SQL,
author = "Peter Z. Revesz",
title = "Safe query languages for constraint databases",
journal = j-TODS,
volume = "23",
number = "1",
pages = "58--99",
month = mar,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-1/p58-revesz/p58-revesz.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-1/p58-revesz/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-1/p58-revesz/",
abstract = "In the database framework of Kanellakis et al. [1990]
it was argued that constraint query languages should
take constraint databases as input and give other
constraint databases that use the same type of atomic
constraints as output. This closed-form requirement has
been difficult to realize in constraint query languages
that contain the negation symbol. This paper describes
a general approach to restricting constraint query
languages with negation to safe subsets that contain
only programs that are evaluable in closed-form on any
valid constraint database input.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; languages; theory; verification",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.2.3} Information Systems,
DATABASE MANAGEMENT, Languages, Datalog.",
}
@Article{Stolboushkin:1998:SSD,
author = "Alexei P. Stolboushkin and Michael A. Taitslin",
title = "Safe stratified datalog with integer order does not
have syntax",
journal = j-TODS,
volume = "23",
number = "1",
pages = "100--109",
month = mar,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-1/p100-stolboushkin/p100-stolboushkin.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-1/p100-stolboushkin/",
abstract = "Stratified Datalog with integer (gap)-order (or {\em
Datalog***\/}) is considered. A {\em
Datalog***\/}-program is said to be safe if its
bottom-up processing terminates on all valid inputs. We
prove that safe {\em Datalog***\/}-programs do not have
effective syntax in the sense that there is no
recursively enumerable set $S$ of safe {\em
Datalog***\/}-programs such that every safe {\em
Datalog***\/}-program is equivalent to a program in
$S$.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "languages; theory; verification",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design; {\bf H.2.3} Information Systems,
DATABASE MANAGEMENT, Languages.",
}
@Article{Anonymous:1998:TR,
author = "Anonymous",
title = "{TODS} Referees",
journal = j-TODS,
volume = "23",
number = "1",
pages = "110--111",
month = mar,
year = "1998",
bibdate = "Mon Jan 18 18:22:17 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Anonymous:1998:C,
author = "Anonymous",
title = "Corrigenda",
journal = j-TODS,
volume = "23",
number = "1",
pages = "112--112",
month = mar,
year = "1998",
bibdate = "Mon Jan 18 18:22:17 1999",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hellerstein:1998:OTQ,
author = "Joseph M. Hellerstein",
title = "Optimization techniques for queries with expensive
methods",
journal = j-TODS,
volume = "23",
number = "2",
pages = "113--157",
month = jun,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-2/p113-hellerstein/p113-hellerstein.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-2/p113-hellerstein/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-2/p113-hellerstein/",
abstract = "Object-relational database management systems allow
knowledgeable users to define new data types as well as
new methods (operators) for the types. This flexibility
produces an attendant complexity, which must be handled
in new ways for an object-relational database
management system to be efficient. In this article we
study techniques for optimizing queries that contain
time-consuming methods. The focus of traditional query
optimizers has been on the choice of join methods and
orders; selections have been handled by ``pushdown''
rules. These rules apply selections in an arbitrary
order before as many joins as possible, using th e
assumption that selection takes no time. However, users
of object-relational systems can embed complex methods
in selections. Thus selections may take significant
amounts of time, and the query optimization model must
be enhanced. In this article we carefully define a
query cost framework that incorporates both selectivity
and cost estimates for selections. We develop an
algorithm called Predicate Migration, and prove that it
produces optimal plans for queries with expensive
methods. We then describe our implementation of
Predicate Migration in the commercial object-relational
database management system Illustra, and discuss
practical issues that affect our earlier assumptions.
We compare Predicate Migration to a variety of simpler
optimization techniques, and demonstrate that Predicate
Migration is the best general solution to date. The
alternative techniques we present may be useful for
constrained workloads.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; expensive methods; extensibility;
object-relational databases; performance; predicate
migration; predicate placement; query optimization;
theory",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Query processing.",
}
@Article{Liu:1998:MAP,
author = "Xiangning Liu and Abdelsalam Helal and Weimin Du",
title = "Multiview access protocols for large-scale
replication",
journal = j-TODS,
volume = "23",
number = "2",
pages = "158--198",
month = jun,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-2/p158-liu/p158-liu.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-2/p158-liu/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-2/p158-liu/",
abstract = "The article proposes a scalable protocol for
replication management in large-scale replicated
systems. The protocol organizes sites and data replicas
into a tree-structured, hierarchical cluster
architecture. The basic idea of the protocol is to
accomplish the complex task of updating replicated data
with a very large number of replicas by a set of
related but independently committed transactions. Each
transaction is responsible for updating replicas in
exactly one cluster and invoking additional
transactions for member clusters. Primary copies (one
from each cluster) are updated by a cross-cluster
transaction. Then each cluster is independently updated
by a separate transaction. This decoupled update
propagation process results in possible multiple views
of replicated data in a cluster. Compared to other
replicated data management protocols, the proposed
protocol has several unique advantages. First, thanks
to a smaller number of replicas each transaction needs
to atomically update in a cluster, the protocol
significantly reduces the transaction abort rate, which
tends to soar in large transactional systems. Second,
the protocol improves user-level transaction response
time as top-level update transactions are allowed to
commit before all replicas have been updated. Third,
read-only queries have the flexibility to see database
views of different degrees of consistency and data
currency. This ranges from global, most up to date, and
consistent views, to local, consistent, but potentially
old views, to local, nearest to users but potentially
inconsistent views. Fourth, the protocol maintains its
scalability by allowing dynamic system reconfiguration
as it grows by splitting a cluster into two or more
smaller ones. Fifth, autonomy of the clusters is
preserved as no specific protocol is required to update
replicas within the same cluster. Clusters are,
therefore, free to use any valid replication or
concurrency control protocols.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Management;
Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; data replication; design; experimentation;
large-scale systems; management; measurement; multiview
access; performance",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Distributed databases. {\bf H.2.4} Information
Systems, DATABASE MANAGEMENT, Systems, Transaction
processing. {\bf C.2.4} Computer Systems Organization,
COMPUTER-COMMUNICATION NETWORKS, Distributed Systems,
Distributed databases.",
}
@Article{Mehrotra:1998:ECM,
author = "Sharad Mehrotra and Rajeev Rastogi and Henry F. Korth
and Abraham Silberschatz",
title = "Ensuring consistency in multidatabases by preserving
two-level serializability",
journal = j-TODS,
volume = "23",
number = "2",
pages = "199--230",
month = jun,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-2/p199-mehrotra/p199-mehrotra.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-2/p199-mehrotra/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-2/p199-mehrotra/",
abstract = "The concept of serializability has been the
traditionally accepted correctness criterion in
database systems. However in multidatabase systems
(MDBSs), ensuring global serializability is a difficult
task. The difficulty arises due to the {\em
heterogeneity\/} of the concurrency control protocols
used by the participating local database management
systems (DBMSs), and the desire to preserve the {\em
autonomy\/} of the local DBMSs. In general, solutions
to the global serializability problem result in
executions with a low degree of concurrency. The
alternative, relaxed serializability, may result in
data inconsistency.\par
In this article, we introduce a systematic approach to
relaxing the serializability requirement in MDBS
environments. Our approach exploits the structure of
the integrity constraints and the nature of transaction
programs to ensure consistency without requiring
executions to be serializable. We develop a simple yet
powerful classification of MDBSs based on the nature of
integrity constraints and transaction programs. For
each of the identified models we show how consistency
can be preserved by ensuring that executions are {\em
two-level serializable\/} (2LSR). 2LSR is a correctness
criterion for MDBS environments weaker than
serializability. What makes our approach interesting is
that unlike global serializability, ensuring 2LSR in
MDBS environments is relatively simple and protocols to
ensure 2LSR permit a high degree of concurrency.
Furthermore, we believe the range of models we consider
cover many practical MDBS environments to which the
results of this article can be applied to preserve
database consistency.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Management; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "beyond serializability; concurrency control; database
consistency; management; multidatabases; theory",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Concurrency. {\bf H.2.4} Information Systems,
DATABASE MANAGEMENT, Systems, Distributed databases.
{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Transaction processing.",
}
@Article{Bertino:1998:ACM,
author = "Elisa Bertino and Claudio Bettini and Elena Ferrari
and Pierangela Samarati",
title = "An access control model supporting periodicity
constraints and temporal reasoning",
journal = j-TODS,
volume = "23",
number = "3",
pages = "231--285",
month = sep,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1998-23-3/p231-bertino/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-3/p231-bertino/",
abstract = "Access control models, such as the ones supported by
commercial DBMSs, are not yet able to fully meet many
application needs. An important requirement derives
from the temporal dimension that permissions have in
many real-world situations. Permissions are often
limited in time or may hold only for specific periods
of time. In this article, we present an access control
model in which periodic temporal intervals are
associated with authorizations. An authorization is
automatically granted in the specified intervals and
revoked when such intervals expire. Deductive temporal
rules with periodicity and order constraints are
provided to derive new authorizations based on the
presence or absence of other authorizations in specific
periods of time. We provide a solution to the problem
of ensuring the uniqueness of the global set of valid
authorizations derivable at each instant, and we
propose an algorithm to compute this set. Moreover, we
address issues related to the efficiency of access
control by adopting a materialization approach. The
resulting model provides a high degree of flexibility
and supports the specification of several protection
requirements that cannot be expressed in traditional
access control models.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "access control; periodic authorization; security;
temporal constraints; time management",
subject = "{\bf H.2.7} Information Systems, DATABASE MANAGEMENT,
Database Administration, Security, integrity, and
protection.",
}
@Article{Castano:1998:CSA,
author = "S. Castano and V. {De Antonellis} and M. G. Fugini and
B. Pernici",
title = "Conceptual schema analysis: techniques and
applications",
journal = j-TODS,
volume = "23",
number = "3",
pages = "286--333",
month = sep,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-3/p286-castano/p286-castano.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-3/p286-castano/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-3/p286-castano/",
abstract = "The problem of analyzing and classifying conceptual
schemas is becoming increasingly important due to the
availability of a large number of schemas related to
existing applications. The purposes of schema analysis
and classification activities can be different: to
extract information on intensional properties of legacy
systems in order to restructure or migrate to new
architectures; to build libraries of reference
conceptual components to be used in building new
applications in a given domain; and to identify
information flows and possible replication of data in
an organization. This article proposes a set of
techniques for schema analysis and classification to be
used separately or in combination. The techniques allow
the analyst to derive significant properties from
schemas, with human intervention limited as far as
possible. In particular, techniques for associating
descriptors with schemas, for abstracting reference
conceptual schemas based on schema clustering, and for
determining schema similarity are presented. A
methodology for systematic schema analysis is
illustrated, with the purpose of identifying and
abstracting into reference components the similar and
potentially reusable parts of a set of schemas.
Experiences deriving from the application of the
proposed techniques and methodology on a large set of
Entity-Relationship conceptual schemas of information
systems in the Italian Public Administration domain are
described",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Documentation; Management",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual modeling; design; documentation;
management; reference components; schema
classification; schema similarity",
subject = "{\bf H.2.1} Information Systems, DATABASE MANAGEMENT,
Logical Design. {\bf H.3.1} Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Content Analysis and
Indexing.",
}
@Article{Formica:1998:EMC,
author = "A. Formica and H. D. Groger and M. Missikoff",
title = "An efficient method for checking object-oriented
database schema correctness",
journal = j-TODS,
volume = "23",
number = "3",
pages = "334--369",
month = sep,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-3/p334-formica/p334-formica.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-3/p334-formica/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-3/p334-formica/",
abstract = "Inheritance is introduced in object-oriented systems
to enhance code reuse and create more compact and
readable software. Powerful object models adopt
multiple inheritance, allowing a type (or class)
definition to inherit from more than one supertype.
Unfortunately, in applying this powerful modeling
mechanism, inheritance conflicts may be generated,
which arise when the same property or operation is
defined in more than one supertype. Inheritance
conflicts identification and resolution is the key
issue of this article. In strongly typed
object-oriented systems the resolution of inheritance
conflicts depends on the compatibility of the types of
the conflicting definitions. In case of incompatible
types, a contradiction arises. This article focuses on
object-oriented databases (ODBs), providing a method
aimed at supporting the designer in the construction of
correct ODB schemas. The first necessary condition for
schema correctness is the absence of contradictions. A
second cause of schema incorrectness is due to the
presence of structurally recursive types that, when
defined within certain hierarchical patterns, cause the
nontermination of the inheritance process. In the
article, after the formal definition of a correct
schema, two graph-theoretic methods aimed at verifying
ODB schema correctness are analyzed. Although the first
method is intuitive but inefficient, the second allows
schema correctness to be checked in polynomial time, in
the size of the schema. The results of this study are
included in the implementation of Mosaico, an
environment for ODB application design.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Theory; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "databases; design; graph theory; inheritance
conflicts; inheritance process; languages;
object-oriented database schemas; recursive types;
theory; verification",
subject = "{\bf H.2.4} Information Systems, DATABASE MANAGEMENT,
Systems, Object-oriented databases. {\bf D.3.3}
Software, PROGRAMMING LANGUAGES, Language Constructs
and Features, Data types and structures. {\bf F.3.1}
Theory of Computation, LOGICS AND MEANINGS OF PROGRAMS,
Specifying and Verifying and Reasoning about Programs,
Mechanical verification. {\bf H.2.3} Information
Systems, DATABASE MANAGEMENT, Languages, Data
description languages (DDL). {\bf H.2.1} Information
Systems, DATABASE MANAGEMENT, Logical Design, Data
models. {\bf H.2.1} Information Systems, DATABASE
MANAGEMENT, Logical Design, Schema and subschema.",
}
@Article{Konopnicki:1998:IGW,
author = "David Konopnicki and Oded Shmueli",
title = "Information gathering in the {World-Wide Web}: the
{W3QL} query language and the {W3QS} system",
journal = j-TODS,
volume = "23",
number = "4",
pages = "369--410",
month = dec,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-4/p369-konopnicki/p369-konopnicki.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-4/p369-konopnicki/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-4/p369-konopnicki/",
abstract = "The World Wide Web (WWW) is a fast growing global
information resource. It contains an enormous amount of
information and provides access to a variety of
services. Since there is no central control and very
few standards of information organization or service
offering, searching for information and services is a
widely recognized problem. To some degree this problem
is solved by ``search services,'' also known as
``indexers,'' such as Lycos, AltaVista, Yahoo, and
others. These sites employ search engines known as
``robots'' or ``knowbots'' that scan the network
periodically and form text-based indices. These
services are limited in certain important aspects.
First, the structural information, namely, the
organization of the document into parts pointing to
each other, is usually lost. Second, one is limited by
the kind of textual analysis provided by the ``search
service.'' Third, search services are incapable of
navigating ``through'' forms. Finally, one cannot
prescribe a complex database-like search. We view the
WWW as a huge database. We have designed a high-level
SQL-like language called W3QL to support effective and
flexible query processing, which addresses the
structure and content of WWW nodes and their varied
sorts of data. We have implemented a system called W3QS
to execute W3QL queries. In W3QS, query results are
declaratively specified and continuously maintained as
views when desired. The current architecture of W3QS
provides a server that enables users to pose queries as
well as integrate their own data analysis tools. The
system and its query language set a framework for the
development of database-like tools over the WWW. A
significant contribution of this article is in
formalizing the WWW and query processing over it.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CGI; design; FORMS; HTML; HTTP; languages; PERL; query
language; query system; World-Wide Web",
subject = "{\bf H.2.3} Information Systems, DATABASE MANAGEMENT,
Languages, Query languages. {\bf H.1.0} Information
Systems, MODELS AND PRINCIPLES, General. {\bf H.3.3}
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Information Search and Retrieval.",
}
@Article{Sistla:1998:TTC,
author = "A. Prasad Sistla and Ouri Wolfson and Yelena Yesha and
Robert Sloan",
title = "Towards a theory of cost management for digital
libraries and electronic commerce",
journal = j-TODS,
volume = "23",
number = "4",
pages = "411--452",
month = dec,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-4/p411-sistla/p411-sistla.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-4/p411-sistla/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-4/p411-sistla/",
abstract = "One of the features that distinguishes digital
libraries from traditional databases is new cost models
for client access to intellectual property. Clients
will pay for accessing data items in digital libraries,
and we believe that optimizing these costs will be as
important as optimizing performance in traditional
databases. In this article we discuss cost models and
protocols for accessing digital libraries, with the
objective of determining the minimum cost protocol for
each model. We expect that in the future information
appliances will come equipped with a cost optimizer, in
the same way that computers today come with a built-in
operating system. This article makes the initial steps
towards a theory and practice of intellectual property
cost management.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Economics; Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; average case analysis; caching; cost
models; demand; economics; on-line services;
performance; protocols; subscription; theory; worst
case analysis",
subject = "{\bf H.2.m} Information Systems, DATABASE MANAGEMENT,
Miscellaneous. {\bf H.3.5} Information Systems,
INFORMATION STORAGE AND RETRIEVAL, Online Information
Services, Commercial services. {\bf H.3.5} Information
Systems, INFORMATION STORAGE AND RETRIEVAL, Online
Information Services, Web-based services. {\bf H.3.7}
Information Systems, INFORMATION STORAGE AND RETRIEVAL,
Digital Libraries, Dissemination.",
}
@Article{Zobel:1998:IFV,
author = "Justin Zobel and Alistair Moffat and Kotagiri
Ramamohanarao",
title = "Inverted files versus signature files for text
indexing",
journal = j-TODS,
volume = "23",
number = "4",
pages = "453--490",
month = dec,
year = "1998",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1998-23-4/p453-zobel/p453-zobel.pdf;
http://www.acm.org/pubs/citations/journals/tods/1998-23-4/p453-zobel/;
http://www.acm.org:80/pubs/citations/journals/tods/1998-23-4/p453-zobel/",
abstract = "Two well-known indexing methods are inverted files and
signature files. We have undertaken a detailed
comparison of these two approaches in the context of
text indexing, paying particular attention to query
evaluation speed and space requirements. We have
examined their relative performance using both
experimentation and a refined approach to modeling of
signature files, and demonstrate that inverted files
are distinctly superior to signature files. Not only
can inverted files be used to evaluate typical queries
in less time than can signature files, but inverted
files require less space and provide greater
functionality. Our results also show that a synthetic
text database can provide a realistic indication of the
behavior of an actual text database. The tools used to
generate the synthetic database have been made publicly
available",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "algorithms; indexing; inverted files; performance;
signature files; text databases; text indexing",
subject = "{\bf E.5} Data, FILES. {\bf H.2.2} Information
Systems, DATABASE MANAGEMENT, Physical Design. {\bf
H.3.3} Information Systems, INFORMATION STORAGE AND
RETRIEVAL, Information Search and Retrieval. {\bf
I.7.3} Computing Methodologies, DOCUMENT AND TEXT
PROCESSING, Index Generation**.",
}
@Article{Datta:1999:BPS,
author = "Anindya Datta and Debra E. Vandermeer and Aslihan
Celik and Vijay Kumar",
title = "Broadcast protocols to support efficient retrieval
from databases by mobile users",
journal = j-TODS,
volume = "24",
number = "1",
pages = "1--79",
month = mar,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-1/p1-datta/",
abstract = "Mobile computing has the potential for managing
information globally. Data management issues in mobile
computing have received some attention in recent times,
and the design of {\em adaptive broadcast protocols\/}
has been posed as an important problem. Such protocols
are employed by database servers to decide on the
content of broadcasts dynamically, in response to
client mobility and demand patterns. In this paper we
design such protocols and also propose efficient
retrieval strategies that may be employed by clients to
download information from broadcasts. The goal is to
design {\em cooperative\/} strategies between server
and client to provide access to information in such a
way as to minimize energy expenditure by clients. We
evaluate the performance of our protocols both
analytically and through simulation.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "adaptive broadcast protocols; client-server computing;
energy conservation; mobile databases",
subject = "Computer Systems Organization ---
Computer-Communication Networks --- Network
Architecture and Design (C.2.1); Information Systems
--- Database Management (H.2); Computer Systems
Organization --- Computer-Communication Networks ---
Network Protocols (C.2.2); Information Systems ---
Database Management --- Systems (H.2.4); Computer
Systems Organization --- Computer-Communication
Networks --- Network Architecture and Design (C.2.1):
{\bf Wireless communication}; Information Systems ---
Information Systems Applications --- Communications
Applications (H.4.3); Information Systems ---
Information Systems Applications --- Communications
Applications (H.4.3): {\bf Internet}",
}
@Article{Levene:1999:DDI,
author = "Mark Levene and George Loizou",
title = "Database design for incomplete relations",
journal = j-TODS,
volume = "24",
number = "1",
pages = "80--126",
month = mar,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-1/p80-levene/",
abstract = "Although there has been a vast amount of research in
the area of relational database design, to our
knowledge, there has been very little work that
considers whether this theory is still valid when
relations in the database may be incomplete. When
relations are incomplete and thus contain null values
the problem of whether satisfaction is additive arises.
Additivity is the property of the equivalence of the
satisfaction of a set of functional dependencies (FDs)
F with the individual satisfaction of each member of F
in an incomplete relation. It is well known that in
general, satisfaction of FDs is not additive.
Previously we have shown that satisfaction is additive
if and only if the set of FDs is monodependent. We
conclude that monodependence is a fundamental desirable
property of a set of FDs when considering incomplete
information in relational database design. We show
that, when the set of FDs F either satisfies the
intersection property or the split-freeness property,
then the problem of finding an optimum cover of F can
be solved in polynomial time in the size of F; in
general, this problem is known to be NP-complete. We
also show that when F satisfies the split-freeness
property then deciding whether there is a superkey of
cardinality k or less can be solved in polynomial time
in the size of F, since all the keys have the same
cardinality. If F only satisfies the intersection
property then this problem is NP-complete, as in the
general case. Moreover, we show that when F either
satisfies the intersection property or the
split-freeness property then deciding whether an
attribute is prime can be solved in polynomial time in
the size of F; in general, this problem is known to be
NP-complete. Assume that a relation schema R is an
appropriate normal form with respect to a set of FDs F.
We show that when F satisfies the intersection property
then the notions of second normal form and third normal
form are equivalent. We also show that when R is in
Boyce-Codd Normal Form (BCNF), then F is monodependent
if and only if either there is a unique key for R, or
for all keys X for R, the cardinality of X is one less
than the number of attributes associated with R.
Finally, we tackle a long-standing problem in
relational database theory by showing that when a set
of FDs F over R satisfies the intersection property, it
also satisfies the split-freeness property (i.e., is
monodependent), if and only if every lossless join
decomposition of R with respect to F is also dependency
preserving. As a corollary of this result we are able
to show that when F satisfies the intersection
property, it also satisfies the intersection property,
it also satisfies the split-freeness property(i.e., is
monodependent), if and only if every lossless join
decomposition of R, which is in BCNF, is also
dependency preserving. Our final result is that when F
is monodependent, then there exists a unique optimum
lossless join decomposition of R, which is in BCNF, and
is also dependency preserving. Furthermore, this
ultimate decomposition can be attained in polynomial
time in the size of F.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "additivity problem; complexity; dependency preserving
decomposition; incomplete information; intersection
property; lossless join decomposition; monodependence;
normal forms; null functional dependencies; optimum
cover; prime attribute problem; split-freeness
property; superkey of cardinality k problem",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Normal forms}",
}
@Article{Wijsen:1999:TFC,
author = "Jef Wijsen",
title = "Temporal {FDs} on complex objects",
journal = j-TODS,
volume = "24",
number = "1",
pages = "127--176",
month = mar,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-1/p127-wijsen/",
abstract = "{\em Temporal functional dependencies\/} (TFD) are
defined for temporal databases that include object
identity. It is argued that object identity can
overcome certain semantic difficulties with existing
temporal relational data models. Practical applications
of TFDs in object bases are discussed. Reasoning about
TFDs is at the center of this paper. It turns out that
the distinction between acyclic and cyclic schemas is
significant. For acyclic schemas, a complete
axiomatization for finite implication is given and an
algorithm for deciding finite implication provided. The
same axiomatization is proven complete for unrestricted
implication in unrestricted schemas, which can be
cyclic. An interesting result is that there are cyclic
schemas for which unrestricted and finite implication
do not coincide. TFDs relate and extend some earlier
work on dependency theory in temporal databases.
Throughout this paper, the construct of TFD is compared
with the notion of temporal FD introduced by Wang et
al. (1997). A comparison with other related work is
provided at the end of the article.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database constraints; functional dependency;
object-identity; temporal databases; time granularity",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1)",
}
@Article{Chaudhuri:1999:OQU,
author = "Surajit Chaudhuri and Kyuseok Shim",
title = "Optimization of queries with user-defined predicates",
journal = j-TODS,
volume = "24",
number = "2",
pages = "177--228",
month = jun,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-2/p177-chaudhuri/",
abstract = "Relational databases provide the ability to store
user-defined functions and predicates which can be
invoked in SQL queries. When evaluation of a
user-defined predicate is relatively expensive, the
traditional method of evaluating predicates as early as
possible is no longer a sound heuristic. There are two
previous approaches for optimizing such queries.
However, neither is able to guarantee the optimal plan
over the desired execution space. We present efficient
techniques that are able to guarantee the choice of an
optimal plan over the desired execution space. The {\em
optimization algorithm with complete rank-ordering\/}
improves upon the naive optimization algorithm by
exploiting the nature of the cost formulas for join
methods and is polynomial in the number of user-defined
predicates (for a given number of relations.) We also
propose {\em pruning rules\/} that significantly reduce
the cost of searching the execution space for both the
naive algorithm as well as for the optimization
algorithm with complete rank-ordering, without
compromising optimality. We also propose a {\em
conservative local heuristic\/} that is simpler and has
low optimization overhead. Although it is not always
guaranteed to find the optimal plans, it produces close
to optimal plans in most cases. We discuss how,
depending on application requirements, to determine the
algorithm of choice. It should be emphasized that our
optimization algorithms handle user-defined selections
as well as user-defined join predicates uniformly. We
present complexity analysis and experimental comparison
of the algorithms.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Management; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "dynamic programming; query optimization; user-defined
predicates",
subject = "Information Systems --- Database Management (H.2);
Information Systems --- Database Management --- General
(H.2.0); Information Systems --- Database Management
--- Systems (H.2.4): {\bf Relational databases}",
}
@Article{Gravano:1999:GTS,
author = "Luis Gravano and H{\'e}ctor Garc{\'\i}a-Molina and
Anthony Tomasic",
title = "{GlOSS}: text-source discovery over the {Internet}",
journal = j-TODS,
volume = "24",
number = "2",
pages = "229--264",
month = jun,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-2/p229-gravano/",
abstract = "The dramatic growth of the Internet has created a new
problem for users: location of the relevant sources of
documents. This article presents a framework for (and
experimentally analyzes a solution to) this problem,
which we call the {\em text-source discovery problem}.
Our approach consists of two phases. First, each text
source exports its contents to a centralized service.
Second, users present queries to the service, which
returns an ordered list of promising text sources. This
article describes {\em GlOSS}, Glossary of Servers
Server, with two versions: {\em bGlOSS}, which provides
a Boolean query retrieval model, and {\em vGlOSS},
which provides a vector-space retrieval model. We also
present {\em hGlOSS}, which provides a decentralized
version of the system. We extensively describe the
methodology for measuring the retrieval effectiveness
of these systems and provide experimental evidence,
based on actual data, that all three systems are highly
effective in determining promising text sources for a
given query.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Measurement; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "digital libraries; distributed information retrieval;
Internet search and retrieval; text databases",
subject = "Information Systems --- Information Storage and
Retrieval --- General (H.3.0); Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3); Information Systems ---
Information Storage and Retrieval --- Digital Libraries
(H.3.7); Information Systems --- Database Management
--- Systems (H.2.4): {\bf Textual databases};
Information Systems --- Information Storage and
Retrieval (H.3)",
}
@Article{Hjaltason:1999:DBS,
author = "G{\'\i}sli R. Hjaltason and Hanan Samet",
title = "Distance browsing in spatial databases",
journal = j-TODS,
volume = "24",
number = "2",
pages = "265--318",
month = jun,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 21 16:01:19 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-2/p265-hjaltason/",
abstract = "We compare two different techniques for browsing
through a collection of spatial objects stored in an
R-tree spatial data structure on the basis of their
distances from an arbitrary spatial query object. The
conventional approach is one that makes use of a
$k$-nearest neighbor algorithm where $k$ is known prior
to the invocation of the algorithm. Thus if $ m k $
neighbors are needed, the $k$-nearest neighbor
algorithm has to be reinvoked for $m$ neighbors,
thereby possibly performing some redundant
computations. The second approach is incremental in the
sense that having obtained the $k$ nearest neighbors,
the $ k + 1 {\em st \/ } $ neighbor can be obtained
without having to calculate the $ k + 1 $ nearest
neighbors from scratch. The incremental approach is
useful when processing complex queries where one of the
conditions involves spatial proximity (e.g., the
nearest city to Chicago with population greater than a
million), in which case a query engine can make use of
a pipelined strategy. We present a general incremental
nearest neighbor algorithm that is applicable to a
large class of hierarchical spatial data structures.
This algorithm is adapted to the R-tree and its
performance is compared to an existing $k$-nearest
neighbor algorithm for R-trees [Rousseopoulos et al.
1995]. Experiments show that the incremental nearest
neighbor algorithm significantly outperforms the
$k$-nearest neighbor algorithm for distance browsing
queries in a spatial database that uses the R-tree as a
spatial index. Moreover, the incremental nearest
neighbor algorithm usually outperforms the $k$-nearest
neighbor algorithm when applied to the $k$-nearest
neighbor problem for the R-tree, although the
improvement is not nearly as large as for distance
browsing queries. In fact, we prove informally that at
any step in its execution the incremental nearest
neighbor algorithm is optimal with respect to the
spatial data structure that is employed. Furthermore,
based on some simplifying assumptions, we prove that in
two dimensions the number of distance computations and
leaf nodes accesses made by the algorithm for finding
$k$ neighbors is $ O(k + k) $.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "distance browsing; hierarchical spatial data
structures; nearest neighbors; R-trees; ranking",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Spatial databases
and GIS}; Data --- Data Structures (E.1): {\bf Trees}",
}
@Article{Alagic:1999:TCO,
author = "Suad Alag{\'\i}c",
title = "Type-checking {OQL} queries in the {ODMG} type
systems",
journal = j-TODS,
volume = "24",
number = "3",
pages = "319--360",
month = sep,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-3/p319-alagic/",
abstract = "Several negative results are proved about the ability
to type-check queries in the only existing proposed
standard for object-oriented databases. The first of
these negative results is that it is not possible to
type-check OQL queries in the type system underlying
the ODMG object model and its definition language ODL.
The second negative result is that OQL queries cannot
be type-checked in the type system of the Java binding
of the ODMG standard either. A solution proposed in
this paper is to extend the ODMG object model with
explicit support for parametric polymorphism (universal
type quantification). These results show that Java
cannot be a viable database programming language unless
extended with parametric polymorphism. This is why
type-checking OQL queries presents no problem for the
type system of the C++ binding of the ODMG standard.
However, a type system that is strictly more powerful
than any of the type systems of the ODMG standard is
required in order to properly type ordered collections
and indices. The required form of polymorphism is
bounded type quantification (constrained genericity)
and even F-bounded polymorphism. A further result is
that neither static nor the standard dynamic
object-oriented type-checking is possible for Java OQL,
in spite of the fact that Java OQL combines features of
two strongly and mostly statically-typed languages.
Contrary to one of the promises of object-oriented
database technology, this result shows that the
impedance mismatch does not disappear in the ODMG
standard. A type-safe reflective technique is proposed
for overcoming this mismatch.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Standardization; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "C++; Java; ODMG standard; OQL; parametric
polymorphism; type systems",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Data description languages (DDL)}; Information
Systems --- Database Management --- Languages (H.2.3):
{\bf Database (persistent) programming languages};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Object-oriented databases}; Software ---
Programming Languages --- Language Classifications
(D.3.2): {\bf Object-oriented languages}; Software ---
Programming Languages --- Language Constructs and
Features (D.3.3): {\bf Classes and objects}; Software
--- Programming Languages --- Language Constructs and
Features (D.3.3): {\bf Inheritance}; Software ---
Programming Languages --- Language Constructs and
Features (D.3.3): {\bf Polymorphism}",
}
@Article{Bozkaya:1999:ILM,
author = "Tolga Bozkaya and Meral Ozsoyoglu",
title = "Indexing large metric spaces for similarity search
queries",
journal = j-TODS,
volume = "24",
number = "3",
pages = "361--404",
month = sep,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-3/p361-bozkaya/",
abstract = "One of the common queries in many database
applications is finding approximate matches to a given
query item from a collection of data items. For
example, given an image database, one may want to
retrieve all images that are similar to a given query
image. Distance-based index structures are proposed for
applications where the distance computations between
objects of the data domain are expensive (such as
high-dimensional data) and the distance function is
metric. In this paper we consider using distance-based
index structures for similarity queries on large metric
spaces. We elaborate on the approach that uses
reference points (vantage points) to partition the data
space into spherical shell-like regions in a
hierarchical manner. We introduce the multivantage
point tree structure (mvp-tree) that uses more than one
vantage point to partition the space into spherical
cuts at each level. In answering similarity-based
queries, the mvp-tree also utilizes the precomputed (at
construction time) distances between the data points
and the vantage points.\par We summarize the
experiments comparing mvp-trees to vp-trees that have a
similar partitioning strategy, but use only one vantage
point at each level and do not make use of the
precomputed distances. Empirical studies show that the
mvp-tree outperforms the vp-tree by 20\% to 80\% for
varying query ranges and different distance
distributions. Next, we generalize the idea of using
multiple vantage points and discuss the results of
experiments we have made to see how varying the number
of vantage points in a node affects performance and how
much is gained in performance by making use of
precomputed distances. The results show that, after
all, it may be best to use a large number of vantage
points in an internal node in order to end up with a
single directory node and keep as many of the
precomputed distances as possible to provide more
efficient filtering during search operations. Finally,
we provide some experimental results that compare
mvp-trees with M-trees, which is a dynamic
distance-based index structure for metric domains.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Measurement; Performance;
Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
subject = "Data --- Data Structures (E.1): {\bf Trees};
Information Systems --- Information Storage and
Retrieval --- Content Analysis and Indexing (H.3.1):
{\bf Indexing methods}; Information Systems ---
Information Storage and Retrieval --- Information
Search and Retrieval (H.3.3): {\bf Search process}",
}
@Article{Casati:1999:SIE,
author = "Fabio Casati and Stefano Ceri and Stefano Paraboschi
and Guiseppe Pozzi",
title = "Specification and implementation of exceptions in
workflow management systems",
journal = j-TODS,
volume = "24",
number = "3",
pages = "405--451",
month = sep,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-3/p405-casati/",
abstract = "Although workflow management systems are most
applicable when an organization follows standard
business processes and routines, any of these processes
faces the need for handling exceptions, i.e.,
asynchronous and anomalous situations that fall outside
the normal control flow.\par
In this paper we concentrate upon anomalous situations
that, although unusual, are part of the semantics of
workflow applications, and should be specified and
monitored coherently; in most real-life applications,
such exceptions affect a significant fraction of
workflow cases. However, very few workflow management
systems are integrated with a highly expressive
language for specifying this kind of exception and with
a system component capable of handling it.\par
We present Chimera-Exc, a language for the
specification of exceptions for workflows based on
detached active rules, and then describe the
architecture of a system, called FAR, that implements
Chimera-Exc and integrates it with a commercial
workflow management system and database server. We
discuss the main issues that were solved by our
implementation, and report on the performance of FAR.
We also discuss design criteria for exceptions in light
of the formal properties of their execution. Finally,
we focus on the portability of FAR on its unbundling to
a generic architecture with detached active rules.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Languages; Management; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active rules; asynchronous events; exceptions;
workflow management systems",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Rule-based databases};
Information Systems --- Information Systems
Applications --- General (H.4.0)",
}
@Article{Dey:1999:IDD,
author = "Debabrata Dey and Veda C. Storey and Terence M.
Barron",
title = "Improving database design through the analysis of
relationships",
journal = j-TODS,
volume = "24",
number = "4",
pages = "453--486",
month = dec,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/1999-24-4/p453-dey/p453-dey.pdf;
http://www.acm.org/pubs/citations/journals/tods/1999-24-4/p453-dey/",
abstract = "Much of the work on conceptual modeling involves the
use of an entity-relationship model in which binary
relationships appear as associations between two
entities. Relationships involving more than two
entities are considered rare and, therefore, have not
received adequate attention. This research provides a
general framework for the analysis of relationships in
which binary relationships simply become a special
case. The framework helps a designer to identify
ternary and other higher-degree relationships that are
commonly represented, often inappropriately, as either
entities or binary relationships. Generalized rules are
also provided for representing higher-degree
relationships in the relational model. This uniform
treatment of relationships should significantly ease
the burden on a designer by enabling him or her to
extract more information from a real-world situation
and represent it properly in a conceptual design.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual model; ER model; integrity constraint;
min-max cardinality; relationship degree; weak
relationship",
subject = "Information Systems --- Models and Principles ---
General (H.1.0); Information Systems --- Database
Management --- Logical Design (H.2.1): {\bf Data
models}; Information Systems --- Database Management
--- Database Administration (H.2.7): {\bf Security,
integrity, and protection}",
}
@Article{Muralidhar:1999:SRD,
author = "Krishnamurty Muralidhar and Rathindra Sarathy",
title = "Security of random data perturbation methods",
journal = j-TODS,
volume = "24",
number = "4",
pages = "487--493",
month = dec,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-4/p487-muralidhar/",
abstract = "Statistical databases often use random data
perturbation (RDP) methods to protect against
disclosure of confidential numerical attributes. One of
the key requirements of RDP methods is that they
provide the appropriate level of security against
snoopers who attempt to obtain information on
confidential attributes through statistical inference.
In this study, we evaluate the security provided by
three methods of perturbation. The results of this
study allow the database administrator to select the
most effective RDP method that assures adequate
protection against disclosure of confidential
information.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Measurement; Security",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bias; covariance; noise addition; random data
perturbation",
subject = "Information Systems --- Database Management ---
Database Administration (H.2.7): {\bf Security,
integrity, and protection}; Information Systems ---
Database Management --- Database Applications (H.2.8):
{\bf Statistical databases}",
}
@Article{Wand:1999:OAR,
author = "Yair Wand and Veda C. Storey and Ron Weber",
title = "An ontological analysis of the relationship construct
in conceptual modeling",
journal = j-TODS,
volume = "24",
number = "4",
pages = "494--528",
month = dec,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-4/p494-wand/",
abstract = "Conceptual models or semantic data models were
developed to capture the meaning of an application
domain as perceived by someone. Moreover, concepts
employed in semantic data models have recently been
adopted in object-oriented approaches to systems
analysis and design. To employ conceptual modeling
constructs effectively, their meanings have to be
defined rigorously. Often, however, rigorous
definitions of these constructs are missing. This
situation occurs especially in the case of the
relationship construct. Empirical evidence shows that
use of relationships is often problematical as a way of
communicating the meaning of an application domain. For
example, users of conceptual modeling methodologies are
frequently confused about whether to show an
association between things via a relationship, an
entity, or an attribute. Because conceptual models are
intended to capture knowledge about a real-world
domain, we take the view that the meaning of modeling
constructs should be sought in models of reality.
Accordingly, we use ontology, which is the branch of
philosophy dealing with models of reality, to analyze
the meaning of common conceptual modeling constructs.
Our analysis provides a precise definition of several
conceptual modeling constructs. Based on our analysis,
we derive rules for the use of relationships in
entity-relationship conceptual modeling. Moreover, we
show how the rules resolve ambiguities that exist in
current practice and how they can enrich the capacity
of an entity-relationship conceptual model to capture
knowledge about an application domain.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conceptual modeling; database design;
entity-relationship model; object-oriented modeling;
ontology; semantic data modeling",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Computing
Milieux --- Management of Computing and Information
Systems --- Project and People Management (K.6.1): {\bf
Systems analysis and design}",
}
@Article{Yan:1999:SID,
author = "Tak W. Yan and Hector Garcia-Molina",
title = "The {SIFT} information dissemination system",
journal = j-TODS,
volume = "24",
number = "4",
pages = "529--565",
month = dec,
year = "1999",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Sep 26 08:44:02 MDT 2000",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/1999-24-4/p529-yan/",
abstract = "Information dissemination is a powerful mechanism for
finding information in wide-area environments. An
information dissemination server accepts long-term user
queries, collects new documents from information
sources, matches the documents against the queries, and
continuously updates the users with relevant
information. This paper is a retrospective of the
Stanford Information Filtering Service (SIFT), a system
that as of April 1996 was processing over 40,000
worldwide subscriptions and over 80,000 daily
documents. The paper describes some of the indexing
mechanisms that were developed for SIFT, as well as the
evaluations that were conducted to select a scheme to
implement. It also describes the implementation of
SIFT, and experimental results for the actual system.
Finally, it also discusses and experimentally evaluates
techniques for distributing a service such as SIFT for
added performance and availability.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Boolean queries; dissemination; filtering; indexing;
vector space queries",
subject = "Information Systems --- Database Management ---
Systems (H.2.4); Information Systems --- Information
Storage and Retrieval --- Information Storage (H.3.2);
Information Systems --- Information Storage and
Retrieval --- Information Search and Retrieval (H.3.3);
Information Systems --- Information Storage and
Retrieval --- Systems and Software (H.3.4)",
}
@Article{Morris:19xx:DON,
author = "K. Morris and J. D. Ullman and A. VanGelder",
title = "Design Overview of the {NAIL!} System",
journal = j-TODS,
volume = "??",
number = "??",
pages = "??--??",
month = "????",
year = "19xx",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Also published in/as: Proc. of International
Conference on Logic Programming, BCS 3, 1986. Also
published in/as: Stanford Un., CSD, TR-CS-86-1108.",
annote = "The {NAIL!} System seems to be a much more powerful
query language than the ones commercially available
today. It adds the power and dexterity of Prolog-like
logic to standard query techniques. The {NAIL!} System
exhibits a tendency to swing the database community
from object-oriented query languages back to
value-oriented query languages. There seemed to be
ambiguity as to how to handle recursive rules. The
paper gave some techniques but didn't prefer one over
the other. Overall, the {NAIL!} System appears to be a
superior attempt at strengthening conventional database
query operations.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Spiegler:19xx:DRA,
author = "I. Spiegler and Y. Noff",
title = "Dynamic Recovery as an Alternative to Data Base
Restoration",
journal = j-TODS,
volume = "??",
number = "??",
pages = "??--??",
month = "????",
year = "19xx",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibsource = "Database/Wiederhold.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Submitted, March 1987.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Guting:2000:FRQ,
author = "Ralf Hartmut G{\"u}ting and Michael H. B{\"o}hlen and
Martin Erwig and Christian S. Jensen and Nikos A.
Lorentzos and Markus Schneider and Michalis
Vazirgiannis",
title = "A foundation for representing and querying moving
objects",
journal = j-TODS,
volume = "25",
number = "1",
pages = "1--42",
month = mar,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-1/p1-guting/p1-guting.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-1/p1-guting/",
abstract = "Spatio-temporal databases deal with geometries
changing over time. The goal of our work is to provide
a DBMS data model and query language capable of
handling such time-dependent geometries, including
those changing continuously that describe {\em moving
objects}. Two fundamental abstractions are {\em moving
point\/} and {\em moving region}, describing objects
for which only the time-dependent position, or position
and extent, respectively, are of interest. We propose
to present such time-dependent geometries as attribute
data types with suitable operations, that is, to
provide an abstract data type extension to a DBMS data
model and query language. This paper presents a design
of such a system of abstract data types. It turns out
that besides the main types of interest, moving point
and moving region, a relatively large number of
auxiliary data types are needed. For example, one needs
a line type to represent the projection of a moving
point into the plane, or a ``moving real'' to represent
the time-dependent distance of two points. It then
becomes crucial to achieve (i) orthogonality in the
design of the system, i.e., type constructors can be
applied uniformly; (ii) genericity and consistency of
operations, i.e., operations range over as many types
as possible and behave consistently; and (iii) closure
and consistency between structure and operations of
nontemporal and related temporal types. Satisfying
these goal leads to a simple and expressive system of
abstract data types that may be integrated into a query
language to yield a powerful language for querying
spatio-temporal data, including moving objects. The
paper formally defines the types and operations, offers
detailed insight into the considerations that went into
the design, and exemplifies the use of the abstract
data types using SQL. The paper offers a precise and
conceptually clean foundation for implementing a
spatio-temporal DBMS extension.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "abstract data types; algebra; moving objects; moving
point; moving region; spatio-temporal data types;
spatio-temporal databases",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf Query languages}; Information
Systems --- Database Management --- Database
Applications (H.2.8): {\bf Spatial databases and GIS}",
}
@Article{Kossmann:2000:IDP,
author = "Donald Kossmann and Konrad Stocker",
title = "Iterative dynamic programming: a new class of query
optimization algorithms",
journal = j-TODS,
volume = "25",
number = "1",
pages = "43--82",
month = mar,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-1/p43-kossmann/p43-kossmann.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-1/p43-kossmann/",
abstract = "The query optimizer is one of the most important
components of a database system. Most commercial query
optimizers today are based on a dynamic-programming
algorithm, as proposed in Selinger et al. [1979]. While
this algorithm produces good optimization results (i.e,
good plans), its high complexity can be prohibitive if
complex queries need to be processed, new query
execution techniques need to be integrated, or in
certain programming environments (e.g., distributed
database systems). In this paper, we present and
thoroughly evaluate a new class of query optimization
algorithms that are based on a principle that we call
{\em iterative dynamic programming}, or IDP for short.
IDP has several important advantages: First,
IDP-algorithms produce the best plans of all known
algorithms in situations in which dynamic programming
is not viable because of its high complexity. Second,
some IDP variants are adaptive and produce as good
plans as dynamic programming if dynamic programming is
viable and as good-as possible plans if dynamic
programming turns out to be not viable. Three, all
IDP-algorithms can very easily be integrated into an
existing optimizer which is based on dynamic
programming.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "dynamic programming; greedy algorithm; iterative
dynamic programming; plan evaluation function; query
optimization; query optimiztion; randomized
optimization",
subject = "Theory of Computation --- Analysis of Algorithms and
Problem Complexity --- Nonnumerical Algorithms and
Problems (F.2.2); Information Systems --- Database
Management --- Systems (H.2.4): {\bf Distributed
databases}; Information Systems --- Database Management
--- Systems (H.2.4): {\bf Relational databases}",
}
@Article{Lerner:2000:MCT,
author = "Barbara Staudt Lerner",
title = "A model for compound type changes encountered in
schema evolution",
journal = j-TODS,
volume = "25",
number = "1",
pages = "83--127",
month = mar,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-1/p83-lerner/p83-lerner.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-1/p83-lerner/",
abstract = "Schema evolution is a problem that is faced by
long-lived data. When a schema changes, existing
persistent data can become inaccessible unless the
database system provides mechanisms to access data
created with previous versions of the schema. Most
existing systems that support schema evolution focus on
changes local to individual types within the schema,
thereby limiting the changes that the database
maintainer can perform. We have developed a model of
type changes involving multiple types. The model
describes both type changes and their impact on data by
defining derivation rules to initialize new data based
on the existing data. The derivation rules can describe
local and nonlocal changes to types to capture the
intent of a large class of type change operations. We
have built a system called Tess (Type Evolution
Software System) that uses this model to recognize type
changes by comparing schemas and then produces a
transformer that can update data in a database to
correspond to a newer version of the schema.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Languages",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "persistent programming languages; schema evolution",
subject = "Information Systems --- Database Management ---
Miscellaneous (H.2.m); Information Systems --- Database
Management --- Languages (H.2.3): {\bf Database
(persistent) programming languages}; Software ---
Software Engineering --- Distribution, Maintenance, and
Enhancement (D.2.7): {\bf Restructuring, reverse
engineering, and reengineering}",
}
@Article{Bohm:2000:CMQ,
author = "Christian B{\"o}hm",
title = "A cost model for query processing in high dimensional
data spaces",
journal = j-TODS,
volume = "25",
number = "2",
pages = "129--178",
month = jun,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-2/p129-bohm/p129-bohm.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-2/p129-bohm/",
abstract = "During the last decade, multimedia databases have
become increasingly important in many application areas
such as medicine, CAD, geography, and molecular
biology. An important research topic in multimedia
databases is similarity search in large data sets. Most
current approaches that address similarity search use
the feature approach, which transforms important
properties of the stored objects into points of a
high-dimensional space (feature vectors). Thus,
similarity search is transformed into a neighborhood
search in feature space. Multidimensional index
structures are usually applied when managing feature
vectors. Query processing can be improved substantially
with optimization techniques such as blocksize
optimization, data space quantization, and dimension
reduction. To determine optimal parameters, an accurate
estimate of index-based query processing performance is
crucial. In this paper we develop a cost model for
index structures for point databases such as the
R*-tree and the X-tree. It provides accurate estimates
of the number of data page accesses for range queries
and nearest-neighbor queries under a Euclidean metric
and a maximum metric and a maximum metric. The problems
specific to high-dimensional data spaces, called
boundary effects, are considered. The concept of the
fractal dimension is used to take the effects of
correlated data into account.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Performance; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cost model; multidimensional index",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8); Information Systems ---
Information Storage and Retrieval --- Content Analysis
and Indexing (H.3.1)",
}
@Article{Cui:2000:TLV,
author = "Yingwei Cui and Jennifer Widom and Janet L. Wiener",
title = "Tracing the lineage of view data in a warehousing
environment",
journal = j-TODS,
volume = "25",
number = "2",
pages = "179--227",
month = jun,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-2/p179-cui/p179-cui.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-2/p179-cui/",
abstract = "We consider the {\em view data lineage\/} problem in a
warehousing environment: For a given data item in a
materialized warehouse view, we want to identify the
set of source data items that produced the view item.
We formally define the lineage problem, develop lineage
tracing algorithms for relational views with
aggregation, and propose mechanisms for performing
consistent lineage tracing in a multisource data
warehousing environment. Our result can form the basis
of a tool that allows analysts to browse warehouse
data, select view tuples of interest, and then
``drill-through'' to examine the exact source tuples
that produced the view tuples of interest.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Design",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data warehouse; derivation; lineage; materialized
views",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Database Manager}",
}
@Article{Parsons:2000:EIT,
author = "Jeffrey Parsons and Yair Wand",
title = "Emancipating instances from the tyranny of classes in
information modeling",
journal = j-TODS,
volume = "25",
number = "2",
pages = "228--268",
month = jun,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-2/p228-parsons/p228-parsons.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-2/p228-parsons/",
abstract = "Database design commonly assumes, explicitly or
implicitly, that instances must belong to classes. This
can be termed the {\em assumption of inherent
classification}. We argue that the extent and
complexity of problems in schema integration, schema
evolution, and interoperability are, to a large degree,
consequences of inherent classification. Furthermore,
we make the case that the assumption of inherent
classification violates philosophical and cognitive
guidelines on classification and is, therefore,
inappropriate in view of the role of data modeling in
representing knowledge about application domains.
\par
As an alternative, we propose a layered approach to
modeling in which information about instances is
separated from any particular classification. Two data
modeling layers are proposed: (1) an {\em instance
model\/} consisting of an instance base (i.e.,
information about instances and properties) and
operations to populate, use, and maintain it; and (2) a
{\em class model\/} consisting of a class base (i.e.,
information about classes defined in terms of
properties) and operations to populate, use, and
maintain it. The two-layered model provides {\em class
independence}. This is analogous to the arguments of
data independence offered by the relational model in
comparison to hierarchical and network models. We show
that a two-layered approach yields several advantages.
In particular, schema integration is shown to be
partially an artifact of inherent classification that
can be greatly simplified in designing a database based
on a layered model; schema evolution is supported
without the complexity of operations currently required
by class-based models; and the difficulties associated
with interoperability among heterogeneous databases are
reduced because there is no need to agree on the
semantics of classes among independent databases. We
conclude by considering the adequacy of a two-layered
approach, outlining possible implementation strategies,
and drawing attention to some practical
considerations.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Management; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "classification; conceptual modeling; database design;
interoperability; ontology; schema evolution; schema
integration",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1): {\bf Data models}; Information
Systems --- Database Management --- Logical Design
(H.2.1): {\bf Schema and subschema}; Information
Systems --- Database Management --- Heterogeneous
Databases (H.2.5): {\bf Data translation**};
Information Systems --- Database Management ---
Heterogeneous Databases (H.2.5)",
}
@Article{Baralis:2000:AAS,
author = "Elena Baralis and Jennifer Widom",
title = "An algebraic approach to static analysis of active
database rules",
journal = j-TODS,
volume = "25",
number = "3",
pages = "269--332",
month = sep,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/2000-25-3/p269-baralis/",
abstract = "Rules in active database systems can be very difficult
to program due to the unstructured and unpredictable
nature of rule processing. We provide static analysis
techniques for predicting whether a given rule set is
guaranteed to terminate and whether rule execution is
confluent (guaranteed to have a unique final state).
Our methods are based on previous techniques for
analyzing rules in active database systems. We improve
considerably on the previous techniques by providing
analysis criteria that are much less conservative: our
methods often determine that a rule set will terminate
or is confluent when previous methods could not make
this determination. Our improved analysis is based on a
``propagation'' algorithm, which uses an extended
relational algebra to accurately determine when the
action of one rule can affect the condition of another,
and determine when rule actions commute. We consider
both condition-action rules and
event-condition-action-rules, making our approach
widely applicable to relational active database rule
languages and to the trigger language in the SQL:1999
standard.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Verification",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "active database systems; confluence; database rule
processing; database trigger processing; termination",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Rule-based databases};
Information Systems --- Database Management ---
Languages (H.2.3): {\bf SQL}",
}
@Article{Kemme:2000:NAD,
author = "Bettina Kemme and Gustavo Alonso",
title = "A new approach to developing and implementing eager
database replication protocols",
journal = j-TODS,
volume = "25",
number = "3",
pages = "333--379",
month = sep,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/2000-25-3/p333-kemme/",
abstract = "Database replication is traditionally seen as a way to
increase the availability and performance of
distributed databases. Although a large number of
protocols providing data consistency and
fault-tolerance have been proposed, few of these ideas
have ever been used in commercial products due to their
complexity and performance implications. Instead,
current products allow inconsistencies and often resort
to centralized approaches which eliminates some of the
advantages of replication. As an alternative, we
propose a suite of replication protocols that addresses
the main problems related to database replication. On
the one hand, our protocols maintain data consistency
and the same transactional semantics found in
centralized systems. On the other hand, they provide
flexibility and reasonable performance. To do so, our
protocols take advantage of the rich semantics of group
communication primitives and the relaxed isolation
guarantees provided by most databases. This allows us
to eliminate the possibility of deadlocks, reduce the
message overhead and increase performance. A detailed
simulation study shows the feasibility of the approach
and the flexibility with which different types of
bottlenecks can be circumvented.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Management; Performance; Reliability",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database replication; fault-tolerance; group
communication; isolation levels;
one-copy-serializability; replica control; total error
multicast",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Concurrency}; Information Systems
--- Database Management --- Systems (H.2.4): {\bf
Distributed databases}; Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Transaction processing}; Computer Systems Organization
--- Computer-Communication Networks --- Distributed
Systems (C.2.4); Computer Systems Organization ---
Performance of Systems (C.4)",
}
@Article{Meo:2000:TDV,
author = "Rosa Meo",
title = "Theory of dependence values",
journal = j-TODS,
volume = "25",
number = "3",
pages = "380--406",
month = sep,
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Apr 14 10:34:48 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/citations/journals/tods/2000-25-3/p380-meo/",
abstract = "A new model to evaluate dependencies in data mining
problems is presented and discussed. The well-known
concept of the association rule is replaced by the new
definition of dependence value, which is a single real
number uniquely associated with a given itemset.
Knowledge of dependence values is sufficient to
describe all the dependencies characterizing a given
data mining problem. The dependence value of an itemset
is the difference between the occurrence probability of
the itemset and a corresponding ``maximum independence
estimate.'' This can be determined as a function of
joint probabilities of the subsets of the itemset being
considered by maximizing a suitable entropy function.
So it is possible to separate in an itemset of
cardinality $k$ the dependence inherited from its
subsets of cardinality ($ k 1 $ ) and the specific
inherent dependence of that itemset. The absolute value
of the difference between the probability p($i$ ) of
the event $i$ that indicates the presence of the
itemset $ \{ a, b, \ldots {} \} $ and its maximum
independence estimate is constant for any combination
of values of $ Q a, b, \ldots {} Q $. In addition, the
Boolean function specifying the combination of values
for which the dependence is positive is a parity
function. So the determination of such combinations is
immediate. The model appears to be simple and
powerful.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Experimentation; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "association rules; dependence rules; entropy;
variables independence",
subject = "Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Data mining};
Information Systems --- Database Management ---
Database Applications (H.2.8): {\bf Statistical
databases}; Information Systems --- Models and
Principles --- Systems and Information Theory (H.1.1):
{\bf Information theory}; Computing Methodologies ---
Artificial Intelligence --- Knowledge Representation
Formalisms and Methods (I.2.4)",
}
@Article{Bohlen:2000:TSM,
author = "Michael H. B{\"o}hlen and Christian S. Jensen and
Richard T. Snodgrass",
title = "Temporal statement modifiers",
journal = j-TODS,
volume = "25",
number = "4",
pages = "407--456",
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 26 08:20:52 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-4/p407-bohlen/p407-bohlen.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-4/p407-bohlen/",
abstract = "A wide range of database applications manage
time-varying data. Many temporal query languages have
been proposed, each one the result of many carefully
made yet subtly interacting design decisions. In this
article we advocate a different approach to
articulating a set of requirements, or desiderata, that
directly imply the syntactic structure and core
semantics of a temporal extension of an (arbitrary)
nontemporal query language. These desiderata facilitate
transitioning applications from a nontemporal query
language and data model, which has received only scant
attention thus far. \par
The paper then introduces the notion of {\em statement
modifiers\/} that provide a means of systematically
adding temporal support to an existing query language.
Statement modifiers apply to all query language
statements, for example, queries, cursor definitions,
integrity constraints, assertions, views, and data
manipulation statements. We also provide a way to
systematically add temporal support to an existing
implementation. The result is a temporal query language
syntax, semantics, and implementation that derives from
first principles. \par
We exemplify this approach by extending SQL-92 with
statement modifiers. This extended language, termed
ATSQL, is formally defined via a
denotational-semantics-style mapping of temporal
statements to expressions using a combination of
temporal and conventional relational algebraic
operators.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Languages; Theory",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "ATSQL; statement modifiers; temporal databases",
subject = "Information Systems --- Database Management ---
Languages (H.2.3): {\bf Data manipulation languages
(DML)}; Information Systems --- Database Management ---
Systems (H.2.4): {\bf Query processing}; Information
Systems --- Database Management --- Systems (H.2.4):
{\bf Relational databases}; Information Systems ---
Database Management --- Languages (H.2.3): {\bf Data
description languages (DDL)}",
}
@Article{Fegaras:2000:OOQ,
author = "Leonidas Fegaras and David Maier",
title = "Optimizing object queries using an effective
calculus",
journal = j-TODS,
volume = "25",
number = "4",
pages = "457--516",
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 26 08:20:52 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-4/p457-fegaras/p457-fegaras.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-4/p457-fegaras/",
abstract = "Object-oriented databases (OODBs) provide powerful
data abstractions and modeling facilities, but they
generally lack a suitable framework for query
processing and optimization. The development of an
effective query optimizer is one of the key factors for
OODB systems to successfully compete with relational
systems, as well as to meet the performance
requirements of many nontraditional applications. We
propose an effective framework with a solid theoretical
basis for optimizing OODB query languages. Our
calculus, called the monoid comprehension calculus,
captures most features of ODMG OQL, and is a good basis
for expressing various optimization algorithms
concisely. This article concentrates on query unnesting
(also known as query decorrelation), an optimization
that, even though it improves performance considerably,
is not treated properly (if at all) by most OODB
systems. Our framework generalizes many unnesting
techniques proposed recently in the literature, and is
capable of removing any form of query nesting using a
very simple and efficient algorithm. The simplicity of
our method is due to the use of the monoid
comprehension calculus as an intermediate form for OODB
queries. The monoid comprehension calculus treats
operations over multiple collection types, aggregates,
and quantifiers in a similar way, resulting in a
uniform method of unnesting queries, regardless of
their type of nesting.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Design; Experimentation; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "nested relations; object-oriented databases; query
decorrelation; query optimization",
subject = "Information Systems --- Database Management ---
Logical Design (H.2.1); Information Systems ---
Database Management --- Systems (H.2.4): {\bf
Object-oriented databases}",
}
@Article{Kossmann:2000:CII,
author = "Donald Kossmann and Michael J. Franklin and Gerhard
Drasch and Wig Ag",
title = "Cache investment: integrating query optimization and
distributed data placement",
journal = j-TODS,
volume = "25",
number = "4",
pages = "517--558",
year = "2000",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 26 08:20:52 MDT 2001",
bibsource = "http://www.acm.org/pubs/toc/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.acm.org/pubs/articles/journals/tods/2000-25-4/p517-kossmann/p517-kossmann.pdf;
http://www.acm.org/pubs/citations/journals/tods/2000-25-4/p517-kossmann/",
abstract = "Emerging distributed query-processing systems support
flexible execution strategies in which each query can
be run using a combination of data shipping and query
shipping. As in any distributed environment, these
systems can obtain tremendous performance and
availability benefits by employing dynamic data
caching. When flexible execution and dynamic caching
are combined, however, a circular dependency arises:
Caching occurs as a by-product of query operator
placement, but query operator placement decisions are
based on (cached) data location. The practical impact
of this dependency is that query optimization decisions
that appear valid on a per-query basis can actually
cause suboptimal performance for all queries in the
long run. \par
To address this problem, we developed {\em Cache
Investment\/} - a novel approach for integrating query
optimization and data placement that looks beyond the
performance of a single query. Cache Investment
sometimes intentionally generates a ``suboptimal'' plan
for a particular query in the interest of effecting a
better data placement for subsequent queries. Cache
Investment can be integrated into a distributed
database system without changing the internals of the
query optimizer. In this paper, we propose Cache
Investment mechanisms and policies and analyze their
performance. The analysis uses results from both an
implementation on the SHORE storage manager and a
detailed simulation model. Our results show that Cache
Investment can significantly improve the overall
performance of a system and demonstrate the trade-offs
among various alternative policies.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
generalterms = "Algorithms; Performance",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cache investment; caching; client-server database
systems; data shipping; dynamic data placement; query
optimization; query shipping",
subject = "Information Systems --- Database Management ---
Systems (H.2.4): {\bf Distributed databases};
Information Systems --- Database Management --- Systems
(H.2.4): {\bf Relational databases}",
}
@Article{Andries:2001:AUM,
author = "Marc Andries and Luca Cabibbo and Jan Paredaens and
Jan van den Bussche",
title = "Applying an update method to a set of receivers",
journal = j-TODS,
volume = "26",
number = "1",
pages = "1--40",
month = mar,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:14:50 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dekhtyar:2001:PTD,
author = "Alex Dekhtyar and Robert Ross and V. S. Subrahmanian",
title = "Probabilistic temporal databases, {I}: algebra",
journal = j-TODS,
volume = "26",
number = "1",
pages = "41--95",
month = mar,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:14:50 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hsu:2001:RBP,
author = "Windsor W. Hsu and Alan Jay Smith and Honesty C.
Young",
title = "{I/O} reference behavior of production database
workloads and the {TPC} benchmarks --- an analysis at
the logical level",
journal = j-TODS,
volume = "26",
number = "1",
pages = "96--143",
month = mar,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:14:50 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chomicki:2001:QAD,
author = "Jan Chomicki and David Toman and Michael H.
B{\"o}hlen",
title = "Querying {ATSQL} databases with temporal logic",
journal = j-TODS,
volume = "26",
number = "2",
pages = "145--178",
month = jun,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fukuda:2001:DMO,
author = "Takeshi Fukuda and Yasuhiko Morimoto and Shimichi
Morishita and Takeshi Tokuyama",
title = "Data mining with optimized two-dimensional association
rules",
journal = j-TODS,
volume = "26",
number = "2",
pages = "179--213",
month = jun,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jajodia:2001:FSM,
author = "Sushil Jajodia and Pierangela Samarati and Maria Luisa
Sapino and V. S. Subrahmanian",
title = "Flexible support for multiple access control
policies",
journal = j-TODS,
volume = "26",
number = "2",
pages = "214--260",
month = jun,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Eiter:2001:POB,
author = "Thomas Eiter and James J. Lu and Thomas Lukasiewicz
and V. S. Subrahmanian",
title = "Probabilistic object bases",
journal = j-TODS,
volume = "26",
number = "3",
pages = "264--312",
month = sep,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2001:AQU,
author = "Chen Li and Edward Chang",
title = "Answering queries with useful bindings",
journal = j-TODS,
volume = "26",
number = "3",
pages = "313--343",
month = sep,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ng:2001:ERD,
author = "Wilfred Ng",
title = "An extension of the relational data model to
incorporate ordered domains",
journal = j-TODS,
volume = "26",
number = "3",
pages = "344--383",
month = sep,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:15 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kotidis:2001:CDV,
author = "Yannis Kotidis and Nick Roussopoulos",
title = "A case for dynamic view management",
journal = j-TODS,
volume = "26",
number = "4",
pages = "388--423",
month = dec,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:16 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Mamoulis:2001:MSJ,
author = "Nikos Mamoulis and Dimitris Papadias",
title = "Multiway spatial joins",
journal = j-TODS,
volume = "26",
number = "4",
pages = "424--475",
month = dec,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:16 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lakshmanan:2001:SES,
author = "Laks V. S. Lakshmanan and Fereidoon Sadri and Subbu N.
Subramanian",
title = "{SchemaSQL}: {An} extension to {SQL} for multidatabase
interoperability",
journal = j-TODS,
volume = "26",
number = "4",
pages = "476--519",
month = dec,
year = "2001",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Feb 19 16:12:16 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Suciu:2002:DQE,
author = "Dan Suciu",
title = "Distributed query evaluation on semistructured data",
journal = j-TODS,
volume = "27",
number = "1",
pages = "1--62",
month = mar,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schuldt:2002:AIT,
author = "Heiko Schuldt and Gustavo Alonso and Catriel Beeri and
Hans-J{\"o}rg Schek",
title = "Atomicity and isolation for transactional processes",
journal = j-TODS,
volume = "27",
number = "1",
pages = "63--116",
month = mar,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Liu:2002:LFD,
author = "Mengchi Liu and Gillian Dobbie and Tok Wang Ling",
title = "A logical foundation for deductive object-oriented
databases",
journal = j-TODS,
volume = "27",
number = "1",
pages = "117--151",
month = mar,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bruno:2002:TSQ,
author = "Nicolas Bruno and Surajit Chaudhuri and Luis Gravano",
title = "Top-$k$ selection queries over relational databases:
{Mapping} strategies and performance evaluation",
journal = j-TODS,
volume = "27",
number = "2",
pages = "153--187",
month = jun,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chakrabarti:2002:LAD,
author = "Kaushik Chakrabarti and Eamonn Keogh and Sharad
Mehrotra and Michael Pazzani",
title = "Locally adaptive dimensionality reduction for indexing
large time series databases",
journal = j-TODS,
volume = "27",
number = "2",
pages = "188--228",
month = jun,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Calders:2002:SDM,
author = "Toon Calders and Raymond T. Ng and Jef Wijsen",
title = "Searching for dependencies at multiple abstraction
levels",
journal = j-TODS,
volume = "27",
number = "3",
pages = "229--260",
month = sep,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gibbons:2002:FIM,
author = "Phillip B. Gibbons and Yossi Matias and Viswanath
Poosala",
title = "Fast incremental maintenance of approximate
histograms",
journal = j-TODS,
volume = "27",
number = "3",
pages = "261--298",
month = sep,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tao:2002:CMO,
author = "Yufei Tao and Dimitris Papadias and Jun Zhang",
title = "Cost models for overlapping and multiversion
structures",
journal = j-TODS,
volume = "27",
number = "3",
pages = "299--342",
month = sep,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:13 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{May:2002:UGS,
author = "Wolfgang May and Bertram Lud{\"a}scher",
title = "Understanding the global semantics of referential
actions using logic rules",
journal = j-TODS,
volume = "27",
number = "4",
pages = "343--397",
month = dec,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:14 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ciaccia:2002:SMS,
author = "Paolo Ciaccia and Marco Patella",
title = "Searching in metric spaces with user-defined and
approximate distances",
journal = j-TODS,
volume = "27",
number = "4",
pages = "398--437",
month = dec,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:14 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fernandez:2002:SFP,
author = "Mary Fern{\'a}ndez and Yana Kadiyska and Dan Suciu and
Atsuyuki Morishima and Wang-Chiew Tan",
title = "{SilkRoute}: a framework for publishing relational
data in {XML}",
journal = j-TODS,
volume = "27",
number = "4",
pages = "438--493",
month = dec,
year = "2002",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Nov 5 11:23:14 MST 2002",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Beneventano:2003:DLS,
author = "Domenico Beneventano and Sonia Bergamaschi and Claudio
Sartori",
title = "Description logics for semantic query optimization in
object-oriented database systems",
journal = j-TODS,
volume = "28",
number = "1",
pages = "1--50",
month = mar,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Karp:2003:SAF,
author = "Richard M. Karp and Scott Shenker and Christos H.
Papadimitriou",
title = "A simple algorithm for finding frequent elements in
streams and bags",
journal = j-TODS,
volume = "28",
number = "1",
pages = "51--55",
month = mar,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Melnik:2003:AAS,
author = "Sergey Melnik and Hector Garcia-Molina",
title = "Adaptive algorithms for set containment joins",
journal = j-TODS,
volume = "28",
number = "1",
pages = "56--99",
month = mar,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tao:2003:SQD,
author = "Yufei Tao and Dimitris Papadias",
title = "Spatial queries in dynamic environments",
journal = j-TODS,
volume = "28",
number = "2",
pages = "101--139",
month = jun,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gunopulos:2003:DAM,
author = "Dimitrios Gunopulos and Roni Khardon and Heikki
Mannila and Sanjeev Saluja and Hannu Toivonen and Ram
Sewak Sharma",
title = "Discovering all most specific sentences",
journal = j-TODS,
volume = "28",
number = "2",
pages = "140--174",
month = jun,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lechtenborger:2003:CRV,
author = "Jens Lechtenb{\"o}rger and Gottfried Vossen",
title = "On the computation of relational view complements",
journal = j-TODS,
volume = "28",
number = "2",
pages = "175--208",
month = jun,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 7 13:51:37 MDT 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wijesekera:2003:RPF,
author = "Duminda Wijesekera and Sushil Jajodia and Francesco
Parisi-Presicce and {\AA}sa Hagstr{\"o}m",
title = "Removing permissions in the flexible authorization
framework",
journal = j-TODS,
volume = "28",
number = "3",
pages = "209--229",
month = sep,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Oct 31 05:55:40 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jacox:2003:ISJ,
author = "Edwin H. Jacox and Hanan Samet",
title = "Iterative spatial join",
journal = j-TODS,
volume = "28",
number = "3",
pages = "230--256",
month = sep,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Oct 31 05:55:40 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jimenez-Peris:2003:QAD,
author = "Ricardo Jim{\'e}nez-Peris and M.
Pati{\~n}o-Mart{\'\i}nez and Gustavo Alonso and Bettina
Kemme",
title = "Are quorums an alternative for data replication?",
journal = j-TODS,
volume = "28",
number = "3",
pages = "257--294",
month = sep,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Oct 31 05:55:40 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tao:2003:APS,
author = "Yufei Tao and Jimeng Sun and Dimitris Papadias",
title = "Analysis of predictive spatio-temporal queries",
journal = j-TODS,
volume = "28",
number = "4",
pages = "295--336",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lakshmanan:2003:EDM,
author = "Laks V. S. Lakshmanan and Carson Kai-Sang Leung and
Raymond T. Ng",
title = "Efficient dynamic mining of constrained frequent
sets",
journal = j-TODS,
volume = "28",
number = "4",
pages = "337--389",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cho:2003:EPR,
author = "Junghoo Cho and Hector Garcia-Molina",
title = "Effective page refresh policies for {Web} crawlers",
journal = j-TODS,
volume = "28",
number = "4",
pages = "390--426",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chomicki:2003:PFR,
author = "Jan Chomicki",
title = "Preference formulas in relational queries",
journal = j-TODS,
volume = "28",
number = "4",
pages = "427--466",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Diao:2003:PSP,
author = "Yanlei Diao and Mehmet Altinel and Michael J. Franklin
and Hao Zhang and Peter Fischer",
title = "Path sharing and predicate evaluation for
high-performance {XML} filtering",
journal = j-TODS,
volume = "28",
number = "4",
pages = "467--516",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hjaltason:2003:IDS,
author = "Gisli R. Hjaltason and Hanan Samet",
title = "Index-driven similarity search in metric spaces",
journal = j-TODS,
volume = "28",
number = "4",
pages = "517--580",
month = dec,
year = "2003",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Dec 13 18:01:35 MST 2003",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kolaitis:2004:F,
author = "Phokion Kolaitis and Michael J. Franklin",
title = "Foreword",
journal = j-TODS,
volume = "29",
number = "1",
pages = "1--1",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Buneman:2004:ASD,
author = "Peter Buneman and Sanjeev Khanna and Keishi Tajima and
Wang-Chiew Tan",
title = "Archiving scientific data",
journal = j-TODS,
volume = "29",
number = "1",
pages = "2--42",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Garofalakis:2004:PWS,
author = "Minos Garofalakis and Phillip B. Gibbons",
title = "Probabilistic wavelet synopses",
journal = j-TODS,
volume = "29",
number = "1",
pages = "43--90",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Grust:2004:AXE,
author = "Torsten Grust and Maurice {Van Keulen} and Jens
Teubner",
title = "Accelerating {XPath} evaluation in any {RDBMS}",
journal = j-TODS,
volume = "29",
number = "1",
pages = "91--131",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ross:2004:SCM,
author = "Kenneth A. Ross",
title = "Selection conditions in main memory",
journal = j-TODS,
volume = "29",
number = "1",
pages = "132--161",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arasu:2004:CMR,
author = "Arvind Arasu and Brian Babcock and Shivnath Babu and
Jon McAlister and Jennifer Widom",
title = "Characterizing memory requirements for queries over
continuous data streams",
journal = j-TODS,
volume = "29",
number = "1",
pages = "162--194",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2004:NFX,
author = "Marcelo Arenas and Leonid Libkin",
title = "A normal form for {XML} documents",
journal = j-TODS,
volume = "29",
number = "1",
pages = "195--232",
month = mar,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Amer-Yahia:2004:DAO,
author = "Sihem Amer-Yahia and Sophie Cluet",
title = "A declarative approach to optimize bulk loading into
databases",
journal = j-TODS,
volume = "29",
number = "2",
pages = "233--281",
month = jun,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sadri:2004:EOS,
author = "Reza Sadri and Carlo Zaniolo and Amir Zarkesh and
Jafar Adibi",
title = "Expressing and optimizing sequence queries in database
systems",
journal = j-TODS,
volume = "29",
number = "2",
pages = "282--318",
month = jun,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Marian:2004:ETQ,
author = "Am{\'e}lie Marian and Nicolas Bruno and Luis Gravano",
title = "Evaluating top-$k$ queries over {Web}-accessible
databases",
journal = j-TODS,
volume = "29",
number = "2",
pages = "319--362",
month = jun,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yu:2004:CAM,
author = "Ting Yu and Divesh Srivastava and Laks V. S.
Lakshmanan and H. V. Jagadish",
title = "A compressed accessibility map for {XML}",
journal = j-TODS,
volume = "29",
number = "2",
pages = "363--402",
month = jun,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Datta:2004:PBA,
author = "Anindya Datta and Kaushik Dutta and Helen Thomas and
Debra Vandermeer and Krithi Ramamritham",
title = "Proxy-based acceleration of dynamically generated
content on the {World Wide Web}: {An} approach and
implementation",
journal = j-TODS,
volume = "29",
number = "2",
pages = "403--443",
month = jun,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Jul 10 10:03:25 MDT 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Vincent:2004:SFD,
author = "Millist W. Vincent and Jixue Liu and Chengfei Liu",
title = "Strong functional dependencies and their application
to normal forms in {XML}",
journal = j-TODS,
volume = "29",
number = "3",
pages = "445--462",
month = sep,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Nov 4 08:30:22 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Trajcevski:2004:MUM,
author = "Goce Trajcevski and Ouri Wolfson and Klaus Hinrichs
and Sam Chamberlain",
title = "Managing uncertainty in moving objects databases",
journal = j-TODS,
volume = "29",
number = "3",
pages = "463--507",
month = sep,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Nov 4 08:30:22 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chaudhuri:2004:EPM,
author = "Surajit Chaudhuri and Vivek Narasayya and Sunita
Sarawagi",
title = "Extracting predicates from mining models for efficient
query evaluation",
journal = j-TODS,
volume = "29",
number = "3",
pages = "508--544",
month = sep,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Nov 4 08:30:22 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Babu:2004:ECR,
author = "Shivnath Babu and Utkarsh Srivastava and Jennifer
Widom",
title = "Exploiting $k$-constraints to reduce memory overhead
in continuous queries over data streams",
journal = j-TODS,
volume = "29",
number = "3",
pages = "545--580",
month = sep,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Nov 4 08:30:22 MST 2004",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ozsoyoglu:2004:QWM,
author = "G{\"u}ltekin {\"O}zsoyo{\u{g}}lu and Ismail Seng{\"o}r
Alting{\"o}vde and Abdullah Al-Hamdani and Selma
Ay{\c{s}}e {\"O}zel and {\"O}zg{\"u}r Ulusoy and Zehra
Meral {\"o}zsoyo{\u{g}}lu",
title = "Querying {Web} metadata: {Native} score management and
text support in databases",
journal = j-TODS,
volume = "29",
number = "4",
pages = "581--634",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Baralis:2004:ECR,
author = "Elena Baralis and Silvia Chiusano",
title = "Essential classification rule sets",
journal = j-TODS,
volume = "29",
number = "4",
pages = "635--674",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chen:2004:MBV,
author = "Songting Chen and Bin Liu and Elke A. Rundensteiner",
title = "Multiversion-based view maintenance over distributed
data sources",
journal = j-TODS,
volume = "29",
number = "4",
pages = "675--709",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Balmin:2004:IVX,
author = "Andrey Balmin and Yannis Papakonstantinou and Victor
Vianu",
title = "Incremental validation of {XML} documents",
journal = j-TODS,
volume = "29",
number = "4",
pages = "710--751",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Green:2004:PXS,
author = "Todd J. Green and Ashish Gupta and Gerome Miklau and
Makoto Onizuka and Dan Suciu",
title = "Processing {XML} streams with deterministic automata
and stream indexes",
journal = j-TODS,
volume = "29",
number = "4",
pages = "752--788",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Samet:2004:DPG,
author = "Hanan Samet",
title = "Decoupling partitioning and grouping: {Overcoming}
shortcomings of spatial indexing with bucketing",
journal = j-TODS,
volume = "29",
number = "4",
pages = "789--830",
month = dec,
year = "2004",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 14 10:39:39 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Milo:2005:EIX,
author = "Tova Milo and Serge Abiteboul and Bernd Amann and Omar
Benjelloun and Fred Dang Ngoc",
title = "Exchanging intensional {XML} data",
journal = j-TODS,
volume = "30",
number = "1",
pages = "1--40",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papadias:2005:PSC,
author = "Dimitris Papadias and Yufei Tao and Greg Fu and
Bernhard Seeger",
title = "Progressive skyline computation in database systems",
journal = j-TODS,
volume = "30",
number = "1",
pages = "41--82",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Witkowski:2005:ASM,
author = "Andrew Witkowski and Srikanth Bellamkonda and Tolga
Bozkaya and Nathan Folkert and Abhinav Gupta and John
Haydu and Lei Sheng and Sankar Subramanian",
title = "Advanced {SQL} modeling in {RDBMS}",
journal = j-TODS,
volume = "30",
number = "1",
pages = "83--121",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Madden:2005:TAQ,
author = "Samuel R. Madden and Michael J. Franklin and Joseph M.
Hellerstein and Wei Hong",
title = "{TinyDB}: an acquisitional query processing system for
sensor networks",
journal = j-TODS,
volume = "30",
number = "1",
pages = "122--173",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fagin:2005:DEG,
author = "Ronald Fagin and Phokion G. Kolaitis and Lucian Popa",
title = "Data exchange: getting to the core",
journal = j-TODS,
volume = "30",
number = "1",
pages = "174--210",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pu:2005:CDS,
author = "Ken Q. Pu and Alberto O. Mendelzon",
title = "Concise descriptions of subsets of structured sets",
journal = j-TODS,
volume = "30",
number = "1",
pages = "211--248",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cormode:2005:WHW,
author = "Graham Cormode and S. Muthukrishnan",
title = "What's hot and what's not: tracking most frequent
items dynamically",
journal = j-TODS,
volume = "30",
number = "1",
pages = "249--278",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Garofalakis:2005:XSP,
author = "Minos Garofalakis and Amit Kumar",
title = "{XML} stream processing using tree-edit distance
embeddings",
journal = j-TODS,
volume = "30",
number = "1",
pages = "279--332",
month = mar,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat May 7 08:01:30 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Geerts:2005:TUB,
author = "Floris Geerts and Bart Goethals and Jan {Van Den
Bussche}",
title = "Tight upper bounds on the number of candidate
patterns",
journal = j-TODS,
volume = "30",
number = "2",
pages = "333--363",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jagadish:2005:IAB,
author = "H. V. Jagadish and Beng Chin Ooi and Kian-Lee Tan and
Cui Yu and Rui Zhang",
title = "{iDistance}: {An} adaptive {B$^+$}-tree based indexing
method for nearest neighbor search",
journal = j-TODS,
volume = "30",
number = "2",
pages = "364--397",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Braga:2005:XXU,
author = "Daniele Braga and Alessandro Campi and Stefano Ceri",
title = "{{\em XQBE} ({\em XQ\/}uery {\em B\/}y {\em
E\/}xample)}: a visual interface to the standard {XML}
query language",
journal = j-TODS,
volume = "30",
number = "2",
pages = "398--443",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gottlob:2005:EAP,
author = "Georg Gottlob and Christoph Koch and Reinhard
Pichler",
title = "Efficient algorithms for processing {XPath} queries",
journal = j-TODS,
volume = "30",
number = "2",
pages = "444--491",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fekete:2005:MSI,
author = "Alan Fekete and Dimitrios Liarokapis and Elizabeth
O'Neil and Patrick O'Neil and Dennis Shasha",
title = "Making snapshot isolation serializable",
journal = j-TODS,
volume = "30",
number = "2",
pages = "492--528",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papadias:2005:ANN,
author = "Dimitris Papadias and Yufei Tao and Kyriakos
Mouratidis and Chun Kit Hui",
title = "Aggregate nearest neighbor queries in spatial
databases",
journal = j-TODS,
volume = "30",
number = "2",
pages = "529--576",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Peng:2005:XSX,
author = "Feng Peng and Sudarshan S. Chawathe",
title = "{XSQ}: a streaming {XPath} engine",
journal = j-TODS,
volume = "30",
number = "2",
pages = "577--623",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wyss:2005:RLM,
author = "Catharine M. Wyss and Edward L. Robertson",
title = "Relational languages for metadata integration",
journal = j-TODS,
volume = "30",
number = "2",
pages = "624--660",
month = jun,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 7 14:14:12 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhang:2005:GMD,
author = "Rui Zhang and Panos Kalnis and Beng Chin Ooi and
Kian-Lee Tan",
title = "Generalized multidimensional data mapping and query
processing",
journal = j-TODS,
volume = "30",
number = "3",
pages = "661--697",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pang:2005:IMS,
author = "Chaoyi Pang and Guozhu Dong and Kotagiri
Ramamohanarao",
title = "Incremental maintenance of shortest distance and
transitive closure in first-order logic and {SQL}",
journal = j-TODS,
volume = "30",
number = "3",
pages = "698--721",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wijsen:2005:DRU,
author = "Jef Wijsen",
title = "Database repairing using updates",
journal = j-TODS,
volume = "30",
number = "3",
pages = "722--768",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Litwin:2005:LHA,
author = "Witold Litwin and Rim Moussa and Thomas Schwarz",
title = "{LH*RS}---a highly-available scalable distributed data
structure",
journal = j-TODS,
volume = "30",
number = "3",
pages = "769--811",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{He:2005:STC,
author = "Zhen He and Byung Suk Lee and Robert Snapp",
title = "Self-tuning cost modeling of user-defined functions in
an object-relational {DBMS}",
journal = j-TODS,
volume = "30",
number = "3",
pages = "812--853",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hurtado:2005:CSI,
author = "Carlos A. Hurtado and Claudio Gutierrez and Alberto O.
Mendelzon",
title = "Capturing summarizability with integrity constraints
in {OLAP}",
journal = j-TODS,
volume = "30",
number = "3",
pages = "854--886",
month = sep,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Oct 12 07:55:28 MDT 2005",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Suciu:2005:F,
author = "Dan Suciu and Gerhard Weikum",
title = "Foreword",
journal = j-TODS,
volume = "30",
number = "4",
pages = "887--887",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Garofalakis:2005:WSG,
author = "Minos Garofalakis and Amit Kumar",
title = "Wavelet synopses for general error metrics",
journal = j-TODS,
volume = "30",
number = "4",
pages = "888--928",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Marx:2005:CX,
author = "Maarten Marx",
title = "Conditional {XPath}",
journal = j-TODS,
volume = "30",
number = "4",
pages = "929--959",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yan:2005:GIB,
author = "Xifeng Yan and Philip S. Yu and Jiawei Han",
title = "Graph indexing based on discriminative frequent
structure analysis",
journal = j-TODS,
volume = "30",
number = "4",
pages = "960--993",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fagin:2005:CSM,
author = "Ronald Fagin and Phokion G. Kolaitis and Lucian Popa
and Wang-Chiew Tan",
title = "Composing schema mappings: {Second-order} dependencies
to the rescue",
journal = j-TODS,
volume = "30",
number = "4",
pages = "994--1055",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bowman:2005:OQS,
author = "Ivan T. Bowman and Kenneth Salem",
title = "Optimization of query streams using semantic
prefetching",
journal = j-TODS,
volume = "30",
number = "4",
pages = "1056--1101",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kaushik:2005:SQO,
author = "Raghav Kaushik and Jeffrey F. Naughton and Raghu
Ramakrishnan and Venkatesan T. Chakravarthy",
title = "Synopses for query optimization: a space-complexity
perspective",
journal = j-TODS,
volume = "30",
number = "4",
pages = "1102--1127",
month = dec,
year = "2005",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Feb 16 11:31:47 MST 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wu:2006:OBI,
author = "Kesheng Wu and Ekow J. Otoo and Arie Shoshani",
title = "Optimizing bitmap indices with efficient compression",
journal = j-TODS,
volume = "31",
number = "1",
pages = "1--38",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schneider:2006:TRB,
author = "Markus Schneider and Thomas Behr",
title = "Topological relationships between complex spatial
objects",
journal = j-TODS,
volume = "31",
number = "1",
pages = "39--81",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jaluta:2006:BTC,
author = "Ibrahim Jaluta and Seppo Sippu and Eljas
Soisalon-Soininen",
title = "{B}-tree concurrency control and recovery in
page-server database systems",
journal = j-TODS,
volume = "31",
number = "1",
pages = "82--132",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gray:2006:CTC,
author = "Jim Gray and Leslie Lamport",
title = "Consensus on transaction commit",
journal = j-TODS,
volume = "31",
number = "1",
pages = "133--160",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Guha:2006:IXD,
author = "Sudipto Guha and H. V. Jagadish and Nick Koudas and
Divesh Srivastava and Ting Yu",
title = "Integrating {XML} data sources using approximate
joins",
journal = j-TODS,
volume = "31",
number = "1",
pages = "161--207",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Abiteboul:2006:RQX,
author = "Serge Abiteboul and Luc Segoufin and Victor Vianu",
title = "Representing and querying {XML} with incomplete
information",
journal = j-TODS,
volume = "31",
number = "1",
pages = "208--254",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pelanis:2006:IPP,
author = "Mindaugas Pelanis and Simonas {\v{S}}altenis and
Christian S. Jensen",
title = "Indexing the past, present, and anticipated future
positions of moving objects",
journal = j-TODS,
volume = "31",
number = "1",
pages = "255--298",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Rao:2006:SXD,
author = "Praveen Rao and Bongki Moon",
title = "Sequencing {XML} data and query twigs for fast pattern
matching",
journal = j-TODS,
volume = "31",
number = "1",
pages = "299--345",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{He:2006:ACS,
author = "Bin He and Kevin Chen-Chuan Chang",
title = "Automatic complex schema matching across {Web} query
interfaces: a correlation mining approach",
journal = j-TODS,
volume = "31",
number = "1",
pages = "346--395",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Guha:2006:ASA,
author = "Sudipto Guha and Nick Koudas and Kyuseok Shim",
title = "Approximation and streaming algorithms for histogram
construction problems",
journal = j-TODS,
volume = "31",
number = "1",
pages = "396--438",
month = mar,
year = "2006",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri May 26 08:20:49 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Qian:2006:DIM,
author = "Gang Qian and Qiang Zhu and Qiang Xue and Sakti
Pramanik",
title = "Dynamic indexing for multidimensional non-ordered
discrete data spaces using a data-partitioning
approach",
journal = j-TODS,
volume = "31",
number = "2",
pages = "439--484",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138395",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Iwerks:2006:MNS,
author = "Glenn S. Iwerks and Hanan Samet and Kenneth P. Smith",
title = "Maintenance of {$K$}-nn and spatial join queries on
continuously moving points",
journal = j-TODS,
volume = "31",
number = "2",
pages = "485--536",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138396",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pentaris:2006:QOD,
author = "Fragkiskos Pentaris and Yannis Ioannidis",
title = "Query optimization in distributed networks of
autonomous database systems",
journal = j-TODS,
volume = "31",
number = "2",
pages = "537--583",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138397",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lin:2006:SLT,
author = "Xuemin Lin and Qing Liu and Yidong Yuan and Xiaofang
Zhou and Hongjun Lu",
title = "Summarizing level-two topological relations in large
spatial datasets",
journal = j-TODS,
volume = "31",
number = "2",
pages = "584--630",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138398",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bright:2006:APB,
author = "Laura Bright and Avigdor Gal and Louiqa Raschid",
title = "Adaptive pull-based policies for wide area data
delivery",
journal = j-TODS,
volume = "31",
number = "2",
pages = "631--671",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138399",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cohen:2006:RQA,
author = "Sara Cohen and Werner Nutt and Yehoshua Sagiv",
title = "Rewriting queries with arbitrary aggregation functions
using views",
journal = j-TODS,
volume = "31",
number = "2",
pages = "672--715",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138400",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kalashnikov:2006:DID,
author = "Dmitri V. Kalashnikov and Sharad Mehrotra",
title = "Domain-independent data cleaning via analysis of
entity-relationship graph",
journal = j-TODS,
volume = "31",
number = "2",
pages = "716--767",
month = jun,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1138394.1138401",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 14 10:11:33 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Eiter:2006:ISI,
author = "Thomas Eiter and Leonid Libkin",
title = "Introduction to special {ICDT} section",
journal = j-TODS,
volume = "31",
number = "3",
pages = "769--769",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166075",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Martens:2006:ECX,
author = "Wim Martens and Frank Neven and Thomas Schwentick and
Geert Jan Bex",
title = "Expressiveness and complexity of {XML Schema}",
journal = j-TODS,
volume = "31",
number = "3",
pages = "770--813",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166076",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Shaft:2006:TNN,
author = "Uri Shaft and Raghu Ramakrishnan",
title = "Theory of nearest neighbors indexability",
journal = j-TODS,
volume = "31",
number = "3",
pages = "814--838",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166077",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Braganholo:2006:PFA,
author = "Vanessa P. Braganholo and Susan B. Davidson and Carlos
A. Heuser",
title = "{PATAX{\'O}}: a framework to allow updates through
{XML} views",
journal = j-TODS,
volume = "31",
number = "3",
pages = "839--886",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166078",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Harizopoulos:2006:IIC,
author = "Stavros Harizopoulos and Anastassia Ailamaki",
title = "Improving instruction cache performance in {OLTP}",
journal = j-TODS,
volume = "31",
number = "3",
pages = "887--920",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166079",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Shao:2006:TNV,
author = "Feng Shao and Antal Novak and Jayavel
Shanmugasundaram",
title = "Triggers over nested views of relational data",
journal = j-TODS,
volume = "31",
number = "3",
pages = "921--967",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166080",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{May:2006:SQU,
author = "Norman May and Sven Helmer and Guido Moerkotte",
title = "Strategies for query unnesting in {XML} databases",
journal = j-TODS,
volume = "31",
number = "3",
pages = "968--1013",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166081",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Polyzotis:2006:XSX,
author = "Neoklis Polyzotis and Minos Garofalakis",
title = "{XSKETCH} synopses for {XML} data graphs",
journal = j-TODS,
volume = "31",
number = "3",
pages = "1014--1063",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166082",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sugumaran:2006:RDO,
author = "Vijayan Sugumaran and Veda C. Storey",
title = "The role of domain ontologies in database design: {An}
ontology management and conceptual modeling
environment",
journal = j-TODS,
volume = "31",
number = "3",
pages = "1064--1094",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166083",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Metwally:2006:IES,
author = "Ahmed Metwally and Divyakant Agrawal and Amr {El
Abbadi}",
title = "An integrated efficient solution for computing
frequent and top-$k$ elements in data streams",
journal = j-TODS,
volume = "31",
number = "3",
pages = "1095--1133",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166084",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See comments in \cite{Liu:2010:CIE}.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chaudhuri:2006:PIR,
author = "Surajit Chaudhuri and Gautam Das and Vagelis Hristidis
and Gerhard Weikum",
title = "Probabilistic information retrieval approach for
ranking of database query results",
journal = j-TODS,
volume = "31",
number = "3",
pages = "1134--1168",
month = sep,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1166074.1166085",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 17 05:41:01 MDT 2006",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Calders:2006:EPA,
author = "Toon Calders and Laks V. S. Lakshmanan and Raymond T.
Ng and Jan Paredaens",
title = "Expressive power of an algebra for data mining",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1169--1214",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189770",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The relational data model has simple and clear
foundations on which significant theoretical and
systems research has flourished. By contrast, most
research on data mining has focused on algorithmic
issues. A major open question is: what's an appropriate
foundation for data mining, which can accommodate
disparate mining tasks? We address this problem by
presenting a database model and an algebra for data
mining. The database model is based on the 3W-model
introduced by Johnson et al. [2000]. This model relied
on black box mining operators. A main contribution of
this article is to open up these black boxes, by using
generic operators in a data mining algebra. Two key
operators in this algebra are regionize, which creates
regions (or models) from data tuples, and a restricted
form of looping called mining loop. Then the resulting
data mining algebra MA is studied and properties
concerning expressive power and complexity are
established. We present results in three directions:
(1) expressiveness of the mining algebra; (2) relations
with alternative frameworks, and (3) interactions
between regionize and mining loop.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Algebra; data mining; expressive power",
}
@Article{Koch:2006:CNX,
author = "Christoph Koch",
title = "On the complexity of nonrecursive {XQuery} and
functional query languages on complex values",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1215--1256",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189771",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article studies the complexity of evaluating
functional query languages for complex values such as
monad algebra and the recursion-free fragment of
XQuery. We show that monad algebra, with equality
restricted to atomic values, is complete for the class
TA[2 O ( n ), O ( n )] of problems solvable in linear
exponential time with a linear number of alternations
if the query is assumed to be part of the input. The
monotone fragment of monad algebra with atomic value
equality but without negation is NEXPTIME-complete. For
monad algebra with deep value equality, that is,
equality of complex values, we establish TA[2 O ( n ),
O ( n )] lower and exponential-space upper bounds. We
also study a fragment of XQuery, Core XQuery, that
seems to incorporate all the features of a query
language on complex values that are traditionally
deemed essential. A close connection between monad
algebra on lists and Core XQuery (with ``child'' as the
only axis) is exhibited. The two languages are shown
expressively equivalent up to representation issues. We
show that Core XQuery is just as hard as monad algebra
with respect to query and combined complexity. As Core
XQuery is NEXPTIME-hard, the best-known techniques for
processing such problems require exponential amounts of
working memory and doubly exponential time in the worst
case. We present a property of queries---the lack of a
certain form of composition---that virtually all
real-world XQueries have and that allows for query
evaluation in PSPACE and thus singly exponential time.
Still, we are able to show for an important special
case---Core XQuery with equality testing restricted to
atomic values---that the composition-free language is
just as expressive as the language with composition.
Thus, under widely-held complexity-theoretic
assumptions, the language with composition is an
exponentially more succinct version of the
composition-free language.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Complex values; complexity; conservativity;
expressiveness; monad algebra; nested-relational
algebra; XML; XQuery",
}
@Article{Ilyas:2006:ARA,
author = "Ihab F. Ilyas and Walid G. Aref and Ahmed K.
Elmagarmid and Hicham G. Elmongui and Rahul Shah and
Jeffrey Scott Vitter",
title = "Adaptive rank-aware query optimization in relational
databases",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1257--1304",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189772",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Rank-aware query processing has emerged as a key
requirement in modern applications. In these
applications, efficient and adaptive evaluation of top-
k queries is an integral part of the application
semantics. In this article, we introduce a rank-aware
query optimization framework that fully integrates
rank-join operators into relational query engines. The
framework is based on extending the System R dynamic
programming algorithm in both enumeration and pruning.
We define ranking as an interesting physical property
that triggers the generation of rank-aware query plans.
Unlike traditional join operators, optimizing for
rank-join operators depends on estimating the input
cardinality of these operators. We introduce a
probabilistic model for estimating the input
cardinality, and hence the cost of a rank-join
operator. To our knowledge, this is the first effort in
estimating the needed input size for optimal rank
aggregation algorithms. Costing ranking plans is key to
the full integration of rank-join operators in
real-world query processing engines. Since optimal
execution strategies picked by static query optimizers
lose their optimality due to estimation errors and
unexpected changes in the computing environment, we
introduce several adaptive execution strategies for
top- k queries that respond to these unexpected changes
and costing errors. Our reactive reoptimization
techniques change the execution plan at runtime to
significantly enhance the performance of running
queries. Since top- k query plans are usually pipelined
and maintain a complex ranking state, altering the
execution strategy of a running ranking query is an
important and challenging task. We conduct an extensive
experimental study to evaluate the performance of the
proposed framework. The experimental results are
twofold: (1) we show the effectiveness of our
cost-based approach of integrating ranking plans in
dynamic programming cost-based optimizers; and (2) we
show a significant speedup (up to 300\%) when using our
adaptive execution of ranking plans over the
state-of-the-art mid-query reoptimization strategies.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "adaptive processing; Advanced query processing;
rank-aware optimization; ranking; top-k",
}
@Article{Jiao:2006:MSS,
author = "Yishan Jiao",
title = "Maintaining stream statistics over multiscale sliding
windows",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1305--1334",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189773",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we propose a new multiscale sliding
window model which differentiates data items in
different time periods of the data stream, based on a
reasonable monotonicity of resolution assumption. Our
model, as a well-motivated extension of the sliding
window model, stands halfway between the traditional
all-history and time-decaying models. We also present
algorithms for estimating two significant data stream
statistics--- $ F_0 $ and Jacard's similarity
coefficient---with reasonable accuracies under the new
model. Our algorithms use space logarithmic in the data
stream size and linear in the number of windows; they
support update time logarithmic in the number of
windows and independent of the accuracy required. Our
algorithms are easy to implement. Experimental results
demonstrate the efficiencies of our algorithms. Our
techniques apply to scenarios in which universe
sampling is used.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data stream; F 0; Jacard's similarity coefficient;
multiscale sliding window model",
}
@Article{Pei:2006:TMS,
author = "Jian Pei and Yidong Yuan and Xuemin Lin and Wen Jin
and Martin Ester and Qing Liu and Wei Wang and Yufei
Tao and Jeffrey Xu Yu and Qing Zhang",
title = "Towards multidimensional subspace skyline analysis",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1335--1381",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189774",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The skyline operator is important for multicriteria
decision-making applications. Although many recent
studies developed efficient methods to compute skyline
objects in a given space, none of them considers
skylines in multiple subspaces simultaneously. More
importantly, the fundamental problem on the semantics
of skylines remains open: Why and in which subspaces is
(or is not) an object in the skyline? Practically,
users may also be interested in the skylines in any
subspaces. Then, what is the relationship between the
skylines in the subspaces and those in the
super-spaces? How can we effectively analyze the
subspace skylines? Can we efficiently compute skylines
in various subspaces and answer various analytical
queries?In this article, we tackle the problem of
multidimensional subspace skyline computation and
analysis. We explore skylines in subspaces. First, we
propose the concept of Skycube, which consists of
skylines of all possible nonempty subspaces of a given
full space. Once a Skycube is materialized, any
subspace skyline queries can be answered online.
However, Skycube cannot fully address the semantic
concerns and may contain redundant information. To
tackle the problem, we introduce a novel notion of
skyline group which essentially is a group of objects
that coincide in the skylines of some subspaces. We
identify the decisive subspaces that qualify skyline
groups in the subspace skylines. The new notions
concisely capture the semantics and the structures of
skylines in various subspaces. Multidimensional roll-up
and drill-down analysis is introduced. We also develop
efficient algorithms to compute Skycube, skyline groups
and their decisive subspaces. A systematic performance
study using both real data sets and synthetic data sets
is reported to evaluate our approach.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data cubing; multidimensional data analysis; Skyline
query",
}
@Article{Jermaine:2006:SMS,
author = "Christopher Jermaine and Alin Dobra and Subramanian
Arumugam and Shantanu Joshi and Abhijit Pol",
title = "The {Sort-Merge-Shrink} join",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1382--1416",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189775",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "One of the most common operations in analytic query
processing is the application of an aggregate function
to the result of a relational join. We describe an
algorithm called the Sort-Merge-Shrink (SMS) Join for
computing the answer to such a query over large,
disk-based input tables. The key innovation of the SMS
join is that if the input data are clustered in a
statistically random fashion on disk, then at all
times, the join provides an online, statistical
estimator for the eventual answer to the query as well
as probabilistic confidence bounds. Thus, a user can
monitor the progress of the join throughout its
execution and stop the join when satisfied with the
estimate's accuracy or run the algorithm to completion
with a total time requirement that is not much longer
than that of other common join algorithms. This
contrasts with other online join algorithms, which
either do not offer such statistical guarantees or can
only offer guarantees so long as the input data can fit
into main memory.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "nonparametric statistics; OLAP; Online algorithms",
}
@Article{Afrati:2006:FSS,
author = "Foto Afrati and Jennifer Widom",
title = "Foreword to special section on {SIGMOD\slash PODS}
2005",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1417--1417",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189776",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yan:2006:FBS,
author = "Xifeng Yan and Feida Zhu and Philip S. Yu and Jiawei
Han",
title = "Feature-based similarity search in graph structures",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1418--1453",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189777",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Similarity search of complex structures is an
important operation in graph-related applications since
exact matching is often too restrictive. In this
article, we investigate the issues of substructure
similarity search using indexed features in graph
databases. By transforming the edge relaxation ratio of
a query graph into the maximum allowed feature misses,
our structural filtering algorithm can filter graphs
without performing pairwise similarity computation. It
is further shown that using either too few or too many
features can result in poor filtering performance. Thus
the challenge is to design an effective feature set
selection strategy that could maximize the filtering
capability. We prove that the complexity of optimal
feature set selection is $ \Omega (2^m) $ in the worst
case, where $m$ is the number of features for
selection. In practice, we identify several criteria to
build effective feature sets for filtering, and
demonstrate that combining features with similar size
and selectivity can improve the filtering and search
performance significantly within a multifilter
composition framework. The proposed feature-based
filtering concept can be generalized and applied to
searching approximate nonconsecutive sequences, trees,
and other structured data as well.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "complexity; Graph database; index; similarity search",
}
@Article{Fuxman:2006:PDE,
author = "Ariel Fuxman and Phokion G. Kolaitis and Ren{\'e}e J.
Miller and Wang-Chiew Tan",
title = "Peer data exchange",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1454--1498",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189778",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we introduce and study a framework,
called peer data exchange, for sharing and exchanging
data between peers. This framework is a special case of
a full-fledged peer data management system and a
generalization of data exchange between a source schema
and a target schema. The motivation behind peer data
exchange is to model authority relationships between
peers, where a source peer may contribute data to a
target peer, specified using source-to-target
constraints, and a target peer may use target-to-source
constraints to restrict the data it is willing to
receive, but cannot modify the data of the source
peer.A fundamental algorithmic problem in this
framework is that of deciding the existence of a
solution: given a source instance and a target instance
for a fixed peer data exchange setting, can the target
instance be augmented in such a way that the source
instance and the augmented target instance satisfy all
constraints of the setting? We investigate the
computational complexity of the problem for peer data
exchange settings in which the constraints are given by
tuple generating dependencies. We show that this
problem is always in NP, and that it can be NP-complete
even for ``acyclic'' peer data exchange settings. We
also show that the data complexity of the certain
answers of target conjunctive queries is in coNP, and
that it can be coNP-complete even for ``acyclic'' peer
data exchange settings. After this, we explore the
boundary between tractability and intractability for
deciding the existence of a solution and for computing
the certain answers of target conjunctive queries. To
this effect, we identify broad syntactic conditions on
the constraints between the peers under which the
existence-of-solutions problem is solvable in
polynomial time. We also identify syntactic conditions
between peer data exchange settings and target
conjunctive queries that yield polynomial-time
algorithms for computing the certain answers. For both
problems, these syntactic conditions turn out to be
tight, in the sense that minimal relaxations of them
lead to intractability. Finally, we introduce the
concept of a universal basis of solutions in peer data
exchange and explore its properties.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "certain answers; conjunctive queries; Data exchange;
data integration; metadata model management; schema
mapping",
}
@Article{Cheng:2006:DMM,
author = "David Cheng and Ravi Kannan and Santosh Vempala and
Grant Wang",
title = "A divide-and-merge methodology for clustering",
journal = j-TODS,
volume = "31",
number = "4",
pages = "1499--1525",
month = dec,
year = "2006",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1189769.1189779",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:31 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We present a divide-and-merge methodology for
clustering a set of objects that combines a top-down
``divide'' phase with a bottom-up ``merge'' phase. In
contrast, previous algorithms use either top-down or
bottom-up methods to construct a hierarchical
clustering or produce a flat clustering using local
search (e.g., k -means). For the divide phase, which
produces a tree whose leaves are the elements of the
set, we suggest an efficient spectral algorithm. When
the data is in the form of a sparse document-term
matrix, we show how to modify the algorithm so that it
maintains sparsity and runs in linear space. The merge
phase quickly finds the optimal partition that respects
the tree for many natural objective functions, for
example, k -means, min-diameter, min-sum, correlation
clustering, etc. We present a thorough experimental
evaluation of the methodology. We describe the
implementation of a meta-search engine that uses this
methodology to cluster results from web searches. We
also give comparative empirical results on several real
datasets.",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Clustering; data mining; information retrieval",
}
@Article{Snodgrass:2007:ESV,
author = "Richard T. Snodgrass",
title = "Editorial: {Single}- versus double-blind reviewing",
journal = j-TODS,
volume = "32",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206050",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This editorial analyzes from a variety of perspectives
the controversial issue of single-blind versus
double-blind reviewing. In single-blind reviewing, the
reviewer is unknown to the author, but the identity of
the author is known to the reviewer. Double-blind
reviewing is more symmetric: The identity of the author
and the reviewer are not revealed to each other. We
first examine the significant scholarly literature
regarding blind reviewing. We then list six benefits
claimed for double-blind reviewing and 21 possible
costs. To compare these benefits and costs, we propose
a double-blind policy for TODS that attempts to
minimize the costs while retaining the core benefit of
fairness that double-blind reviewing provides, and
evaluate that policy against each of the listed
benefits and costs. Following that is a general
discussion considering several questions: What does
this have to do with TODS, does bias exist in computer
science, and what is the appropriate decision
procedure? We explore the ``knobs'' a policy design can
manipulate to fine-tune a double-blind review policy.
This editorial ends with a specific decision.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Anonymous citation; blinding efficacy; double-blind
review; gender bias; single-blind review; status bias",
}
@Article{Pourabbas:2007:EEJ,
author = "Elaheh Pourabbas and Arie Shoshani",
title = "Efficient estimation of joint queries from multiple
{OLAP} databases",
journal = j-TODS,
volume = "32",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206051",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Given an OLAP query expressed over multiple source
OLAP databases, we study the problem of estimating the
resulting OLAP target database. The problem arises when
it is not possible to derive the result from a single
database. The method we use is linear indirect
estimation, commonly used for statistical estimation.
We examine two obvious computational methods for
computing such a target database, called the full
cross-product (F) and preaggregation (P) methods. We
study the accuracy and computational cost of these
methods. While the F method provides a more accurate
estimate, it is more expensive computationally than P.
Our contribution is in proposing a third, new method,
called the partial preaggregation method (PP), which is
significantly less expensive than F, but just as
accurate. We prove formally that the PP method yields
the same results as the F method, and provide
analytical and experimental results on the accuracy and
computational benefits of the PP method.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "multiple summary databases; OLAP; query estimation",
}
@Article{Olteanu:2007:FNS,
author = "Dan Olteanu",
title = "Forward node-selecting queries over trees",
journal = j-TODS,
volume = "32",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206052",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Node-selecting queries over trees lie at the core of
several important XML languages for the web, such as
the node-selection language XPath, the query language
XQuery, and the transformation language XSLT. The main
syntactic constructs of such queries are the backward
predicates, for example, ancestor and preceding, and
the forward predicates, for example, descendant and
following. Forward predicates are included in the
depth-first, left-to-right preorder relation associated
with the input tree, whereas backward predicates are
included in the inverse of this preorder
relation.\par
This work is devoted to an expressiveness study of
node-selecting queries with proven theoretical and
practical applicability, especially in the field of
query evaluation against XML streams. The main question
it answers positively is whether, for each input query
with forward and backward predicates, there exists an
equivalent forward-only output query. This question is
then positively answered for input and output queries
of varying structural complexity, using LOGLIN and
PSPACE reductions.\par
Various existing applications based on the results of
this work are reported, including query optimization
and streamed evaluation.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Expressiveness; rewriting; streams; XML; XPath",
}
@Article{Nash:2007:CMG,
author = "Alan Nash and Philip A. Bernstein and Sergey Melnik",
title = "Composition of mappings given by embedded
dependencies",
journal = j-TODS,
volume = "32",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206053",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Composition of mappings between schemas is essential
to support schema evolution, data exchange, data
integration, and other data management tasks. In many
applications, mappings are given by embedded
dependencies. In this article, we study the issues
involved in composing such mappings.\par
Our algorithms and results extend those of Fagin et al.
[2004], who studied the composition of mappings given
by several kinds of constraints. In particular, they
proved that full source-to-target tuple-generating
dependencies (tgds) are closed under composition, but
embedded source-to-target tgds are not. They introduced
a class of second-order constraints, SO tgds, that is
closed under composition and has desirable properties
for data exchange.\par
We study constraints that need not be source-to-target
and we concentrate on obtaining (first-order) embedded
dependencies. As part of this study, we also consider
full dependencies and second-order constraints that
arise from Skolemizing embedded dependencies. For each
of the three classes of mappings that we study, we
provide: (a) an algorithm that attempts to compute the
composition; and (b) sufficient conditions on the input
mappings which guarantee that the algorithm will
succeed.\par
In addition, we give several negative results. In
particular, we show that full and second-order
dependencies that are not limited to be
source-to-target are not closed under composition (for
the latter, under the additional restriction that no
new function symbols are introduced). Furthermore, we
show that determining whether the composition can be
given by these kinds of dependencies is undecidable.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "database theory; Metadata management",
}
@Article{Hwang:2007:OTK,
author = "Seung-won Hwang and Kevin Chen-chuan Chang",
title = "Optimizing top-k queries for middleware access: a
unified cost-based approach",
journal = j-TODS,
volume = "32",
number = "1",
pages = "5:1--5:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206054",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article studies optimizing top- k queries in
middlewares. While many assorted algorithms have been
proposed, none is generally applicable to a wide range
of possible scenarios. Existing algorithms lack both
the ``generality'' to support a wide range of access
scenarios and the systematic ``adaptivity'' to account
for runtime specifics. To fulfill this critical
lacking, we aim at taking a cost-based optimization
approach: By runtime search over a space of algorithms,
cost-based optimization is general across a wide range
of access scenarios, yet adaptive to the specific
access costs at runtime. While such optimization has
been taken for granted for relational queries from
early on, it has been clearly lacking for ranked
queries. In this article, we thus identify and address
the barriers of realizing such a unified framework. As
the first barrier, we need to define a
``comprehensive'' space encompassing all possibly
optimal algorithms to search over. As the second
barrier and a conflicting goal, such a space should
also be ``focused'' enough to enable efficient search.
For SQL queries that are explicitly composed of
relational operators, such a space, by definition,
consists of schedules of relational operators (or
``query plans''). In contrast, top- k queries do not
have logical tasks, such as relational operators. We
thus define the logical tasks of top- k queries as
building blocks to identify a comprehensive and focused
space for top- k queries. We then develop efficient
search schemes over such space for identifying the
optimal algorithm. Our study indicates that our
framework not only unifies, but also outperforms
existing algorithms specifically designed for their
scenarios.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "middlewares; Top-k query processing",
}
@Article{Ceri:2007:MCV,
author = "Stefano Ceri and Francesco {Di Giunta} and Pier Luca
Lanzi",
title = "Mining constraint violations",
journal = j-TODS,
volume = "32",
number = "1",
pages = "6:1--6:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206055",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we introduce pesudoconstraints, a
novel data mining pattern aimed at identifying rare
events in databases. At first, we formally define
pesudoconstraints using a probabilistic model and
provide a statistical test to identify
pesudoconstraints in a database. Then, we focus on a
specific class of pesudoconstraints, named cycle
pesudoconstraints, which often occur in databases. We
define cycle pesudoconstraints in the context of the ER
model and present an automatic method for detecting
cycle pesudoconstraints from a relational database.
Finally, we present an experiment to show cycle
pesudoconstraints ``at work'' on real data.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Deviation detection; probabilistic models; relational
data mining",
}
@Article{Jacox:2007:SJT,
author = "Edwin H. Jacox and Hanan Samet",
title = "Spatial join techniques",
journal = j-TODS,
volume = "32",
number = "1",
pages = "7:1--7:??",
month = mar,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1206049.1206056",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:36:55 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A variety of techniques for performing a spatial join
are reviewed. Instead of just summarizing the
literature and presenting each technique in its
entirety, distinct components of the different
techniques are described and each is decomposed into an
overall framework for performing a spatial join. A
typical spatial join technique consists of the
following components: partitioning the data, performing
internal-memory spatial joins on subsets of the data,
and checking if the full polygons intersect. Each
technique is decomposed into these components and each
component addressed in a separate section so as to
compare and contrast similar aspects of each technique.
The goal of this survey is to describe the algorithms
within each component in detail, comparing and
contrasting competing methods, thereby enabling further
analysis and experimentation with each component and
allowing the best algorithms for a particular situation
to be built piecemeal, or, even better, enabling an
optimizer to choose which algorithms to use.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "External memory algorithms; plane-sweep; spatial
join",
}
@Article{Athitsos:2007:QSE,
author = "Vassilis Athitsos and Marios Hadjieleftheriou and
George Kollios and Stan Sclaroff",
title = "Query-sensitive embeddings",
journal = j-TODS,
volume = "32",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242525",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A common problem in many types of databases is
retrieving the most similar matches to a query object.
Finding these matches in a large database can be too
slow to be practical, especially in domains where
objects are compared using computationally expensive
similarity (or distance) measures. Embedding methods
can significantly speed-up retrieval by mapping objects
into a vector space, where distances can be measured
rapidly using a Minkowski metric. In this article we
present a novel way to improve embedding quality. In
particular, we propose to construct embeddings that use
a query-sensitive distance measure for the target space
of the embedding. This distance measure is used to
compare those vectors that the query and database
objects are mapped to. The term ``query-sensitive''
means that the distance measure changes, depending on
the current query object. We demonstrate theoretically
that using a query-sensitive distance measure increases
the modeling power of embeddings and allows them to
capture more of the structure of the original space. We
also demonstrate experimentally that query-sensitive
embeddings can significantly improve retrieval
performance. In experiments with an image database of
handwritten digits and a time-series database, the
proposed method outperforms existing state-of-the-art
non-Euclidean indexing methods, meaning that it
provides significantly better tradeoffs between
efficiency and retrieval accuracy.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Embedding methods; nearest-neighbor retrieval;
non-Euclidean spaces; nonmetric spaces; similarity
matching",
}
@Article{Chaudhuri:2007:OSS,
author = "Surajit Chaudhuri and Gautam Das and Vivek Narasayya",
title = "Optimized stratified sampling for approximate query
processing",
journal = j-TODS,
volume = "32",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242526",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The ability to approximately answer aggregation
queries accurately and efficiently is of great benefit
for decision support and data mining tools. In contrast
to previous sampling-based studies, we treat the
problem as an optimization problem where, given a
workload of queries, we select a stratified random
sample of the original data such that the error in
answering the workload queries using the sample is
minimized. A key novelty of our approach is that we can
tailor the choice of samples to be robust, even for
workloads that are ``similar'' but not necessarily
identical to the given workload. Finally, our
techniques recognize the importance of taking into
account the variance in the data distribution in a
principled manner. We show how our solution can be
implemented on a database system, and present results
of extensive experiments on Microsoft SQL Server that
demonstrate the superior quality of our method compared
to previous work.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximation; query processing; Random sampling",
}
@Article{Deligiannakis:2007:EWM,
author = "Antonios Deligiannakis and Minos Garofalakis and Nick
Roussopoulos",
title = "Extended wavelets for multiple measures",
journal = j-TODS,
volume = "32",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242527",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Several studies have demonstrated the effectiveness of
the Haar wavelet decomposition as a tool for reducing
large amounts of data down to compact wavelet synopses
that can be used to obtain fast, accurate approximate
answers to user queries. Although originally designed
for minimizing the overall mean-squared (i.e., $ L^2
$-norm) error in the data approximation, recently
proposed methods also enable the use of Haar wavelets
in minimizing other error metrics, such as the relative
error in data value reconstruction, which is arguably
the most important for approximate query answers.
Relatively little attention, however, has been paid to
the problem of using wavelet synopses as an approximate
query answering tool over complex tabular datasets
containing multiple measures, such as those typically
found in real-life OLAP applications. Existing
decomposition approaches will either operate on each
measure individually, or treat all measures as a vector
of values and process them simultaneously. As we
demonstrate in this article, these existing individual
or combined storage approaches for the wavelet
coefficients of different measures can easily lead to
suboptimal storage utilization, resulting in
drastically reduced accuracy for approximate query
answers. To address this problem, in this work, we
introduce the notion of an extended wavelet coefficient
as a flexible, efficient storage method for wavelet
coefficients over multimeasure data. We also propose
novel algorithms for constructing effective (optimal or
near-optimal) extended wavelet-coefficient synopses
under a given storage constraint, for both sum-squared
error and relative-error norms. Experimental results
with both real-life and synthetic datasets validate our
approach, demonstrating that our techniques
consistently obtain significant gains in approximation
accuracy compared to existing solutions.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate query processing; data synopses;
Wavelets",
}
@Article{Rusu:2007:PRN,
author = "Florin Rusu and Alin Dobra",
title = "Pseudo-random number generation for sketch-based
estimations",
journal = j-TODS,
volume = "32",
number = "2",
pages = "11:1--11:48",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242528",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The exact computation of aggregate queries, like the
size of join of two relations, usually requires large
amounts of memory (constrained in data-streaming) or
communication (constrained in distributed computation)
and large processing times. In this situation,
approximation techniques with provable guarantees, like
sketches, are one possible solution. The performance of
sketches depends crucially on the ability to generate
particular pseudo-random numbers. In this article we
investigate both theoretically and empirically the
problem of generating k -wise independent pseudo-random
numbers and, in particular, that of generating 3- and
4-wise independent pseudo-random numbers that are fast
range-summable (i.e., they can be summed in sublinear
time). Our specific contributions are: (a) we provide a
thorough comparison of the various pseudo-random number
generating schemes; (b) we study both theoretically and
empirically the fast range-summation property of 3- and
4-wise independent generating schemes; (c) we provide
algorithms for the fast range-summation of two 3-wise
independent schemes, BCH and extended Hamming; and (d)
we show convincing theoretical and empirical evidence
that the extended Hamming scheme performs as well as
any 4-wise independent scheme for estimating the size
of join of two relations using AMS sketches, even
though it is only 3-wise independent. We use this
scheme to generate estimators that significantly
outperform state-of-the-art solutions for two problems,
namely, size of spatial joins and selectivity
estimation.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate query processing; data synopses; fast
range-summation; Sketches",
}
@Article{Mazeika:2007:ESA,
author = "Arturas Mazeika and Michael H. B{\"o}hlen and Nick
Koudas and Divesh Srivastava",
title = "Estimating the selectivity of approximate string
queries",
journal = j-TODS,
volume = "32",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242529",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Approximate queries on string data are important due
to the prevalence of such data in databases and various
conventions and errors in string data. We present the
VSol estimator, a novel technique for estimating the
selectivity of approximate string queries. The VSol
estimator is based on inverse strings and makes the
performance of the selectivity estimator independent of
the number of strings. To get inverse strings we
decompose all database strings into overlapping
substrings of length q (q-grams) and then associate
each q-gram with its inverse string: the IDs of all
strings that contain the q-gram. We use signatures to
compress inverse strings, and clustering to group
similar signatures.\par
We study our technique analytically and experimentally.
The space complexity of our estimator only depends on
the number of neighborhoods in the database and the
desired estimation error. The time to estimate the
selectivity is independent of the number of database
strings and linear with respect to the length of query
string. We give a detailed empirical performance
evaluation of our solution for synthetic and real-world
datasets. We show that VSol is effective for large
skewed databases of short strings.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Inverse strings; min-wise hash signatures; q-grams",
}
@Article{Zeng:2007:CCC,
author = "Zhiping Zeng and Jianyong Wang and Lizhu Zhou and
George Karypis",
title = "Out-of-core coherent closed quasi-clique mining from
large dense graph databases",
journal = j-TODS,
volume = "32",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1242524.1242530",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:09 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Due to the ability of graphs to represent more generic
and more complicated relationships among different
objects, graph mining has played a significant role in
data mining, attracting increasing attention in the
data mining community. In addition, frequent coherent
subgraphs can provide valuable knowledge about the
underlying internal structure of a graph database, and
mining frequently occurring coherent subgraphs from
large dense graph databases has witnessed several
applications and received considerable attention in the
graph mining community recently. In this article, we
study how to efficiently mine the complete set of
coherent closed quasi-cliques from large dense graph
databases, which is an especially challenging task due
to the fact that the downward-closure property no
longer holds. By fully exploring some properties of
quasi-cliques, we propose several novel optimization
techniques which can prune the unpromising and
redundant subsearch spaces effectively. Meanwhile, we
devise an efficient closure checking scheme to
facilitate the discovery of closed quasi-cliques only.
Since large databases cannot be held in main memory, we
also design an out-of-core solution with efficient
index structures for mining coherent closed
quasi-cliques from large dense graph databases. We call
this Cocain*. Thorough performance study shows that
Cocain* is very efficient and scalable for large dense
graph databases.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "coherent subgraph; frequent closed subgraph; Graph
mining; out-of-core algorithm; quasi-clique",
}
@Article{Ipeirotis:2007:MMC,
author = "Panagiotis G. Ipeirotis and Alexandros Ntoulas and
Junghoo Cho and Luis Gravano",
title = "Modeling and managing changes in text databases",
journal = j-TODS,
volume = "32",
number = "3",
pages = "14:1--14:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272744",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Large amounts of (often valuable) information are
stored in web-accessible text databases.
``Metasearchers'' provide unified interfaces to query
multiple such databases at once. For efficiency,
metasearchers rely on succinct statistical summaries of
the database contents to select the best databases for
each query. So far, database selection research has
largely assumed that databases are static, so the
associated statistical summaries do not evolve over
time. However, databases are rarely static and the
statistical summaries that describe their contents need
to be updated periodically to reflect content changes.
In this article, we first report the results of a study
showing how the content summaries of 152 real web
databases evolved over a period of 52 weeks. Then, we
show how to use ``survival analysis'' techniques in
general, and Cox's proportional hazards regression in
particular, to model database changes over time and
predict when we should update each content summary.
Finally, we exploit our change model to devise update
schedules that keep the summaries up to date by
contacting databases only when needed, and then we
evaluate the quality of our schedules experimentally
over real web databases.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "distributed information retrieval; Metasearching; text
database selection",
}
@Article{Tao:2007:RSM,
author = "Yufei Tao and Xiaokui Xiao and Reynold Cheng",
title = "Range search on multidimensional uncertain data",
journal = j-TODS,
volume = "32",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272745",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:22 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In an uncertain database, every object o is associated
with a probability density function, which describes
the likelihood that o appears at each position in a
multidimensional workspace. This article studies two
types of range retrieval fundamental to many analytical
tasks. Specifically, a nonfuzzy query returns all the
objects that appear in a search region $ r_q $ with at
least a certain probability $ t_q $. On the other hand,
given an uncertain object $q$, fuzzy search retrieves
the set of objects that are within distance $
\varepsilon_q $ from $q$ with no less than probability
$ t_q $. The core of our methodology is a novel concept
of ``probabilistically constrained rectangle'', which
permits effective pruning\slash validation of
nonqualifying\slash qualifying data. We develop a new
index structure called the U-tree for minimizing the
query overhead. Our algorithmic findings are
accompanied with a thorough theoretical analysis, which
reveals valuable insight into the problem
characteristics, and mathematically confirms the
efficiency of our solutions. We verify the
effectiveness of the proposed techniques with extensive
experiments.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "range search; Uncertain databases",
}
@Article{Sinha:2007:MRB,
author = "Rishi Rakesh Sinha and Marianne Winslett",
title = "Multi-resolution bitmap indexes for scientific data",
journal = j-TODS,
volume = "32",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272746",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The unique characteristics of scientific data and
queries cause traditional indexing techniques to
perform poorly on scientific workloads, occupy
excessive space, or both. Refinements of bitmap indexes
have been proposed previously as a solution to this
problem. In this article, we describe the difficulties
we encountered in deploying bitmap indexes with
scientific data and queries from two real-world
domains. In particular, previously proposed methods of
binning, encoding, and compressing bitmap vectors
either were quite slow for processing the large-range
query conditions our scientists used, or required
excessive storage space. Nor could the indexes easily
be built or used on parallel platforms. In this
article, we show how to solve these problems through
the use of multi-resolution, parallelizable bitmap
indexes, which support a fine-grained trade-off between
storage requirements and query performance. Our
experiments with large data sets from two scientific
domains show that multi-resolution, parallelizable
bitmap indexes occupy an acceptable amount of storage
while improving range query performance by roughly a
factor of 10, compared to a single-resolution bitmap
index of reasonable size.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "bitmap index; parallel index; Query processing;
scientific data management",
}
@Article{Chen:2007:IHJ,
author = "Shimin Chen and Anastassia Ailamaki and Phillip B.
Gibbons and Todd C. Mowry",
title = "Improving hash join performance through prefetching",
journal = j-TODS,
volume = "32",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272747",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Hash join algorithms suffer from extensive CPU cache
stalls. This article shows that the standard hash join
algorithm for disk-oriented databases (i.e. GRACE)
spends over 80\% of its user time stalled on CPU cache
misses, and explores the use of CPU cache prefetching
to improve its cache performance. Applying prefetching
to hash joins is complicated by the data dependencies,
multiple code paths, and inherent randomness of
hashing. We present two techniques, group prefetching
and software-pipelined prefetching, that overcome these
complications. These schemes achieve 1.29--4.04X
speedups for the join phase and 1.37--3.49X speedups
for the partition phase over GRACE and simple
prefetching approaches. Moreover, compared with
previous cache-aware approaches (i.e. cache
partitioning), the schemes are at least 36\% faster on
large relations and do not require exclusive use of the
CPU cache to be effective. Finally, comparing the
elapsed real times when disk I/Os are in the picture,
our cache prefetching schemes achieve 1.12--1.84X
speedups for the join phase and 1.06--1.60X speedups
for the partition phase over the GRACE hash join
algorithm.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "CPU cache performance; CPU cache prefetching; group
prefetching; Hash join; software-pipelined
prefetching",
}
@Article{Cao:2007:SQO,
author = "Bin Cao and Antonio Badia",
title = "{SQL} query optimization through nested relational
algebra",
journal = j-TODS,
volume = "32",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272748",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:57 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Most research work on optimization of nested queries
focuses on aggregate subqueries. In this article, we
show that existing approaches are not adequate for
nonaggregate subqueries, especially for those having
multiple subqueries and certain comparison operators.
We then propose a new efficient approach, the nested
relational approach, based on the nested relational
algebra. The nested relational approach treats all
subqueries in a uniform manner, being able to deal with
nested queries of any type and any level. We report on
experimental work that confirms that existing
approaches have difficulties dealing with nonaggregate
subqueries, and that the nested relational approach
offers better performance. We also discuss algebraic
optimization rules for further optimizing the nested
relational approach and the issue of integrating it
into relational database systems.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Nested queries; nested relational algebra;
nonrelational query processing",
}
@Article{Mamoulis:2007:ETA,
author = "Nikos Mamoulis and Man Lung Yiu and Kit Hung Cheng and
David W. Cheung",
title = "Efficient top-$k$ aggregation of ranked inputs",
journal = j-TODS,
volume = "32",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1272743.1272749",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:22 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A top- k query combines different rankings of the same
set of objects and returns the k objects with the
highest combined score according to an aggregate
function. We bring to light some key observations,
which impose two phases that any top- k algorithm,
based on sorted accesses, should go through. Based on
them, we propose a new algorithm, which is designed to
minimize the number of object accesses, the
computational cost, and the memory requirements of top-
k search with monotone aggregate functions. We provide
an analysis for its cost and show that it is always no
worse than the baseline ``no random accesses''
algorithm in terms of computations, accesses, and
memory required. As a side contribution, we perform a
space analysis, which indicates the memory requirements
of top- k algorithms that only perform sorted accesses.
For the case, where the required space exceeds the
available memory, we propose disk-based variants of our
algorithm. We propose and optimize a multiway top- k
join operator, with certain advantages over evaluation
trees of binary top- k join operators. Finally, we
define and study the computation of top- k cubes and
the implementation of roll-up and drill-down operations
in such cubes. Extensive experiments with synthetic and
real data show that, compared to previous techniques,
our method accesses fewer objects, while being orders
of magnitude faster.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "rank aggregation; Top- k queries",
}
@Article{Chaudhuri:2007:IAS,
author = "Surajit Chaudhuri",
title = "Introduction to {ACM SIGMOD} 2006 conference papers",
journal = j-TODS,
volume = "32",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292610",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ipeirotis:2007:TQO,
author = "Panagiotis G. Ipeirotis and Eugene Agichtein and
Pranay Jain and Luis Gravano",
title = "Towards a query optimizer for text-centric tasks",
journal = j-TODS,
volume = "32",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292611",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Text is ubiquitous and, not surprisingly, many
important applications rely on textual data for a
variety of tasks. As a notable example, information
extraction applications derive structured relations
from unstructured text; as another example, focused
crawlers explore the Web to locate pages about specific
topics. Execution plans for text-centric tasks follow
two general paradigms for processing a text database:
either we can scan, or ``crawl,'' the text database or,
alternatively, we can exploit search engine indexes and
retrieve the documents of interest via carefully
crafted queries constructed in task-specific ways. The
choice between crawl- and query-based execution plans
can have a substantial impact on both execution time
and output ``completeness'' (e.g., in terms of recall).
Nevertheless, this choice is typically ad hoc and based
on heuristics or plain intuition. In this article, we
present fundamental building blocks to make the choice
of execution plans for text-centric tasks in an
informed, cost-based way. Towards this goal, we show
how to analyze query- and crawl-based plans in terms of
both execution time and output completeness. We adapt
results from random-graph theory and statistics to
develop a rigorous cost model for the execution plans.
Our cost model reflects the fact that the performance
of the plans depends on fundamental task-specific
properties of the underlying text databases. We
identify these properties and present efficient
techniques for estimating the associated parameters of
the cost model. We also present two optimization
approaches for text-centric tasks that rely on the
cost-model parameters and select efficient execution
plans. Overall, our optimization approaches help build
efficient execution plans for a task, resulting in
significant efficiency and output completeness
benefits. We complement our results with a large-scale
experimental evaluation for three important
text-centric tasks and over multiple real-life data
sets.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "distributed information retrieval; focused crawling;
information extraction; Metasearching; text database
selection",
}
@Article{Petropoulos:2007:EIQ,
author = "Michalis Petropoulos and Alin Deutsch and Yannis
Papakonstantinou and Yannis Katsis",
title = "Exporting and interactively querying {Web}
service-accessed sources: {The CLIDE System}",
journal = j-TODS,
volume = "32",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292612",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The CLIDE System assists the owners of sources that
participate in Web service-based data publishing
systems to publish a restricted set of parameterized
queries over the schema of their sources and package
them as WSDL services. The sources may be relational
databases, which naturally have a schema, or ad hoc
information/application systems whereas the owner
publishes a virtual schema. CLIDE allows information
clients to pose queries over the published schema and
utilizes prior work on answering queries using views to
answer queries that can be processed by combining and
processing the results of one or more Web service
calls. These queries are called feasible. Contrary to
prior work, where infeasible queries are rejected
without an explanatory feedback, leading the user into
a frustrating trial-and-error cycle, CLIDE features a
query formulation interface, which extends the QBE-like
query builder of Microsoft's SQL Server with a color
scheme that guides the user toward formulating feasible
queries. CLIDE guarantees that the suggested query edit
actions are complete (i.e., each feasible query can be
built by following only suggestions), rapidly
convergent (the suggestions are tuned to lead to the
closest feasible completions of the query), and
suitably summarized (at each interaction step, only a
minimal number of actions needed to preserve
completeness are suggested). We present the algorithms,
implementation, and performance evaluation showing that
CLIDE is a viable on-line tool.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "limited access patterns; Middleware; query rewriting;
Web services",
}
@Article{Sharfman:2007:GAM,
author = "Izchak Sharfman and Assaf Schuster and Daniel Keren",
title = "A geometric approach to monitoring threshold functions
over distributed data streams",
journal = j-TODS,
volume = "32",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292613",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Monitoring data streams in a distributed system is the
focus of much research in recent years. Most of the
proposed schemes, however, deal with monitoring simple
aggregated values, such as the frequency of appearance
of items in the streams. More involved challenges, such
as the important task of feature selection (e.g., by
monitoring the information gain of various features),
still require very high communication overhead using
naive, centralized algorithms.\par
We present a novel geometric approach which reduces
monitoring the value of a function (vis-{\`a}-vis a
threshold) to a set of constraints applied locally on
each of the streams. The constraints are used to
locally filter out data increments that do not affect
the monitoring outcome, thus avoiding unnecessary
communication. As a result, our approach enables
monitoring of arbitrary threshold functions over
distributed data streams in an efficient manner.\par
We present experimental results on real-world data
which demonstrate that our algorithms are highly
scalable, and considerably reduce communication load in
comparison to centralized algorithms.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Distributed monitoring",
}
@Article{VandenBussche:2007:IPS,
author = "Jan {Van den Bussche}",
title = "Introduction to the {PODS} 2006 special section",
journal = j-TODS,
volume = "32",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292614",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fagin:2007:ISM,
author = "Ronald Fagin",
title = "Inverting schema mappings",
journal = j-TODS,
volume = "32",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292615",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A schema mapping is a specification that describes how
data structured under one schema (the source schema) is
to be transformed into data structured under a
different schema (the target schema). Although the
notion of an inverse of a schema mapping is important,
the exact definition of an inverse mapping is somewhat
elusive. This is because a schema mapping may associate
many target instances with each source instance, and
many source instances with each target instance. Based
on the notion that the composition of a mapping and its
inverse is the identity, we give a formal definition
for what it means for a schema mapping $ M \prime $ to
be an inverse of a schema mapping $M$ for a class $S$
of source instances. We call such an inverse an
$S$-inverse. A particular case of interest arises when
$S$ is the class of all source instances, in which case
an $S$-inverse is a global inverse. We focus on the
important and practical case of schema mappings
specified by source-to-target tuple-generating
dependencies, and uncover a rich theory. When $S$ is
specified by a set of dependencies with a finite chase,
we show how to construct an $S$-inverse when one
exists. In particular, we show how to construct a
global inverse when one exists. Given $M$ and $ M
\prime $, we show how to define the largest class $S$
such that $ M \prime $ is an $S$-inverse of $M$.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "chase; computational complexity; Data exchange; data
integration; dependencies; inverse; metadata model
management; schema mapping; second-order logic",
}
@Article{Bender:2007:APM,
author = "Michael A. Bender and Haodong Hu",
title = "An adaptive packed-memory array",
journal = j-TODS,
volume = "32",
number = "4",
pages = "26:1--26:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292616",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The packed-memory array (PMA) is a data structure that
maintains a dynamic set of $N$ elements in sorted order
in a $ \Theta (N) $-sized array. The idea is to
intersperse $ \Theta (N) $ empty spaces or gaps among
the elements so that only a small number of elements
need to be shifted around on an insert or delete.
Because the elements are stored physically in sorted
order in memory or on disk, the PMA can be used to
support extremely efficient range queries.
Specifically, the cost to scan $L$ consecutive elements
is $ O(1 + L / B) $ memory transfers.\par
This article gives the first adaptive packed-memory
array (APMA), which automatically adjusts to the input
pattern. Like the traditional PMA, any pattern of
updates costs only $ O(\log_2 N) $ amortized element
moves and $ O(1 + (\log_2 N) / B) $ amortized memory
transfers per update. However, the APMA performs even
better on many common input distributions achieving
only $ O(\log N) $ amortized element moves and $ O(1 +
(\log N) / B) $ amortized memory transfers. The article
analyzes sequential inserts, where the insertions are
to the front of the APMA, hammer inserts, where the
insertions ``hammer'' on one part of the APMA, random
inserts, where the insertions are after random elements
in the APMA, and bulk inserts, where for constant $
\alpha $ $ \epsilon $ $ [0, 1] $, $N$ $ \alpha $
elements are inserted after random elements in the
APMA. The article then gives simulation results that
are consistent with the asymptotic bounds. For
sequential insertions of roughly 1.4 million elements,
the APMA has four times fewer element moves per
insertion than the traditional PMA and running times
that are more than seven times faster.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "adaptive packed-memory array; cache oblivious;
locality preserving; packed-memory array; range query;
rebalance; sequential file maintenance; sequential
scan; sparse array",
}
@Article{Ioannidis:2007:IES,
author = "Yannis Ioannidis",
title = "Introduction to the {EDBT} 2006 special section",
journal = j-TODS,
volume = "32",
number = "4",
pages = "27:1--27:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292617",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bruno:2007:PDR,
author = "Nicolas Bruno and Surajit Chaudhuri",
title = "Physical design refinement: {The} `merge-reduce'
approach",
journal = j-TODS,
volume = "32",
number = "4",
pages = "28:1--28:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292618",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Physical database design tools rely on a DBA-provided
workload to pick an ``optimal'' set of indexes and
materialized views. Such tools allow either creating a
new such configuration or adding new structures to
existing ones. However, these tools do not provide
adequate support for the incremental and flexible
refinement of existing physical structures. Although
such refinements are often very valuable for DBAs, a
completely manual approach to refinement can lead to
infeasible solutions (e.g., excessive use of space). In
this article, we focus on the important problem of
physical design refinement and propose a
transformational architecture that is based upon two
novel primitive operations, called merging and
reduction. These operators help refine a configuration,
treating indexes and materialized views in a unified
way, as well as succinctly explain the refinement
process to DBAs.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Physical database design; physical design refinment;
view merging and reduction",
}
@Article{Skopal:2007:UFF,
author = "Tom{\'a}{\v{s}} Skopal",
title = "Unified framework for fast exact and approximate
search in dissimilarity spaces",
journal = j-TODS,
volume = "32",
number = "4",
pages = "29:1--29:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292619",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In multimedia systems we usually need to retrieve
database (DB) objects based on their similarity to a
query object, while the similarity assessment is
provided by a measure which defines a (dis)similarity
score for every pair of DB objects. In most existing
applications, the similarity measure is required to be
a metric, where the triangle inequality is utilized to
speed up the search for relevant objects by use of
metric access methods (MAMs), for example, the M-tree.
A recent research has shown, however, that nonmetric
measures are more appropriate for similarity modeling
due to their robustness and ease to model a
made-to-measure similarity. Unfortunately, due to the
lack of triangle inequality, the nonmetric measures
cannot be directly utilized by MAMs. From another point
of view, some sophisticated similarity measures could
be available in a black-box nonanalytic form (e.g., as
an algorithm or even a hardware device), where no
information about their topological properties is
provided, so we have to consider them as nonmetric
measures as well. From yet another point of view, the
concept of similarity measuring itself is inherently
imprecise and we often prefer fast but approximate
retrieval over an exact but slower one.\par
To date, the mentioned aspects of similarity retrieval
have been solved separately, that is, exact versus
approximate search or metric versus nonmetric search.
In this article we introduce a similarity retrieval
framework which incorporates both of the aspects into a
single unified model. Based on the framework, we show
that for any dissimilarity measure (either a metric or
nonmetric) we are able to change the ``amount'' of
triangle inequality, and so obtain an approximate or
full metric which can be used for MAM-based retrieval.
Due to the varying ``amount'' of triangle inequality,
the measure is modified in a way suitable for either an
exact but slower or an approximate but faster
retrieval. Additionally, we introduce the TriGen
algorithm aimed at constructing the desired
modification of any black-box distance automatically,
using just a small fraction of the database.",
acknowledgement = ack-nhfb,
articleno = "29",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate and exact search; Similarity retrieval",
}
@Article{Li:2007:NGN,
author = "Yunyao Li and Huahai Yang and H. V. Jagadish",
title = "{NaLIX}: a generic natural language search environment
for {XML} data",
journal = j-TODS,
volume = "32",
number = "4",
pages = "30:1--30:??",
month = nov,
year = "2007",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1292609.1292620",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:32 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We describe the construction of a generic natural
language query interface to an XML database. Our
interface can accept a large class of English sentences
as a query, which can be quite complex and include
aggregation, nesting, and value joins, among other
things. This query is translated, potentially after
reformulation, into an XQuery expression. The
translation is based on mapping grammatical proximity
of natural language parsed tokens in the parse tree of
the query sentence to proximity of corresponding
elements in the XML data to be retrieved. Iterative
search in the form of followup queries is also
supported. Our experimental assessment, through a user
study, demonstrates that this type of natural language
interface is good enough to be usable now, with no
restrictions on the application domain.",
acknowledgement = ack-nhfb,
articleno = "30",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "dialog system; iterative search; Natural language
interface; XML; XQuery",
}
@Article{Hristidis:2008:ABK,
author = "Vagelis Hristidis and Heasoo Hwang and Yannis
Papakonstantinou",
title = "Authority-based keyword search in databases",
journal = j-TODS,
volume = "33",
number = "1",
pages = "1:1--1:40",
month = mar,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1331904.1331905",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:49 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Our system applies authority-based ranking to keyword
search in databases modeled as labeled graphs. Three
ranking factors are used: the relevance to the query,
the specificity and the importance of the result. All
factors are handled using authority-flow techniques
that exploit the link-structure of the data graph, in
contrast to traditional Information Retrieval. We
address the performance challenges in computing the
authority flows in databases by using precomputation
and exploiting the database schema if present. We
conducted user surveys and performance experiments on
multiple real and synthetic datasets, to assess the
semantic meaningfulness and performance of our
system.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Authority flow; PageRank; quality experiments;
ranking; specificity",
}
@Article{Aggarwal:2008:SDM,
author = "Charu C. Aggarwal and Philip S. Yu",
title = "On static and dynamic methods for condensation-based
privacy-preserving data mining",
journal = j-TODS,
volume = "33",
number = "1",
pages = "2:1--2:39",
month = mar,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1331904.1331906",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:49 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In recent years, privacy-preserving data mining has
become an important problem because of the large amount
of personal data which is tracked by many business
applications. In many cases, users are unwilling to
provide personal information unless the privacy of
sensitive information is guaranteed. In this paper, we
propose a new framework for privacy-preserving data
mining of multidimensional data. Previous work for
privacy-preserving data mining uses a perturbation
approach which reconstructs data distributions in order
to perform the mining. Such an approach treats each
dimension independently and therefore ignores the
correlations between the different dimensions. In
addition, it requires the development of a new
distribution-based algorithm for each data mining
problem, since it does not use the multidimensional
records, but uses aggregate distributions of the data
as input. This leads to a fundamental re-design of data
mining algorithms. In this paper, we will develop a new
and flexible approach for privacy-preserving data
mining that does not require new problem-specific
algorithms, since it maps the original data set into a
new anonymized data set. These anonymized data closely
match the characteristics of the original data
including the correlations among the different
dimensions. We will show how to extend the method to
the case of data streams. We present empirical results
illustrating the effectiveness of the method. We also
show the efficiency of the method for data streams.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "databases data mining; k -anonymity; Privacy",
}
@Article{Balazinska:2008:FTB,
author = "Magdalena Balazinska and Hari Balakrishnan and Samuel
R. Madden and Michael Stonebraker",
title = "Fault-tolerance in the {Borealis} distributed stream
processing system",
journal = j-TODS,
volume = "33",
number = "1",
pages = "3:1--3:44",
month = mar,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1331904.1331907",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:49 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Over the past few years, Stream Processing Engines
(SPEs) have emerged as a new class of software systems,
enabling low latency processing of streams of data
arriving at high rates. As SPEs mature and get used in
monitoring applications that must continuously run
(e.g., in network security monitoring), a significant
challenge arises: SPEs must be able to handle various
software and hardware faults that occur, masking them
to provide high availability (HA). In this article, we
develop, implement, and evaluate DPC (Delay, Process,
and Correct), a protocol to handle crash failures of
processing nodes and network failures in a distributed
SPE.\par
Like previous approaches to HA, DPC uses replication
and masks many types of node and network failures. In
the presence of network partitions, the designer of any
replication system faces a choice between providing
availability or data consistency across the replicas.
In DPC, this choice is made explicit: the user
specifies an availability bound (no result should be
delayed by more than a specified delay threshold even
under failure if the corresponding input is available),
and DPC attempts to minimize the resulting
inconsistency between replicas (not all of which might
have seen the input data) while meeting the given delay
threshold. Although conceptually simple, the DPC
protocol tolerates the occurrence of multiple
simultaneous failures as well as any further failures
that occur during recovery.\par
This article describes DPC and its implementation in
the Borealis SPE. We show that DPC enables a
distributed SPE to maintain low-latency processing at
all times, while also achieving eventual consistency,
where applications eventually receive the complete and
correct output streams. Furthermore, we show that,
independent of system size and failure location, it is
possible to handle failures almost up-to the
user-specified bound in a manner that meets the
required availability without introducing any
inconsistency.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "availability; consistency; Distributed stream
processing; fault-tolerance",
}
@Article{Fan:2008:IPX,
author = "Wenfei Fan and Philip Bohannon",
title = "Information preserving {XML} schema embedding",
journal = j-TODS,
volume = "33",
number = "1",
pages = "4:1--4:44",
month = mar,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1331904.1331908",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:49 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A fundamental concern of data integration in an XML
context is the ability to embed one or more source
documents in a target document so that (a) the target
document conforms to a target schema and (b) the
information in the source documents is preserved. In
this paper, information preservation for XML is
formally studied, and the results of this study guide
the definition of a novel notion of schema embedding
between two XML DTD schemas represented as graphs.
Schema embedding generalizes the conventional notion of
graph similarity by allowing an edge in a source DTD
schema to be mapped to a path in the target DTD.
Instance-level embeddings can be derived from the
schema embedding in a straightforward manner, such that
conformance to a target schema and information
preservation are guaranteed. We show that it is
NP-complete to find an embedding between two DTD
schemas. We also outline efficient heuristic algorithms
to find candidate embeddings, which have proved
effective by our experimental study. These yield the
first systematic and effective approach to finding
information preserving XML mappings.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data transformation; information integration;
information preservation; schema embedding; schema
mapping; XML; XSLT",
}
@Article{Sharaf:2008:AMP,
author = "Mohamed A. Sharaf and Panos K. Chrysanthis and
Alexandros Labrinidis and Kirk Pruhs",
title = "Algorithms and metrics for processing multiple
heterogeneous continuous queries",
journal = j-TODS,
volume = "33",
number = "1",
pages = "5:1--5:44",
month = mar,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1331904.1331909",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jun 12 16:37:49 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The emergence of monitoring applications has
precipitated the need for Data Stream Management
Systems (DSMSs), which constantly monitor incoming data
feeds (through registered continuous queries), in order
to detect events of interest. In this article, we
examine the problem of how to schedule multiple
Continuous Queries (CQs) in a DSMS to optimize
different Quality of Service (QoS) metrics. We show
that, unlike traditional online systems, scheduling
policies in DSMSs that optimize for average response
time will be different from policies that optimize for
average slowdown, which is a more appropriate metric to
use in the presence of a heterogeneous workload.
Towards this, we propose policies to optimize for the
average-case performance for both metrics.
Additionally, we propose a hybrid scheduling policy
that strikes a fine balance between performance and
fairness, by looking at both the average- and
worst-case performance, for both metrics. We also show
how our policies can be adaptive enough to handle the
inherent dynamic nature of monitoring applications.
Furthermore, we discuss how our policies can be
efficiently implemented and extended to exploit sharing
in optimized multi-query plans and multi-stream CQs.
Finally, we experimentally show using real data that
our policies consistently outperform currently used
ones.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "continuous queries; Data stream management system;
operator scheduling",
}
@Article{Fan:2008:CFD,
author = "Wenfei Fan and Floris Geerts and Xibei Jia and
Anastasios Kementsietsidis",
title = "Conditional functional dependencies for capturing data
inconsistencies",
journal = j-TODS,
volume = "33",
number = "2",
pages = "6:1--6:48",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366103",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We propose a class of integrity constraints for
relational databases, referred to as {\em conditional
functional dependencies\/} (CFDs), and study their
applications in data cleaning. In contrast to
traditional functional dependencies (FDs) that were
developed mainly for schema design, CFDs aim at
capturing the consistency of data by enforcing bindings
of semantically related values. For static analysis of
CFDs we investigate {\em the consistency problem},
which is to determine whether or not there exists a
nonempty database satisfying a given set of CFDs, and
{\em the implication problem}, which is to decide
whether or not a set of CFDs entails another CFD. We
show that while any set of transitional FDs is
trivially consistent, the consistency problem is
NP-complete for CFDs, but it is in PTIME when either
the database schema is predefined or no attributes
involved in the CFDs have a finite domain. For the
implication analysis of CFDs, we provide an inference
system analogous to Armstrong's axioms for FDs, and
show that the implication problem is coNP-complete for
CFDs in contrast to the linear-time complexity for
their traditional counterpart. We also present an
algorithm for computing a minimal cover of a set of
CFDs. Since CFDs allow data bindings, in some cases
CFDs may be physically large, complicating the
detection of constraint violations. We develop
techniques for detecting CFD violations in SQL as well
as novel techniques for checking multiple constraints
by a single query. We also provide incremental methods
for checking CFDs in response to changes to the
database. We experimentally verify the effectiveness of
our CFD-based methods for inconsistency detection. This
work not only yields a constraint theory for CFDs but
is also a step toward a practical constraint-based
method for improving data quality.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data cleaning; functional dependency; SQL",
}
@Article{Jacox:2008:MSS,
author = "Edwin H. Jacox and Hanan Samet",
title = "Metric space similarity joins",
journal = j-TODS,
volume = "33",
number = "2",
pages = "7:1--7:38",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366104",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Similarity join algorithms find pairs of objects that
lie within a certain distance $ \epsilon $ of each
other. Algorithms that are adapted from spatial join
techniques are designed primarily for data in a vector
space and often employ some form of a multidimensional
index. For these algorithms, when the data lies in a
metric space, the usual solution is to embed the data
in vector space and then make use of a multidimensional
index. Such an approach has a number of drawbacks when
the data is high dimensional as we must eventually find
the most discriminating dimensions, which is not
trivial. In addition, although the maximum distance
between objects increases with dimension, the ability
to discriminate between objects in each dimension does
not. These drawbacks are overcome via the introduction
of a new method called {\em Quickjoin\/} that does not
require a multidimensional index and instead adapts
techniques used in distance-based indexing for use in a
method that is conceptually similar to the Quicksort
algorithm. A formal analysis is provided of the
Quickjoin method. Experiments show that the Quickjoin
method significantly outperforms two existing
techniques.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "distance-based indexing; external memory algorithms;
nearest neighbor queries; range queries; ranking;
similarity join",
}
@Article{He:2008:COD,
author = "Bingsheng He and Qiong Luo",
title = "Cache-oblivious databases: {Limitations} and
opportunities",
journal = j-TODS,
volume = "33",
number = "2",
pages = "8:1--8:42",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366105",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Cache-oblivious techniques, proposed in the theory
community, have optimal asymptotic bounds on the amount
of data transferred between any two adjacent levels of
an arbitrary memory hierarchy. Moreover, this optimal
performance is achieved without any hardware platform
specific tuning. These properties are highly attractive
to autonomous databases, especially because the
hardware architectures are becoming increasingly
complex and diverse.\par
In this article, we present our design, implementation,
and evaluation of the first cache-oblivious in-memory
query processor, EaseDB. Moreover, we discuss the
inherent limitations of the cache-oblivious approach as
well as the opportunities given by the upcoming
hardware architectures. Specifically, a cache-oblivious
technique usually requires sophisticated algorithm
design to achieve a comparable performance to its
cache-conscious counterpart. Nevertheless, this
development-time effort is compensated by the
automaticity of performance achievement and the reduced
ownership cost. Furthermore, this automaticity enables
cache-oblivious techniques to outperform their
cache-conscious counterparts in multi-threading
processors.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "cache-conscious; cache-oblivious; chip
multiprocessors; data caches; simultaneous
multithreading",
}
@Article{Cormode:2008:ACQ,
author = "Graham Cormode and Minos Garofalakis",
title = "Approximate continuous querying over distributed
streams",
journal = j-TODS,
volume = "33",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366106",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "While traditional database systems optimize for
performance on one-shot query processing, emerging
large-scale monitoring applications require continuous
tracking of complex data-analysis queries over
collections of physically distributed streams. Thus,
effective solutions have to be simultaneously
space/time efficient (at each remote monitor site),
communication efficient (across the underlying
communication network), and provide continuous,
guaranteed-quality approximate query answers. In this
paper, we propose novel algorithmic solutions for the
problem of continuously tracking a broad class of
complex aggregate queries in such a distributed-streams
setting. Our tracking schemes maintain approximate
query answers with provable error guarantees, while
simultaneously optimizing the storage space and
processing time at each remote site, and the
communication cost across the network. In a nutshell,
our algorithms rely on tracking general-purpose
randomized sketch summaries of local streams at remote
sites along with concise prediction models of local
site behavior in order to produce highly communication-
and space/time-efficient solutions. The end result is a
powerful approximate query tracking framework that
readily incorporates several complex analysis queries
(including distributed join and multi-join aggregates,
and approximate wavelet representations), thus giving
the first known low-overhead tracking solution for such
queries in the distributed-streams model. Experiments
with real data validate our approach, revealing
significant savings over naive solutions as well as our
analytical worst-case guarantees.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate query processing; continuous distributed
monitoring; data stream algorithms; data synopses",
}
@Article{Eiter:2008:RLQ,
author = "Thomas Eiter and Michael Fink and Gianluigi Greco and
Domenico Lembo",
title = "Repair localization for query answering from
inconsistent databases",
journal = j-TODS,
volume = "33",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366107",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Query answering from inconsistent databases amounts to
finding ``meaningful'' answers to queries posed over
database instances that do not satisfy integrity
constraints specified over their schema. A declarative
approach to this problem relies on the notion of
repair, that is, a database that satisfies integrity
constraints and is obtained from the original
inconsistent database by ``minimally'' adding and/or
deleting tuples. Consistent answers to a user query are
those answers that are in the evaluation of the query
over each repair. Motivated by the fact that computing
consistent answers from inconsistent databases is in
general intractable, the present paper investigates
techniques that allow to localize the difficult part of
the computation on a small fragment of the database at
hand, called ``affected'' part. Based on a number of
localization results, an approach to query answering
from inconsistent data is presented, in which the query
is evaluated over each of the repairs of the affected
part only, augmented with the part that is not
affected. Single query results are then suitably
recombined. For some relevant settings, techniques are
also discussed to factorize repairs into components
that can be processed independently of one another,
thereby guaranteeing exponential gain w.r.t. the basic
approach, which is not based on localization. The
effectiveness of the results is demonstrated for
consistent query answering over expressive schemas,
based on logic programming specifications as proposed
in the literature.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "consistent query answering; data integration; database
repairs; inconsistency management in databases; logic
programming; stable models",
}
@Article{Fagin:2008:QIS,
author = "Ronald Fagin and Phokion G. Kolaitis and Lucian Popa
and Wang-Chiew Tan",
title = "Quasi-inverses of schema mappings",
journal = j-TODS,
volume = "33",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366108",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Schema mappings are high-level specifications that
describe the relationship between two database schemas.
Two operators on schema mappings, namely the
composition operator and the inverse operator, are
regarded as especially important. Progress on the study
of the inverse operator was not made until very
recently, as even finding the exact semantics of this
operator turned out to be a fairly delicate task.
Furthermore, this notion is rather restrictive, since
it is rare that a schema mapping possesses an
inverse.\par
In this article, we introduce and study the notion of a
quasi-inverse of a schema mapping. This notion is a
principled relaxation of the notion of an inverse of a
schema mapping; intuitively, it is obtained from the
notion of an inverse by not differentiating between
instances that are equivalent for data-exchange
purposes. For schema mappings specified by
source-to-target tuple-generating dependencies (s-t
tgds), we give a necessary and sufficient combinatorial
condition for the existence of a quasi-inverse, and
then use this condition to obtain both positive and
negative results about the existence of quasi-inverses.
In particular, we show that every LAV (local-as-view)
schema mapping has a quasi-inverse, but that there are
schema mappings specified by full s-t tgds that have no
quasi-inverse. After this, we study the language needed
to express quasi-inverses of schema mappings specified
by s-t tgds, and we obtain a complete characterization.
We also characterize the language needed to express
inverses of schema mappings, and thereby solve a
problem left open in the earlier study of the inverse
operator. Finally, we show that quasi-inverses can be
used in many cases to recover the data that was
exported by the original schema mapping when performing
data exchange.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "chase; data exchange; data integration; dependencies;
inverse; metadata model management; quasi-inverse;
schema mapping",
}
@Article{Zhang:2008:CTA,
author = "Donghui Zhang and Alexander Markowetz and Vassilis J.
Tsotras and Dimitrios Gunopulos and Bernhard Seeger",
title = "On computing temporal aggregates with range
predicates",
journal = j-TODS,
volume = "33",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1366102.1366109",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jun 25 08:39:17 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Computing temporal aggregates is an important but
costly operation for applications that maintain
time-evolving data (data warehouses, temporal
databases, etc.) Due to the large volume of such data,
performance improvements for temporal aggregate queries
are critical. Previous approaches have aggregate
predicates that involve only the time dimension. In
this article we examine techniques to compute temporal
aggregates that include key-range predicates as well
({\em range-temporal aggregates\/}). In particular we
concentrate on the SUM aggregate, while COUNT is a
special case. To handle arbitrary key ranges, previous
methods would need to keep a separate index for every
possible key range. We propose an approach based on a
new index structure called the {\em Multiversion
SB-Tree}, which incorporates features from both the
SB-Tree and the Multiversion B+--tree, to handle
arbitrary key-range temporal aggregate queries. We
analyze the performance of our approach and present
experimental results that show its efficiency.
Furthermore, we address a novel and practical variation
called {\em functional\/} range-temporal aggregates.
Here, the value of any record is a function over time.
The meaning of aggregates is altered such that the
contribution of a record to the aggregate result is
proportional to the size of the intersection between
the record's time interval and the query time interval.
Both analytical and experimental results show the
efficiency of our result.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "functional aggregates; indexing; range predicates;
temporal aggregates",
}
@Article{Soliman:2008:PTR,
author = "Mohamed A. Soliman and Ihab F. Ilyas and Kevin
Chen--Chuan Chang",
title = "Probabilistic top-$k$ and ranking-aggregate queries",
journal = j-TODS,
volume = "33",
number = "3",
pages = "13:1--13:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386119",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Ranking and aggregation queries are widely used in
data exploration, data analysis, and decision-making
scenarios. While most of the currently proposed ranking
and aggregation techniques focus on deterministic data,
several emerging applications involve data that is
unclean or uncertain. Ranking and aggregating uncertain
(probabilistic) data raises new challenges in query
semantics and processing, making conventional methods
inapplicable. Furthermore, uncertainty imposes
probability as a new ranking dimension that does not
exist in the traditional settings.\par
In this article we introduce new probabilistic
formulations for top-$k$ and ranking-aggregate queries
in probabilistic databases. Our formulations are based
on marriage of traditional top-$k$ semantics with
possible worlds semantics. In the light of these
formulations, we construct a generic processing
framework supporting both query types, and leveraging
existing query processing and indexing capabilities in
current RDBMSs. The framework encapsulates a state
space model and efficient search algorithms to compute
query answers. Our proposed techniques minimize the
number of accessed tuples and the size of materialized
search space to compute query answers. Our experimental
study shows the efficiency of our techniques under
different data distributions with orders of magnitude
improvement over na{\"\i}ve methods.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregation; probabilistic data; Query processing;
ranking; top-k",
}
@Article{Ke:2008:CPM,
author = "Yiping Ke and James Cheng and Wilfred Ng",
title = "Correlated pattern mining in quantitative databases",
journal = j-TODS,
volume = "33",
number = "3",
pages = "14:1--14:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386120",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study mining correlations from quantitative
databases and show that this is a more effective
approach than mining associations to discover useful
patterns. We propose the novel notion of {\em
quantitative correlated pattern\/} (QCP), which is
founded on two formal concepts, mutual information and
all-confidence. We first devise a normalization on
mutual information and apply it to the problem of QCP
mining to capture the dependency between the
attributes. We further adopt all-confidence as a
quality measure to ensure, at a finer granularity, the
dependency between the attributes with specific
quantitative intervals. We also propose an effective
supervised method that combines the consecutive
intervals of the quantitative attributes based on
mutual information, such that the interval-combining is
guided by the dependency between the attributes. We
develop an algorithm, {\em QCoMine}, to mine QCPs
efficiently by utilizing normalized mutual information
and all-confidence to perform bilevel pruning. We also
identify the redundancy existing in the set of QCPs and
propose effective techniques to eliminate the
redundancy. Our extensive experiments on both real and
synthetic datasets verify the efficiency of {\em
QCoMine\/} and the quality of the QCPs. The
experimental results also justify the effectiveness of
our proposed techniques for redundancy elimination. To
further demonstrate the usefulness and the quality of
QCPs, we study an application of QCPs to
classification. We demonstrate that the classifier
built on the QCPs achieves higher classification
accuracy than the state-of-the-art classifiers built on
association rules.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "correlated patterns; information-theoretic approach;
mutual information; Quantitative databases",
}
@Article{Rusu:2008:SSJ,
author = "Florin Rusu and Alin Dobra",
title = "Sketches for size of join estimation",
journal = j-TODS,
volume = "33",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386121",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Sketching techniques provide approximate answers to
aggregate queries both for data-streaming and
distributed computation. Small space summaries that
have linearity properties are required for both types
of applications. The prevalent method for analyzing
sketches uses moment analysis and
distribution-independent bounds based on moments. This
method produces clean, easy to interpret, theoretical
bounds that are especially useful for deriving
asymptotic results. However, the theoretical bounds
obscure fine details of the behavior of various
sketches and they are mostly not indicative of which
type of sketches should be used in practice. Moreover,
no significant empirical comparison between various
sketching techniques has been published, which makes
the choice even harder. In this article we take a close
look at the sketching techniques proposed in the
literature from a statistical point of view with the
goal of determining properties that indicate the actual
behavior and producing tighter confidence bounds.
Interestingly, the statistical analysis reveals that
two of the techniques, Fast-AGMS and Count-Min, provide
results that are in some cases orders of magnitude
better than the corresponding theoretical predictions.
We conduct an extensive empirical study that compares
the different sketching techniques in order to
corroborate the statistical analysis with the
conclusions we draw from it. The study indicates the
expected performance of various sketches, which is
crucial if the techniques are to be used by
practitioners. The overall conclusion of the study is
that Fast-AGMS sketches are, for the full spectrum of
problems, either the best, or close to the best,
sketching technique. We apply the insights obtained
from the statistical study and the experimental results
to design effective algorithms for sketching interval
data. We show how the two basic methods for sketching
interval data, DMAP and fast range-summation, can be
improved significantly with respect to the update time
without a significant loss in accuracy. The gain in
update time can be as large as two orders of magnitude,
thus making the improved methods practical. The
empirical study suggests that DMAP is preferable when
update time is the critical requirement and fast
range-summation is desirable for better accuracy.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "AGMS sketches; Count-Min sketches; DMAP; fast
range-summation; Fast-AGMS sketches; Fast-Count
sketches; Size of join estimation",
}
@Article{Xu:2008:CBS,
author = "Fei Xu and Christopher Jermaine and Alin Dobra",
title = "Confidence bounds for sampling-based group by
estimates",
journal = j-TODS,
volume = "33",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386122",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Sampling is now a very important data management tool,
to such an extent that an interface for database
sampling is included in the latest SQL standard. In
this article we reconsider in depth what at first may
seem like a very simple problem --- computing the error
of a sampling-based guess for the answer to a GROUP BY
query over a multitable join. The difficulty when
sampling for the answer to such a query is that the
same sample will be used to guess the result of the
query for each group, which induces correlations among
the estimates. Thus, from a statistical point-of-view
it is very problematic and even dangerous to use
traditional methods such as confidence intervals for
communicating estimate accuracy to the user. We explore
ways to address this problem, and pay particular
attention to the computational aspects of computing
``safe'' confidence intervals.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Approximate query processing; multiple hypothesis
testing; sampling",
}
@Article{LeFevre:2008:WAA,
author = "Kristen LeFevre and David J. DeWitt and Raghu
Ramakrishnan",
title = "Workload-aware anonymization techniques for
large-scale datasets",
journal = j-TODS,
volume = "33",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386123",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Protecting individual privacy is an important problem
in microdata distribution and publishing. Anonymization
algorithms typically aim to satisfy certain privacy
definitions with minimal impact on the quality of the
resulting data. While much of the previous literature
has measured quality through simple one-size-fits-all
measures, we argue that quality is best judged with
respect to the workload for which the data will
ultimately be used.\par
This article provides a suite of anonymization
algorithms that incorporate a target class of
workloads, consisting of one or more data mining tasks
as well as selection predicates. An extensive empirical
evaluation indicates that this approach is often more
effective than previous techniques. In addition, we
consider the problem of scalability. The article
describes two extensions that allow us to scale the
anonymization algorithms to datasets much larger than
main memory. The first extension is based on ideas from
scalable decision trees, and the second is based on
sampling. A thorough performance evaluation indicates
that these techniques are viable in practice.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "anonymity; data mining; Databases; performance;
privacy; scalability",
}
@Article{Karras:2008:HSO,
author = "Panagiotis Karras and Nikos Mamoulis",
title = "Hierarchical synopses with optimal error guarantees",
journal = j-TODS,
volume = "33",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386124",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Hierarchical synopsis structures offer a viable
alternative in terms of efficiency and flexibility in
relation to traditional summarization techniques such
as histograms. Previous research on such structures has
mostly focused on a single model, based on the Haar
wavelet decomposition. In previous work, we have
introduced a more refined, wavelet-inspired
hierarchical index structure for synopsis construction:
the Haar$^+$ tree. The chief advantages of this
structure are twofold. First, it achieves higher
synopsis quality at the task of summarizing data sets
with sharp discontinuities than state-of-the-art
histogram and Haar wavelet techniques. Second, thanks
to its search space delimitation capacity, Haar$^+$
synopsis construction operates in time {\em linear\/}
in the size of the data set for {\em any\/} monotonic
distributive error metric. Contemporaneous research has
introduced another hierarchical synopsis structure, the
compact hierarchical histogram (CHH). In this article,
we elaborate on both these structures. First, we
formally prove that the CHH, in its default
binary-hierarchy form, is a simplified variant of a
Haar$^+$ tree. We then focus on the summarization
problem, with both these hierarchical synopsis
structures, in which an error guarantee expressed by a
{\em maximum-error\/} metric is required. We show that
this problem is most efficiently solved through its
dual, space-minimization counterpart, which can also
achieve {\em optimal quality}. In this case, there is a
benefit to be gained by specializing the algorithm for
each structure; hence, our algorithm for
optimal-quality maximum-error CHH requires {\em low
polynomial\/} time; on the other hand, optimal-quality
Haar$^+$ synopses for maximum-error metrics are
constructed in exponential time; hence, we also develop
a low-polynomial-time approximation scheme for the
maximum-error Haar$^+$ case. Furthermore, we extend our
approach for both general-error and maximum-error
Haar$^+$ synopses to arbitrary dimensionality. In our
experimental study, (i) we confirm the theoretically
expected superiority of Haar$^+$ synopses over Haar
wavelet methods in both construction time and achieved
quality for representative error metrics; (ii) we
demonstrate that Haar$^+$ synopses are also constructed
faster than optimal plain histograms, and, moreover,
achieve higher synopsis quality with highly
discontinuous data sets; such an advantage of a
hierarchical synopsis structure over a histogram had
been intuitively expressed, but never experimentally
verified; and (iii) we show that Haar$^+$ synopsis
quality supersedes that of a CHH.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate query processing; data synopses;
Summarization",
}
@Article{Lester:2008:EOI,
author = "Nicholas Lester and Alistair Moffat and Justin Zobel",
title = "Efficient online index construction for text
databases",
journal = j-TODS,
volume = "33",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1386118.1386125",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 29 14:05:10 MDT 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Inverted index structures are a core element of
current text retrieval systems. They can be constructed
quickly using offline approaches, in which one or more
passes are made over a static set of input data, and,
at the completion of the process, an index is available
for querying. However, there are search environments in
which even a small delay in timeliness cannot be
tolerated, and the index must always be queryable and
up to date. Here we describe and analyze a {\em
geometric partitioning\/} mechanism for online index
construction that provides a range of tradeoffs between
costs, and can be adapted to different balances of
insertion and querying operations. Detailed
experimental results are provided that show the extent
of these tradeoffs, and that these new methods can
yield substantial savings in online indexing costs.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Index construction; index update; search engines; text
indexing",
}
@Article{Ozsoyoglu:2008:FTS,
author = "Z. Meral {\"O}zsoyo{\u{g}}lu",
title = "Foreword to {TODS SIGMOD\slash PODS\slash ICDT 2007}
special issue",
journal = j-TODS,
volume = "33",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412332",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ooi:2008:IAS,
author = "Beng Chin Ooi",
title = "Introduction to {ACM SIGMOD 2007} special section",
journal = j-TODS,
volume = "33",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412333",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Melnik:2008:CMB,
author = "Sergey Melnik and Atul Adya and Philip A. Bernstein",
title = "Compiling mappings to bridge applications and
databases",
journal = j-TODS,
volume = "33",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412334",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Translating data and data access operations between
applications and databases is a longstanding data
management problem. We present a novel approach to this
problem, in which the relationship between the
application data and the persistent storage is
specified using a declarative mapping, which is
compiled into bidirectional views that drive the data
transformation engine. Expressing the application model
as a view on the database is used to answer queries,
while expressing the database schema as a view on the
application model allows us to leverage view
maintenance algorithms for update translation. This
approach has been implemented in a commercial product.
It enables developers to interact with a relational
database via a conceptual schema and an object-oriented
programming surface. We outline the implemented system
and focus on the challenges of mapping compilation,
which include rewriting queries under constraints and
supporting nonrelational constructs.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Mapping; query rewriting; updateable views",
}
@Article{Jermaine:2008:SAQ,
author = "Chris Jermaine and Subramanian Arumugam and Abhijit
Pol and Alin Dobra",
title = "Scalable approximate query processing with the {DBO}
engine",
journal = j-TODS,
volume = "33",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412335",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article describes query processing in the DBO
database system. Like other database systems designed
for ad hoc analytic processing, DBO is able to compute
the exact answers to queries over a large relational
database in a scalable fashion. Unlike any other system
designed for analytic processing, DBO can constantly
maintain a guess as to the final answer to an aggregate
query throughout execution, along with statistically
meaningful bounds for the guess's accuracy. As DBO
gathers more and more information, the guess gets more
and more accurate, until it is 100\% accurate as the
query is completed. This allows users to stop the
execution as soon as they are happy with the query
accuracy, and thus encourages exploratory data
analysis.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Online aggregation; randomized algorithms; sampling",
}
@Article{Libkin:2008:IPS,
author = "Leonid Libkin",
title = "Introduction to the {PODS 2007} special section",
journal = j-TODS,
volume = "33",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412336",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2008:ECX,
author = "Wenfei Fan and Floris Geerts and Frank Neven",
title = "Expressiveness and complexity of {XML} publishing
transducers",
journal = j-TODS,
volume = "33",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412337",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A number of languages have been developed for
specifying XML publishing, that is, transformations of
relational data into XML trees. These languages
generally describe the behaviors of a middleware
controller that builds an output tree iteratively,
issuing queries to a relational source and expanding
the tree with the query results at each step. To study
the complexity and expressive power of XML publishing
languages, this article proposes a notion of {\em
publishing transducers}, which generate XML trees from
relational data. We study a variety of publishing
transducers based on what relational queries a
transducer can issue, what temporary stores a
transducer can use during tree generation, and whether
or not some tree nodes are allowed to be virtual, that
is, excluded from the output tree. We first show how
existing XML publishing languages can be characterized
by such transducers, and thus provide a synergy between
theory and practice. We then study the membership,
emptiness, and equivalence problems for various classes
of transducers. We establish lower and upper bounds,
all matching, ranging from PTIME to undecidable.
Finally, we investigate the expressive power of these
transducers and existing languages. We show that when
treated as relational query languages, different
classes of transducers capture either complexity
classes (e.g., PSPACE) or fragments of datalog (e.g.,
linear datalog). For tree generation, we establish
connections between publishing transducers and logical
transductions, among other things.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "complexity; data exchange; expressiveness; transducer;
XML publishing",
}
@Article{Jayram:2008:ESA,
author = "T. S. Jayram and Andrew McGregor and S. Muthukrishnan
and Erik Vee",
title = "Estimating statistical aggregates on probabilistic
data streams",
journal = j-TODS,
volume = "33",
number = "4",
pages = "26:1--26:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412338",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The probabilistic stream model was introduced by
Jayram et al. [2007]. It is a generalization of the
data stream model that is suited to handling {\em
probabilistic\/} data, where each item of the stream
represents a probability distribution over a set of
possible events. Therefore, a probabilistic stream
determines a distribution over a potentially
exponential number of classical {\em deterministic\/}
streams, where each item is deterministically one of
the domain values.\par
We present algorithms for computing commonly used
aggregates on a probabilistic stream. We present the
first one pass streaming algorithms for estimating the
expected mean of a probabilistic stream. Next, we
consider the problem of estimating frequency moments
for probabilistic data. We propose a general approach
to obtain unbiased estimators working over
probabilistic data by utilizing unbiased estimators
designed for standard streams. Applying this approach,
we extend a classical data stream algorithm to obtain a
one-pass algorithm for estimating $ F_2 $, the second
frequency moment. We present the first known streaming
algorithms for estimating $ F_0 $, the number of
distinct items on probabilistic streams. Our work also
gives an efficient one-pass algorithm for estimating
the median, and a two-pass algorithm for estimating the
range.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "frequency moments; mean; median; OLAP; Probabilistic
streams",
}
@Article{Schwentick:2008:IIS,
author = "Thomas Schwentick and Dan Suciu",
title = "Introduction to {ICDT 2007} special section",
journal = j-TODS,
volume = "33",
number = "4",
pages = "27:1--27:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412339",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Buneman:2008:EIP,
author = "Peter Buneman and James Cheney and Stijn Vansummeren",
title = "On the expressiveness of implicit provenance in query
and update languages",
journal = j-TODS,
volume = "33",
number = "4",
pages = "28:1--28:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412340",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Information describing the origin of data, generally
referred to as {\em provenance}, is important in
scientific and curated databases where it is the basis
for the trust one puts in their contents. Since such
databases are constructed using operations of both
query and update languages, it is of paramount
importance to describe the effect of these languages on
provenance.\par
In this article we study provenance for query and
update languages that are closely related to SQL, and
compare two ways in which they can manipulate
provenance so that elements of the input are rearranged
to elements of the output: {\em implicit provenance},
where a query or update only provides the rearranged
output, and provenance is provided implicitly by a
default provenance semantics; and {\em explicit
provenance}, where a query or update provides both the
output and the description of the provenance of each
component of the output. Although explicit provenance
is in general more expressive, we show that the classes
of implicit provenance operations expressible by query
and update languages correspond to natural semantic
subclasses of the explicit provenance queries.\par
One of the consequences of this study is that
provenance separates the expressive power of query and
update languages. The model is also relevant to
annotation propagation schemes in which annotations on
the input to a query or update have to be transferred
to the output or vice versa.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "conservativity; nested relational calculus; nested
update language; Provenance",
}
@Article{Ghelli:2008:CAX,
author = "Giorgio Ghelli and Kristoffer Rose and J{\'e}r{\^o}me
Sim{\'e}on",
title = "Commutativity analysis for {XML} updates",
journal = j-TODS,
volume = "33",
number = "4",
pages = "29:1--29:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412341",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "An effective approach to support XML updates is to use
XQuery extended with update operations. This approach
results in very expressive languages which are
convenient for users but are difficult to optimize or
reason about. A crucial question underlying many static
analysis problems for such languages, from optimization
to view maintenance, is whether two expressions
commute. Unfortunately, commutativity is undecidable
for most existing XML update languages. In this
article, we propose a conservative analysis for an
expressive XML update language that can be used to
determine commutativity. The approach relies on a form
of path analysis that computes upper bounds for the
nodes that are accessed or modified in a given
expression. Our main result is a theorem that can be
used to identify commuting expressions. We illustrate
how the technique applies to concrete examples of query
optimization in the presence of updates.",
acknowledgement = ack-nhfb,
articleno = "29",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "commutativity; optimization; updates; XML; XQuery",
}
@Article{Pavlou:2008:FAD,
author = "Kyriacos E. Pavlou and Richard T. Snodgrass",
title = "Forensic analysis of database tampering",
journal = j-TODS,
volume = "33",
number = "4",
pages = "30:1--30:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412342",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Regulations and societal expectations have recently
expressed the need to mediate access to valuable
databases, even by insiders. One approach is tamper
detection via cryptographic hashing. This article shows
how to determine when the tampering occurred, what data
was tampered with, and perhaps, ultimately, who did the
tampering, via forensic analysis. We present four
successively more sophisticated forensic analysis
algorithms: the Monochromatic, RGBY, Tiled Bitmap, and
a3D algorithms, and characterize their ``forensic
cost'' under worst-case, best-case, and average-case
assumptions on the distribution of corruption sites. A
lower bound on forensic cost is derived, with RGBY and
a3D being shown optimal for a large number of
corruptions. We also provide validated cost formul{\ae}
for these algorithms and recommendations for the
circumstances in which each algorithm is indicated.",
acknowledgement = ack-nhfb,
articleno = "30",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "a3D algorithm; compliant records; forensic analysis
algorithm; forensic cost; Monochromatic algorithm;
Polychromatic algorithm; RGBY algorithm; Tiled Bitmap
algorithm",
}
@Article{Bartolini:2008:ESB,
author = "Ilaria Bartolini and Paolo Ciaccia and Marco Patella",
title = "Efficient sort-based skyline evaluation",
journal = j-TODS,
volume = "33",
number = "4",
pages = "31:1--31:??",
month = nov,
year = "2008",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1412331.1412343",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 23 11:45:08 MST 2008",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Skyline queries compute the set of Pareto-optimal
tuples in a relation, that is, those tuples that are
not {\em dominated\/} by any other tuple in the same
relation. Although several algorithms have been
proposed for efficiently evaluating skyline queries,
they either necessitate the relation to have been
indexed or have to perform the dominance tests on {\em
all\/} the tuples in order to determine the result. In
this article we introduce salsa, a novel skyline
algorithm that exploits the idea of presorting the
input data so as to effectively {\em limit\/} the
number of tuples to be read and compared. This makes
salsa also attractive when skyline queries are executed
on top of systems that do not understand skyline
semantics, or when the skyline logic runs on clients
with limited power and/or bandwidth. We prove that, if
one considers symmetric sorting functions, the number
of tuples to be read is minimized by sorting data
according to a ``minimum coordinate,'' minC, criterion,
and that performance can be further improved if data
distribution is known and an asymmetric sorting
function is used. Experimental results obtained on
synthetic and real datasets show that salsa
consistently outperforms state-of-the-art sequential
skyline algorithms and that its performance can be
accurately predicted.",
acknowledgement = ack-nhfb,
articleno = "31",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Monotone functions; Skyline query",
}
@Article{Mishra:2009:DQM,
author = "Chaitanya Mishra and Nick Koudas",
title = "The design of a query monitoring system",
journal = j-TODS,
volume = "34",
number = "1",
pages = "1:1--1:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508858",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Query monitoring refers to the problem of observing
and predicting various parameters related to the
execution of a query in a database system. In addition
to being a useful tool for database users and
administrators, it can also serve as an information
collection service for resource allocation and adaptive
query processing techniques. In this article, we
present a query monitoring system from the ground up,
describing various new techniques for query monitoring,
their implementation inside a real database system, and
a novel interface that presents the observed and
predicted information in an accessible manner. To
enable this system, we introduce several lightweight
online techniques for progressively estimating and
refining the cardinality of different relational
operators using information collected at query
execution time. These include binary and multiway joins
as well as typical grouping operations and combinations
thereof. We describe the various algorithms used to
efficiently implement estimators and present the
results of an evaluation of a prototype implementation
of our framework in an open-source data management
system. Our results demonstrate the feasibility and
practical utility of the approach presented herein.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "progress estimation; Query monitoring",
}
@Article{Cheng:2009:EQP,
author = "James Cheng and Yiping Ke and Wilfred Ng",
title = "Efficient query processing on graph databases",
journal = j-TODS,
volume = "34",
number = "1",
pages = "2:1--2:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508859",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problem of processing {\em subgraph
queries\/} on a database that consists of a set of
graphs. The answer to a subgraph query is the set of
graphs in the database that are supergraphs of the
query. In this article, we propose an efficient index,
{\em FG*-index}, to solve this problem.\par
The cost of processing a subgraph query using most
existing indexes mainly consists of two parts: the {\em
index probing\/} cost and the {\em candidate
verification\/} cost. Index probing is to find the
query in the index, or to find the graphs from which we
can generate a candidate answer set for the query.
Candidate verification is to test whether each graph in
the candidate set is indeed a supergraph of the query.
We design FG*-index to minimize these two costs as
follows.\par
FG*-index consists of three components: the {\em
FG-index}, the {\em feature-index}, and the {\em
FAQ-index}. First, the FG-index employs the concept of
{\em Frequent subGraph\/} ({\em FG\/}) to allow the set
of queries that are FGs to be answered without
candidate verification. We call this set of queries
{\em FG-queries}. We can enlarge the set of FG-queries
so that more queries can be answered without candidate
verification; however, a larger set of FG-queries
implies a larger FG-index and hence the index probing
cost also increases. We propose the feature-index to
reduce the index probing cost. The feature-index uses
features to filter false results that are matched in
the FG-index, so that we can quickly find the truly
matching graphs for a query. For processing
non-FG-queries, we propose the FAQ-index, which is
dynamically constructed from the set of {\em Frequently
Asked non-FG-Queries\/} ({\em FAQs\/}). Using the
FAQ-index, verification is not required for processing
FAQs and only a small number of candidates need to be
verified for processing non-FG-queries that are {\em
not frequently asked}. Finally, a comprehensive set of
experiments verifies that query processing using
FG*-index is up to orders of magnitude more efficient
than state-of-the-art indexes and it is also more
scalable.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "frequent subgraphs; Graph databases; graph indexing;
graph query processing",
}
@Article{Spiegel:2009:TSA,
author = "Joshua Spiegel and Neoklis Polyzotis",
title = "{TuG} synopses for approximate query answering",
journal = j-TODS,
volume = "34",
number = "1",
pages = "3:1--3:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508860",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article introduces the Tuple Graph (TuG)
synopses, a new class of data summaries that enable
accurate approximate answers for complex relational
queries. The proposed summarization framework adopts a
``semi-structured'' view of the relational database,
modeling a relational data set as a graph of tuples and
join queries as graph traversals, respectively. The key
idea is to approximate the structure of the induced
data graph in a concise synopsis, and to approximate
the answer to a query by performing the corresponding
traversal over the summarized graph. We detail the
(TuG) synopsis model that is based on this novel
approach, and we describe an efficient and scalable
construction algorithm for building accurate (TuG)
within a specific storage budget. We validate the
performance of (TuG) with an extensive experimental
study on real-life and synthetic datasets. Our results
verify the effectiveness of (TuG) in generating
accurate approximate answers for complex join queries,
and demonstrate their benefits over existing
summarization techniques.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate query processing; Data synopses;
selectivity estimation",
}
@Article{Kramer:2009:SIC,
author = "J{\"u}rgen Kr{\"a}mer and Bernhard Seeger",
title = "Semantics and implementation of continuous sliding
window queries over data streams",
journal = j-TODS,
volume = "34",
number = "1",
pages = "4:1--4:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508861",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In recent years the processing of continuous queries
over potentially infinite data streams has attracted a
lot of research attention. We observed that the
majority of work addresses individual stream operations
and system-related issues rather than the development
of a general-purpose basis for stream processing
systems. Furthermore, example continuous queries are
often formulated in some declarative query language
without specifying the underlying semantics precisely
enough. To overcome these deficiencies, this article
presents a consistent and powerful operator algebra for
data streams which ensures that continuous queries have
well-defined, deterministic results. In analogy to
traditional database systems, we distinguish between a
logical and a physical operator algebra. While the
logical algebra specifies the semantics of the
individual operators in a descriptive but concrete way
over temporal multisets, the physical algebra provides
efficient implementations in the form of
stream-to-stream operators. By adapting and enhancing
research from temporal databases to meet the
challenging requirements in streaming applications, we
are able to carry over the conventional transformation
rules from relational databases to stream processing.
For this reason, our approach not only makes it
possible to express continuous queries with a sound
semantics, but also provides a solid foundation for
query optimization, one of the major research topics in
the stream community. Since this article seamlessly
explains the steps from query formulation to query
execution, it outlines the innovative features and
operational functionality implemented in our
state-of-the-art stream processing infrastructure.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "continuous queries; data streams; query optimization;
Semantics",
}
@Article{Jain:2009:QAO,
author = "Alpa Jain and Panagiotis G. Ipeirotis",
title = "A quality-aware optimizer for information extraction",
journal = j-TODS,
volume = "34",
number = "1",
pages = "5:1--5:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508862",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A large amount of structured information is buried in
unstructured text. Information extraction systems can
extract structured relations from the documents and
enable sophisticated, SQL-like queries over
unstructured text. Information extraction systems are
not perfect and their output has imperfect precision
and recall (i.e., contains spurious tuples and misses
good tuples). Typically, an extraction system has a set
of parameters that can be used as ``knobs'' to tune the
system to be either precision- or recall-oriented.
Furthermore, the choice of documents processed by the
extraction system also affects the quality of the
extracted relation. So far, estimating the output
quality of an information extraction task has been an
ad hoc procedure, based mainly on heuristics. In this
article, we show how to use Receiver Operating
Characteristic (ROC) curves to estimate the extraction
quality in a statistically robust way and show how to
use ROC analysis to select the extraction parameters in
a principled manner. Furthermore, we present analytic
models that reveal how different document retrieval
strategies affect the quality of the extracted
relation. Finally, we present our maximum likelihood
approach for estimating, on the fly, the parameters
required by our analytic models to predict the runtime
and the output quality of each execution plan. Our
experimental evaluation demonstrates that our
optimization approach predicts accurately the output
quality and selects the fastest execution plan that
satisfies the output quality restrictions.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Information Extraction; ROC curves",
}
@Article{Considine:2009:RAA,
author = "Jeffrey Considine and Marios Hadjieleftheriou and
Feifei Li and John Byers and George Kollios",
title = "Robust approximate aggregation in sensor data
management systems",
journal = j-TODS,
volume = "34",
number = "1",
pages = "6:1--6:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508863",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In the emerging area of sensor-based systems, a
significant challenge is to develop scalable,
fault-tolerant methods to extract useful information
from the data the sensors collect. An approach to this
data management problem is the use of sensor database
systems, which allow users to perform aggregation
queries such as MIN, COUNT, and AVG on the readings of
a sensor network. In addition, more advanced queries
such as frequency counting and quantile estimation can
be supported. Due to energy limitations in sensor-based
networks, centralized data collection is generally
impractical, so most systems use in-network aggregation
to reduce network traffic. However, even these
aggregation strategies remain bandwidth-intensive when
combined with the fault-tolerant, multipath routing
methods often used in these environments. To avoid this
expense, we investigate the use of approximate
in-network aggregation using small sketches. We present
duplicate-insensitive sketching techniques that can be
implemented efficiently on small sensor devices with
limited hardware support and we analyze both their
performance and accuracy. Finally, we present an
experimental evaluation that validates the
effectiveness of our methods.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregation; approximation algorithms; Sensor
databases; sketches; synopses",
}
@Article{Angiulli:2009:DOP,
author = "Fabrizio Angiulli and Fabio Fassetti and Luigi
Palopoli",
title = "Detecting outlying properties of exceptional objects",
journal = j-TODS,
volume = "34",
number = "1",
pages = "7:1--7:??",
month = apr,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1508857.1508864",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:22:33 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Assume you are given a data population characterized
by a certain number of attributes. Assume, moreover,
you are provided with the information that one of the
individuals in this data population is abnormal, but no
reason whatsoever is given to you as to why this
particular individual is to be considered abnormal. In
several cases, you will be indeed interested in
discovering such reasons. This article is precisely
concerned with this problem of discovering sets of
attributes that account for the (a priori stated)
abnormality of an individual within a given dataset. A
criterion is presented to measure the abnormality of
combinations of attribute values featured by the given
abnormal individual with respect to the reference
population. In this respect, each subset of attributes
is intended to somehow represent a ``property'' of
individuals. We distinguish between global and local
properties. Global properties are subsets of attributes
explaining the given abnormality with respect to the
entire data population. With local ones, instead, two
subsets of attributes are singled out, where the former
one justifies the abnormality within the data
subpopulation selected using the values taken by the
exceptional individual on those attributes included in
the latter one. The problem of individuating abnormal
properties with associated explanations is formally
stated and analyzed. Such a formal characterization is
then exploited in order to devise efficient algorithms
for detecting both global and local forms of most
abnormal properties. The experimental evidence, which
is accounted for in the article, shows that the
algorithms are both able to mine meaningful information
and to accomplish the computational task by examining a
negligible fraction of the search space.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data mining; knowledge discovery; outlier
characterization",
}
@Article{Wong:2009:ABA,
author = "Raymond Chi-Wing Wong and Ada Wai-Chee Fu and Ke Wang
and Jian Pei",
title = "Anonymization-based attacks in privacy-preserving data
publishing",
journal = j-TODS,
volume = "34",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1538909.1538910",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:23:25 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data publishing generates much concern over the
protection of individual privacy. Recent studies
consider cases where the adversary may possess
different kinds of knowledge about the data. In this
article, we show that knowledge of the mechanism or
algorithm of anonymization for data publication can
also lead to extra information that assists the
adversary and jeopardizes individual privacy. In
particular, all known mechanisms try to minimize
information loss and such an attempt provides a
loophole for attacks. We call such an attack a
minimality attack. In this article, we introduce a
model called $m$-confidentiality which deals with
minimality attacks, and propose a feasible solution.
Our experiments show that minimality attacks are
practical concerns on real datasets and that our
algorithm can prevent such attacks with very little
overhead and information loss.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data publishing; k -anonymity; l -diversity;
minimality attack; Privacy preservation",
}
@Article{Ghinita:2009:FED,
author = "Gabriel Ghinita and Panagiotis Karras and Panos Kalnis
and Nikos Mamoulis",
title = "A framework for efficient data anonymization under
privacy and accuracy constraints",
journal = j-TODS,
volume = "34",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1538909.1538911",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:23:25 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Recent research studied the problem of publishing
microdata without revealing sensitive information,
leading to the privacy-preserving paradigms of
$k$-anonymity and $l$-diversity. $k$-anonymity protects
against the identification of an individual's record.
$l$-diversity, in addition, safeguards against the
association of an individual with specific sensitive
information. However, existing approaches suffer from
at least one of the following drawbacks: (i)
$l$-diversification is solved by techniques developed
for the simpler $k$-anonymization problem, causing
unnecessary information loss. (ii) The anonymization
process is inefficient in terms of computational and
I/O cost. (iii) Previous research focused exclusively
on the privacy-constrained problem and ignored the
equally important accuracy-constrained (or dual)
anonymization problem.\par
In this article, we propose a framework for efficient
anonymization of microdata that addresses these
deficiencies. First, we focus on one-dimensional (i.e.,
single-attribute) quasi-identifiers, and study the
properties of optimal solutions under the $k$-anonymity
and $l$-diversity models for the privacy-constrained
(i.e., direct) and the accuracy-constrained (i.e.,
dual) anonymization problems. Guided by these
properties, we develop efficient heuristics to solve
the one-dimensional problems in linear time. Finally,
we generalize our solutions to multidimensional
quasi-identifiers using space-mapping techniques.
Extensive experimental evaluation shows that our
techniques clearly outperform the existing approaches
in terms of execution time and information loss.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "anonymity; Privacy",
}
@Article{Hartmann:2009:ERA,
author = "Sven Hartmann and Sebastian Link",
title = "Efficient reasoning about a robust {XML} key
fragment",
journal = j-TODS,
volume = "34",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1538909.1538912",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:23:25 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We review key constraints in the context of XML as
introduced by Buneman et al. We demonstrate
that:\par
(1) one of the proposed inference rules is not sound in
general, and\par
(2) the inference rules are incomplete for XML key
implication, even for nonempty sets of simple key
paths.\par
This shows, in contrast to earlier statements, that the
axiomatizability of XML keys is still open, and
efficient algorithms for deciding their implication
still need to be developed. Solutions to these problems
have a wide range of applications including consistency
validation, XML schema design, data exchange and
integration, consistent query answering, XML query
optimization and rewriting, and indexing.\par
In this article, we investigate the axiomatizability
and implication problem for XML keys with nonempty sets
of simple key paths. In particular, we propose a set of
inference rules that is indeed sound and complete for
the implication of such XML keys. We demonstrate that
this fragment is robust by showing the duality of XML
key implication to the reachability problem of fixed
nodes in a suitable digraph. This enables us to develop
a quadratic-time algorithm for deciding implication,
and shows that reasoning about this XML key fragment is
practically efficient. Therefore, XML applications can
be unlocked effectively since they benefit not only
from those XML keys specified explicitly by the data
designer but also from those that are specified
implicitly.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "axiomatization; implication; reachability; XML data;
XML key",
}
@Article{Lin:2009:SII,
author = "Yi Lin and Bettina Kemme and Ricardo Jim{\'e}nez-Peris
and Marta Pati{\~n}o-Mart{\'\i}nez and Jos{\'e} Enrique
Armend{\'a}riz-I{\~n}igo",
title = "Snapshot isolation and integrity constraints in
replicated databases",
journal = j-TODS,
volume = "34",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1538909.1538913",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:23:25 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Database replication is widely used for fault
tolerance and performance. However, it requires replica
control to keep data copies consistent despite updates.
The traditional correctness criterion for the
concurrent execution of transactions in a replicated
database is 1-copy-serializability. It is based on
serializability, the strongest isolation level in a
nonreplicated system. In recent years, however,
Snapshot Isolation (SI), a slightly weaker isolation
level, has become popular in commercial database
systems. There exist already several replica control
protocols that provide SI in a replicated system.
However, most of the correctness reasoning for these
protocols has been rather informal. Additionally, most
of the work so far ignores the issue of integrity
constraints. In this article, we provide a formal
definition of 1-copy-SI using and extending a
well-established definition of SI in a nonreplicated
system. Our definition considers integrity constraints
in a way that conforms to the way integrity constraints
are handled in commercial systems. We discuss a set of
necessary and sufficient conditions for a replicated
history to be producible under 1-copy-SI. This makes
our formalism a convenient tool to prove the
correctness of replica control algorithms.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "integrity constraints; Replication; snapshot
isolation",
}
@Article{Su:2009:OOA,
author = "Weifeng Su and Jiying Wang and Frederick H.
Lochovsky",
title = "{ODE}: Ontology-assisted data extraction",
journal = j-TODS,
volume = "34",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1538909.1538914",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jul 2 12:23:25 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Online databases respond to a user query with result
records encoded in HTML files. Data extraction, which
is important for many applications, extracts the
records from the HTML files automatically. We present a
novel data extraction method, ODE (Ontology-assisted
Data Extraction), which automatically extracts the
query result records from the HTML pages. ODE first
constructs an ontology for a domain according to
information matching between the query interfaces and
query result pages from different Web sites within the
same domain. Then, the constructed domain ontology is
used during data extraction to identify the query
result section in a query result page and to align and
label the data values in the extracted records. The
ontology-assisted data extraction method is fully
automatic and overcomes many of the deficiencies of
current automatic data extraction methods. Experimental
results show that ODE is extremely accurate for
identifying the query result section in an HTML page,
segmenting the query result section into query result
records, and aligning and labeling the data values in
the query result records.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data value alignment; Domain ontology; label
assignment",
}
@Article{Agarwal:2009:ISS,
author = "Pankaj K. Agarwal and Junyi Xie and Jun Yang and Hai
Yu",
title = "Input-sensitive scalable continuous join query
processing",
journal = j-TODS,
volume = "34",
number = "3",
pages = "13:1--13:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567275",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article considers the problem of scalably
processing a large number of continuous queries. Our
approach, consisting of novel data structures and
algorithms and a flexible processing framework,
advances the state-of-the-art in several ways. First,
our approach is query sensitive in the sense that it
exploits potential overlaps in query predicates for
efficient group processing. We partition the collection
of continuous queries into groups based on the
clustering patterns of the query predicates, and apply
specialized processing strategies to heavily clustered
groups (or {\em hotspots\/}). We show how to maintain
the hotspots efficiently, and use them to scalably
process continuous select-join, band-join, and
window-join queries. Second, our approach is also data
sensitive, in the sense that it makes cost-based
decisions on how to process each incoming tuple based
on its characteristics. Experiments demonstrate that
our approach can improve the processing throughput by
orders of magnitude.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Continuous queries; data streams; event matching;
publish/subscribe",
}
@Article{Sharifzadeh:2009:PSS,
author = "Mehdi Sharifzadeh and Cyrus Shahabi and Leyla Kazemi",
title = "Processing spatial skyline queries in both vector
spaces and spatial network databases",
journal = j-TODS,
volume = "34",
number = "3",
pages = "14:1--14:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567276",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we first introduce the concept of
Spatial Skyline Queries (SSQ). Given a set of data
points $P$ and a set of query points $Q$, each data
point has a number of {\em derived spatial\/}
attributes each of which is the point's distance to a
query point. An SSQ retrieves those points of $P$ which
are not dominated by any other point in $P$ considering
their derived spatial attributes. The main difference
with the regular skyline query is that this {\em
spatial domination\/} depends on the location of the
query points $Q$. SSQ has application in several
domains such as emergency response and online maps. The
main intuition and novelty behind our approaches is
that we exploit the geometric properties of the SSQ
problem space to avoid the exhaustive examination of
all the point pairs in $P$ and $Q$. Consequently, we
reduce the complexity of SSQ search from $ O(|P|^2 |Q|)
$ to $ O(|S|^2 |C| + \sqrt {|P|}) $, where $ |S| $ and
$ |C| $ are the solution size and the number of
vertices of the convex hull of $Q$,
respectively.\par
Considering Euclidean distance, we propose two
algorithms, $ B^2 S^2 $ and VS$^2$, for static query
points and one algorithm, VCS$^2$, for streaming $Q$
whose points change location over time (e.g., are
mobile). VCS$^2$ exploits the pattern of change in $Q$
to avoid unnecessary recomputation of the skyline and
hence efficiently perform updates. We also propose two
algorithms, SNS$^2$ and VSNS$^2$, that compute the
spatial skyline with respect to the network distance in
a spatial network database. Our extensive experiments
using real-world datasets verify that both R-tree-based
$ B^2 S^2 $ and Voronoi-based VS$^2$ outperform the
best competitor approach in terms of both processing
time and I/O cost. Furthermore, their output computed
based on Euclidean distance is a good approximation of
the spatial skyline in network space. For accurate
computation of spatial skylines in network space, our
experiments showed the superiority of VSNS$^2$ over
SNS$^2$.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "spatial databases; Spatial skyline; Voronoi diagrams",
}
@Article{Yi:2009:SSG,
author = "Ke Yi and Feifei Li and Graham Cormode and Marios
Hadjieleftheriou and George Kollios and Divesh
Srivastava",
title = "Small synopses for group-by query verification on
outsourced data streams",
journal = j-TODS,
volume = "34",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567277",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Due to the overwhelming flow of information in many
data stream applications, data outsourcing is a natural
and effective paradigm for individual businesses to
address the issue of scale. In the standard data
outsourcing model, the data owner outsources streaming
data to one or more third-party servers, which answer
queries posed by a potentially large number of clients
on the data owner's behalf. Data outsourcing
intrinsically raises issues of trust, making outsourced
query assurance on data streams a problem with
important practical implications. Existing solutions
proposed in this model all build upon cryptographic
primitives such as signatures and collision-resistant
hash functions, which only work for certain types of
queries, for example, simple selection/aggregation
queries.\par
In this article, we consider another common type of
queries, namely, ``GROUP BY, SUM'' queries, which
previous techniques fail to support. Our new solutions
are not based on cryptographic primitives, but instead
use algebraic and probabilistic techniques to compute a
small synopsis on the true query result, which is then
communicated to the client so as to verify the
correctness of the query result returned by the server.
The synopsis uses a constant amount of space
irrespective of the result size, has an extremely small
probability of failure, and can be maintained using no
extra space when the query result changes as elements
stream by. We then generalize our synopsis to allow
some tolerance on the number of erroneous groups, in
order to support semantic load shedding on the server.
When the number of erroneous groups is indeed
tolerable, the synopsis can be strengthened so that we
can locate and even correct these errors. Finally, we
implement our techniques and perform an empirical
evaluation using live network traffic.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data streams; outsourcing; Synopses",
}
@Article{Perez:2009:SCS,
author = "Jorge P{\'e}rez and Marcelo Arenas and Claudio
Gutierrez",
title = "Semantics and complexity of {SPARQL}",
journal = j-TODS,
volume = "34",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567278",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "SPARQL is the standard language for querying RDF data.
In this article, we address systematically the formal
study of the database aspects of SPARQL, concentrating
in its graph pattern matching facility. We provide a
compositional semantics for the core part of SPARQL,
and study the complexity of the evaluation of several
fragments of the language. Among other complexity
results, we show that the evaluation of general SPARQL
patterns is PSPACE-complete. We identify a large class
of SPARQL patterns, defined by imposing a simple and
natural syntactic restriction, where the query
evaluation problem can be solved more efficiently. This
restriction gives rise to the class of well-designed
patterns. We show that the evaluation problem is
coNP-complete for well-designed patterns. Moreover, we
provide several rewriting rules for well-designed
patterns whose application may have a considerable
impact in the cost of evaluating SPARQL queries.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Complexity; query language; RDF; semantic Web;
SPARQL",
}
@Article{Markowetz:2009:KSR,
author = "Alexander Markowetz and Yin Yang and Dimitris
Papadias",
title = "Keyword search over relational tables and streams",
journal = j-TODS,
volume = "34",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567279",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "{\em Relational Keyword Search\/} (R-KWS) provides an
intuitive way to query relational data without
requiring SQL, or knowledge of the underlying schema.
In this article we describe a comprehensive framework
for R-KWS covering snapshot queries on conventional
tables and continuous queries on relational streams.
Our contributions are summarized as follows: (i) We
provide formal semantics, addressing the temporal
validity and order of results, spanning uniformly over
tables and streams; (ii) we investigate two general
methodologies for query processing, {\em graph based\/}
and {\em operator based}, that resolve several problems
of previous approaches; and (iii) we develop a range of
algorithms and optimizations covering both
methodologies. We demonstrate the effectiveness of
R-KWS, as well as the significant performance benefits
of the proposed techniques, through extensive
experiments with static and streaming datasets.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "data graph; data streams; query processing; relational
databases; Search",
}
@Article{Cohen:2009:ICP,
author = "Sara Cohen and Benny Kimelfeld and Yehoshua Sagiv",
title = "Incorporating constraints in probabilistic {XML}",
journal = j-TODS,
volume = "34",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2009",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1567274.1567280",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Aug 31 16:11:01 MDT 2009",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Constraints are important, not only for maintaining
data integrity, but also because they capture natural
probabilistic dependencies among data items. A {\em
probabilistic XML database\/} (PXDB) is the probability
subspace comprising the instances of a {\em
p-document\/} that satisfy a set of constraints. In
contrast to existing models that can express
probabilistic dependencies, it is shown that query
evaluation is tractable in PXDBs. The problems of
sampling and determining well-definedness (i.e.,
whether the aforesaid subspace is nonempty) are also
tractable. Furthermore, queries and constraints can
include the aggregate functions {\em count, max,
min,\/} and {\em ratio.\/} Finally, this approach can
be easily extended to allow a probabilistic
interpretation of constraints.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "constraints; Probabilistic databases; probabilistic
XML; sampling probabilistic data",
}
@Article{Sasha:2009:FTS,
author = "Dennis Sasha and Maurizio Lenzerini and Z. Meral
{\"O}zsoyo{\u{g}}lu",
title = "Foreword to {TODS SIGMOD\slash PODS 2008} special
issue",
journal = j-TODS,
volume = "34",
number = "4",
pages = "19:1--19:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cahill:2009:SIS,
author = "Michael J. Cahill and Uwe R{\"o}hm and Alan D.
Fekete",
title = "Serializable isolation for snapshot databases",
journal = j-TODS,
volume = "34",
number = "4",
pages = "20:1--20:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{He:2009:RQC,
author = "Bingsheng He and Mian Lu and Ke Yang and Rui Fang and
Naga K. Govindaraju and Qiong Luo and Pedro V. Sander",
title = "Relational query coprocessing on graphics processors",
journal = j-TODS,
volume = "34",
number = "4",
pages = "21:1--21:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2009:RSM,
author = "Marcelo Arenas and Jorge P{\'e}rez and Cristian
Riveros",
title = "The recovery of a schema mapping: {Bringing} exchanged
data back",
journal = j-TODS,
volume = "34",
number = "4",
pages = "22:1--22:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Abiteboul:2009:SAA,
author = "Serge Abiteboul and Luc Segoufin and Victor Vianu",
title = "Static analysis of active {XML} systems",
journal = j-TODS,
volume = "34",
number = "4",
pages = "23:1--23:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chow:2009:CQP,
author = "Chi-Yin Chow and Mohamed F. Mokbel and Walid G. Aref",
title = "{Casper*}: {Query} processing for location services
without compromising privacy",
journal = j-TODS,
volume = "34",
number = "4",
pages = "24:1--24:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Benedikt:2009:XRL,
author = "Michael Benedikt and Christoph Koch",
title = "From {XQuery} to relational logics",
journal = j-TODS,
volume = "34",
number = "4",
pages = "25:1--25:??",
month = dec,
year = "2009",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:50 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ghanem:2010:SVD,
author = "Thanaa M. Ghanem and Ahmed K. Elmagarmid and
Per-{\AA}ke Larson and Walid G. Aref",
title = "Supporting views in data stream management systems",
journal = j-TODS,
volume = "35",
number = "1",
pages = "1:1--1:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wu:2010:AML,
author = "Kesheng Wu and Arie Shoshani and Kurt Stockinger",
title = "Analyses of multi-level and multi-component compressed
bitmap indexes",
journal = j-TODS,
volume = "35",
number = "1",
pages = "2:1--2:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lian:2010:RSS,
author = "Xiang Lian and Lei Chen",
title = "Reverse skyline search in uncertain databases",
journal = j-TODS,
volume = "35",
number = "1",
pages = "3:1--3:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Augsten:2010:GDB,
author = "Nikolaus Augsten and Michael B{\"o}hlen and Johann
Gamper",
title = "The $ p q $-gram distance between ordered labeled
trees",
journal = j-TODS,
volume = "35",
number = "1",
pages = "4:1--4:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kolahi:2010:ITA,
author = "Solmaz Kolahi and Leonid Libkin",
title = "An information-theoretic analysis of worst-case
redundancy in database design",
journal = j-TODS,
volume = "35",
number = "1",
pages = "5:1--5:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schnaitter:2010:OAE,
author = "Karl Schnaitter and Neoklis Polyzotis",
title = "Optimal algorithms for evaluating rank joins in
database systems",
journal = j-TODS,
volume = "35",
number = "1",
pages = "6:1--6:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Soror:2010:AVM,
author = "Ahmed A. Soror and Umar Farooq Minhas and Ashraf
Aboulnaga and Kenneth Salem and Peter Kokosielis and
Sunil Kamath",
title = "Automatic virtual machine configuration for database
workloads",
journal = j-TODS,
volume = "35",
number = "1",
pages = "7:1--7:??",
month = feb,
year = "2010",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Mar 15 12:22:52 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Xiao:2010:TAT,
author = "Xiaokui Xiao and Yufei Tao and Nick Koudas",
title = "Transparent anonymization: {Thwarting} adversaries who
know the algorithm",
journal = j-TODS,
volume = "35",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735887",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Numerous generalization techniques have been proposed
for privacy-preserving data publishing. Most existing
techniques, however, implicitly assume that the
adversary knows little about the anonymization
algorithm adopted by the data publisher. Consequently,
they cannot guard against privacy attacks that exploit
various characteristics of the anonymization mechanism.
This article provides a practical solution to this
problem. First, we propose an analytical model for
evaluating disclosure risks, when an adversary knows
{\em everything\/} in the anonymization process, except
the sensitive values. Based on this model, we develop a
privacy principle, {\em transparent l-diversity}, which
ensures privacy protection against such powerful
adversaries. We identify three algorithms that achieve
transparent $l$-diversity, and verify their
effectiveness and efficiency through extensive
experiments with real data.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "generalization; l -diversity; Privacy-preserving data
publishing",
}
@Article{U:2010:OMB,
author = "Leong Hou U. and Kyriakos Mouratidis and Man Lung Yiu
and Nikos Mamoulis",
title = "Optimal matching between spatial datasets under
capacity constraints",
journal = j-TODS,
volume = "35",
number = "2",
pages = "9:1--9:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735888",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Consider a set of {\em customers\/} (e.g., WiFi
receivers) and a set of {\em service providers\/}
(e.g., wireless access points), where each provider has
a {\em capacity\/} and the quality of service offered
to its customers is anti-proportional to their
distance. The {\em Capacity Constrained Assignment\/}
(CCA) is a matching between the two sets such that (i)
each customer is assigned to at most one provider, (ii)
every provider serves no more customers than its
capacity, (iii) the maximum possible number of
customers are served, and (iv) the sum of Euclidean
distances within the assigned provider-customer pairs
is minimized. Although max-flow algorithms are
applicable to this problem, they require the complete
distance-based bipartite graph between the customer and
provider sets. For large spatial datasets, this graph
is expensive to compute and it may be too large to fit
in main memory. Motivated by this fact, we propose
efficient algorithms for {\em optimal assignment\/}
that employ novel edge-pruning strategies, based on the
spatial properties of the problem. Additionally, we
develop incremental techniques that maintain an optimal
assignment (in the presence of updates) with a
processing cost several times lower than CCA
recomputation from scratch. Finally, we present {\em
approximate\/} (i.e., suboptimal) CCA solutions that
provide a tunable trade-off between result accuracy and
computation cost, abiding by theoretical quality
guarantees. A thorough experimental evaluation
demonstrates the efficiency and practicality of the
proposed techniques.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Optimal assignment; spatial databases",
}
@Article{Liu:2010:RSI,
author = "Ziyang Liu and Yi Chen",
title = "Return specification inference and result clustering
for keyword search on {XML}",
journal = j-TODS,
volume = "35",
number = "2",
pages = "10:1--10:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735889",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Keyword search enables Web users to easily access XML
data without the need to learn a structured query
language and to study possibly complex data schemas.
Existing work has addressed the problem of selecting
qualified data nodes that match keywords and connecting
them in a meaningful way, in the spirit of inferring
the {\em where clause\/} in XQuery. However, how to
infer the {\em return clause\/} for keyword searches is
an open problem.\par
To address this challenge, we present a keyword search
engine for data-centric XML, XSeek, to infer the
semantics of the search and identify return nodes
effectively. XSeek recognizes possible entities and
attributes inherently represented in the data. It also
distinguishes between predicates and return
specifications in query keywords. Then based on the
analysis of both XML data structures and keyword
patterns, XSeek generates return nodes. Furthermore,
when the query is ambiguous and it is hard or
impossible to determine the desirable return
information, XSeek clusters the query results according
to their semantics based on the user-specified
granularity, and enables the user to easily browse and
select the desired ones. Extensive experimental studies
show the effectiveness and efficiency of XSeek.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "keyword search; result clustering; XML",
}
@Article{Bex:2010:ICR,
author = "Geert Jan Bex and Frank Neven and Thomas Schwentick
and Stijn Vansummeren",
title = "Inference of concise regular expressions and {DTDs}",
journal = j-TODS,
volume = "35",
number = "2",
pages = "11:1--11:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735890",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider the problem of inferring a concise
Document Type Definition (DTD) for a given set of
XML-documents, a problem that basically reduces to
learning {\em concise\/} regular expressions from
positive examples strings. We identify two classes of
concise regular expressions --- the single occurrence
regular expressions (SOREs) and the chain regular
expressions (CHAREs) --- that capture the far majority
of expressions used in practical DTDs. For the
inference of SOREs we present several algorithms that
first infer an automaton for a given set of example
strings and then translate that automaton to a
corresponding SORE, possibly repairing the automaton
when no equivalent SORE can be found. In the process,
we introduce a novel automaton to regular expression
rewrite technique which is of independent interest.
When only a very small amount of XML data is available,
however (for instance when the data is generated by Web
service requests or by answers to queries), these
algorithms produce regular expressions that are too
specific. Therefore, we introduce a novel learning
algorithm crx that directly infers CHAREs (which form a
subclass of SOREs) without going through an automaton
representation. We show that crx performs very well
within its target class on very small datasets.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Regular expressions; schema inference; XML",
}
@Article{DeCapitaniDiVimercati:2010:EPR,
author = "Sabrina {De Capitani Di Vimercati} and Sara Foresti
and Sushil Jajodia and Stefano Paraboschi and
Pierangela Samarati",
title = "Encryption policies for regulating access to
outsourced data",
journal = j-TODS,
volume = "35",
number = "2",
pages = "12:1--12:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735891",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Current access control models typically assume that
resources are under the strict custody of a trusted
party which monitors each access request to verify if
it is compliant with the specified access control
policy. There are many scenarios where this approach is
becoming no longer adequate. Many clear trends in Web
technology are creating a need for owners of sensitive
information to manage access to it by legitimate users
using the services of {\em honest but curious\/} third
parties, that is, parties trusted with providing the
required service but not authorized to read the actual
data content. In this scenario, the data owner encrypts
the data before outsourcing and stores them at the
server. Only the data owner and users with knowledge of
the key will be able to decrypt the data. Possible
access authorizations are to be enforced by the owner.
In this article, we address the problem of enforcing
selective access on outsourced data without need of
involving the owner in the access control process. The
solution puts forward a novel approach that combines
cryptography with authorizations, thus enforcing access
control via {\em selective encryption}. The article
presents a formal model for access control management
and illustrates how an authorization policy can be
translated into an equivalent encryption policy while
minimizing the amount of keys and cryptographic tokens
to be managed. The article also introduces a two-layer
encryption approach that allows the data owner to
outsource, besides the data, the complete management of
the authorization policy itself, thus providing
efficiency and scalability in dealing with policy
updates. We also discuss experimental results showing
that our approach is able to efficiently manage complex
scenarios.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data outsourcing; encryption policy; privacy",
}
@Article{Koutrika:2010:PQB,
author = "Georgia Koutrika and Yannis Ioannidis",
title = "Personalizing queries based on networks of composite
preferences",
journal = j-TODS,
volume = "35",
number = "2",
pages = "13:1--13:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735892",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "People's preferences are expressed at varying levels
of granularity and detail as a result of partial or
imperfect knowledge. One may have some preference for a
general class of entities, for example, liking
comedies, and another one for a fine-grained, specific
class, such as disliking recent thrillers with Al
Pacino. In this article, we are interested in capturing
such complex, multi-granular preferences for
personalizing database queries and in studying their
impact on query results. We organize the collection of
one's preferences in a {\em preference network\/} (a
directed acyclic graph), where each node refers to a
subclass of the entities that its parent refers to, and
whenever they both apply, more specific preferences
override more generic ones. We study query
personalization based on networks of preferences and
provide efficient algorithms for identifying relevant
preferences, modifying queries accordingly, and
processing personalized queries. Finally, we present
results of both synthetic and real-user experiments,
which: (a) demonstrate the efficiency of our
algorithms, (b) provide insight as to the
appropriateness of the proposed preference model, and
(c) show the benefits of query personalization based on
composite preferences compared to simpler preference
representations.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "personalization; Preference modeling; preference
networks",
}
@Article{Flesca:2010:QRI,
author = "Sergio Flesca and Filippo Furfaro and Francesco
Parisi",
title = "Querying and repairing inconsistent numerical
databases",
journal = j-TODS,
volume = "35",
number = "2",
pages = "14:1--14:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735893",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The problem of extracting consistent information from
relational databases violating integrity constraints on
numerical data is addressed. In particular, aggregate
constraints defined as linear inequalities on
aggregate-sum queries on input data are considered. The
notion of repair as consistent set of updates at
attribute-value level is exploited, and the
characterization of several data-complexity issues
related to repairing data and computing consistent
query answers is provided. Moreover, a method for
computing ``reasonable'' repairs of inconsistent
numerical databases is provided, for a restricted but
expressive class of aggregate constraints. Several
experiments are presented which assess the
effectiveness of the proposed approach in real-life
application scenarios.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "aggregate constraints; consistent query answer;
Inconsistent databases; repairs",
}
@Article{Liu:2010:CIE,
author = "Hongyan Liu and Xiaoyu Wang and Yinghui Yang",
title = "Comments on {``An integrated efficient solution for
computing frequent and top-$k$ elements in data
streams''}",
journal = j-TODS,
volume = "35",
number = "2",
pages = "15:1--15:??",
month = apr,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1735886.1735894",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 28 13:44:08 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Metwally:2006:IES}.",
abstract = "We investigate a well-known algorithm, {\em
Space-Saving\/} [Metwally et al. 2006], which has been
proven efficient and effective at mining frequent
elements in data streams. We discovered an error in one
of the theorems in Metwally et al. [2006]. Experiments
are conducted to illustrate the error.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "approximate queries; data streams; frequent elements;
top-$k$ elements; Zipfian distributions",
}
@Article{Graefe:2010:SBT,
author = "Goetz Graefe",
title = "A survey of {B}-tree locking techniques",
journal = j-TODS,
volume = "35",
number = "3",
pages = "16:1--16:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806908",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "B-trees have been ubiquitous in database management
systems for several decades, and they are used in other
storage systems as well. Their basic structure and
basic operations are well and widely understood
including search, insertion, and deletion. Concurrency
control of operations in B-trees, however, is perceived
as a difficult subject with many subtleties and special
cases. The purpose of this survey is to clarify,
simplify, and structure the topic of concurrency
control in B-trees by dividing it into two subtopics
and exploring each of them in depth.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chen:2010:COI,
author = "Su Chen and Mario A. Nascimento and Beng Chin Ooi and
Kian-Lee Tan",
title = "Continuous online index tuning in moving object
databases",
journal = j-TODS,
volume = "35",
number = "3",
pages = "17:1--17:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806909",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In a {\em Moving Object Database\/} (MOD), the
dataset, for example, the location of objects and their
distribution, and the workload change frequently.
Traditional static indexes are not able to cope well
with such changes, that is, their effectiveness and
efficiency are seriously affected. This calls for the
development of novel indexes that can be reconfigured
automatically based on the state of the system. In this
article, we design and present the ST$^2$ B-tree, a
{\em S\/}elf-{\em T\/}unable {\em S\/}patio-{\em
T\/}emporal {\em B\/}$^+$ -tree index for MODs. In
ST$^2$ B-tree, the data space is partitioned into
regions of different density with respect to a set of
reference points. Based on the density, objects in a
region are managed using a grid of appropriate
granularity; intuitively, a dense region employs a grid
with fine granularity, while a sparse region uses a
grid with coarse granularity. In this way, the ST$^2$
B-tree adapts itself to workload diversity in space. To
enable online tuning, the ST$^2$ B-tree employs a
``multitree'' indexing technique. The underlying
B$^+$-tree is logically divided into two subtrees.
Objects are dispatched to either subtree depending on
their last update time. The two subtrees are rebuilt
periodically and alternately. Whenever a subtree is
rebuilt, it is tuned to optimize performance by picking
an appropriate setting (e.g., the set of reference
points and grid granularity) based on the most recent
data and workload. To cut down the overhead of
rebuilding, we propose an eager update technique to
construct the subtree. Finally, we present a tuning
framework for the ST$^2$ B-tree, where the tuning is
conducted online and automatically without human
intervention, and without interfering with the regular
functions of the MOD. We have implemented the tuning
framework and the ST$^2$ B-tree, and conducted
extensive performance evaluations. The results show
that the self-tuning mechanism minimizes the
degradation of performance caused by workload changes
without any noticeable overhead.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Data distribution; index tuning; location-based
services; moving object indexing; self-tuning",
}
@Article{Hu:2010:PAL,
author = "Haibo Hu and Jianliang Xu and Sai Tung On and Jing Du
and Joseph Kee-Yin Ng",
title = "Privacy-aware location data publishing",
journal = j-TODS,
volume = "35",
number = "3",
pages = "18:1--18:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806910",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article examines a new problem of $k$-anonymity
with respect to a reference dataset in privacy-aware
location data publishing: given a user dataset and a
sensitive event dataset, we want to generalize the user
dataset such that by joining it with the event dataset
through location, each event is covered by at least $k$
users. Existing $k$ -anonymity algorithms generalize
every $k$ user locations to the same vague value,
regardless of the events. Therefore, they tend to
overprotect against the privacy compromise and make the
published data less useful. In this article, we propose
a new generalization paradigm called {\em local
enlargement}, as opposed to conventional hierarchy- or
partition-based generalization. Local enlargement
guarantees that user locations are enlarged just enough
to cover all events $k$ times, and thus maximize the
usefulness of the published data. We develop an $
O(H_n) $-approximate algorithm under the local
enlargement paradigm, where $n$ is the maximum number
of events a user could possibly cover and $ H_n $ is
the Harmonic number of $n$. With strong pruning
techniques and mathematical analysis, we show that it
runs efficiently and that the generalized user
locations are up to several orders of magnitude smaller
than those by the existing algorithms. In addition, it
is robust enough to protect against various privacy
attacks.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "k -anonymity; location privacy",
}
@Article{Liu:2010:IXS,
author = "Ziyang Liu and Yu Huang and Yi Chen",
title = "Improving {XML} search by generating and utilizing
informative result snippets",
journal = j-TODS,
volume = "35",
number = "3",
pages = "19:1--19:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806911",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Snippets are used by almost every text search engine
to complement the ranking scheme in order to
effectively handle user searches, which are inherently
ambiguous and whose relevance semantics are difficult
to assess. Despite the fact that XML is a standard
representation format of Web data, research on
generating result snippets for XML search remains
limited.\par
To tackle this important yet open problem, in this
article, we present a system extract which generates
snippets for XML search results. We identify that a
good XML result snippet should be a meaningful
information unit of a small size that effectively
summarizes this query result and differentiates it from
others, according to which users can quickly assess the
relevance of the query result. We have designed and
implemented a novel algorithm to satisfy these
requirements. Furthermore, we propose to cluster the
query results based on their snippets. Since XML result
clustering can only be done at query time,
snippet-based clustering significantly improves the
efficiency while compromising little clustering
accuracy. We verified the efficiency and effectiveness
of our approach through experiments.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "clustering; keyword search; snippets; XML",
}
@Article{Tao:2010:EAN,
author = "Yufei Tao and Ke Yi and Cheng Sheng and Panos Kalnis",
title = "Efficient and accurate nearest neighbor and closest
pair search in high-dimensional space",
journal = j-TODS,
volume = "35",
number = "3",
pages = "20:1--20:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806912",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Nearest Neighbor (NN) search in high-dimensional space
is an important problem in many applications. From the
database perspective, a good solution needs to have two
properties: (i) it can be easily incorporated in a
relational database, and (ii) its query cost should
increase {\em sublinearly\/} with the dataset size,
regardless of the data and query distributions. {\em
Locality-Sensitive Hashing\/} (LSH) is a well-known
methodology fulfilling both requirements, but its
current implementations either incur expensive space
and query cost, or abandon its theoretical guarantee on
the quality of query results.\par
Motivated by this, we improve LSH by proposing an
access method called the {\em Locality-Sensitive
B-tree\/} (LSB-tree) to enable fast, accurate,
high-dimensional NN search in relational databases. The
combination of several LSB-trees forms a {\em
LSB-forest\/} that has strong quality guarantees, but
improves dramatically the efficiency of the previous
LSH implementation having the same guarantees. In
practice, the LSB-tree itself is also an effective
index which consumes linear space, supports efficient
updates, and provides accurate query results. In our
experiments, the LSB-tree was faster than: (i)
iDistance (a famous technique for exact NN search) by
two orders of magnitude, and (ii) MedRank (a recent
approximate method with nontrivial quality guarantees)
by one order of magnitude, and meanwhile returned much
better results.\par
As a second step, we extend our LSB technique to solve
another classic problem, called Closest Pair (CP)
search, in high-dimensional space. The long-term
challenge for this problem has been to achieve {\em
subquadratic\/} running time at very high
dimensionalities, which fails most of the existing
solutions. We show that, using a LSB-forest, CP search
can be accomplished in (worst-case) time significantly
lower than the quadratic complexity, yet still ensuring
very good quality. In practice, accurate answers can be
found using just two LSB-trees, thus giving a
substantial reduction in the space and running time. In
our experiments, our technique was faster: (i) than
distance browsing (a well-known method for solving the
problem exactly) by several orders of magnitude, and
(ii) than D-shift (an approximate approach with
theoretical guarantees in low-dimensional space) by one
order of magnitude, and at the same time, outputs
better results.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "closest pair search; Locality-sensitive hashing;
nearest neighbor search",
}
@Article{Nash:2010:VQD,
author = "Alan Nash and Luc Segoufin and Victor Vianu",
title = "Views and queries: {Determinacy} and rewriting",
journal = j-TODS,
volume = "35",
number = "3",
pages = "21:1--21:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806913",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We investigate the question of whether a query $Q$ can
be answered using a set $V$ of views. We first define
the problem in information-theoretic terms: we say that
$V$ determines $Q$ if $V$ provides enough information
to uniquely determine the answer to $Q$. Next, we look
at the problem of rewriting $Q$ in terms of $V$ using a
specific language. Given a view language $V$ and query
language $Q$, we say that a rewriting language $R$ is
complete for $V$-to-$Q$ rewritings if every $ Q \in Q $
can be rewritten in terms of $ V \in V $ using a query
in $R$, whenever $V$ determines $Q$. While query
rewriting using views has been extensively investigated
for some specific languages, the connection to the
information-theoretic notion of determinacy, and the
question of completeness of a rewriting language have
received little attention. In this article we
investigate systematically the notion of determinacy
and its connection to rewriting. The results concern
decidability of determinacy for various view and query
languages, as well as the power required of complete
rewriting languages. We consider languages ranging from
first-order to conjunctive queries.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "Queries; rewriting; views",
}
@Article{Denecker:2010:TLR,
author = "Marc Denecker and {\'A}lvaro Cort{\'e}s-Calabuig and
Maurice Bruynooghes and Ofer Arieli",
title = "Towards a logical reconstruction of a theory for
locally closed databases",
journal = j-TODS,
volume = "35",
number = "3",
pages = "22:1--22:??",
month = jul,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1806907.1806914",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jul 28 15:53:01 MDT 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The {\em Closed World Assumption\/} (CWA) on databases
expresses the assumption that an atom not in the
database is false. This assumption is applicable only
in cases where the database has complete knowledge
about the domain of discourse. In this article, we
investigate {\em locally closed\/} databases, that is:
databases that are sound but partially incomplete about
their domain. Such databases consist of a standard
database instance, augmented with a collection of {\em
Local Closed World Assumptions\/} (LCWAs). A LCWA is a
``local'' form of the CWA, expressing that a database
relation is complete in a certain area, called a {\em
window of expertise}. In this work, we study locally
closed databases both from a knowledge representation
and from a computational perspective. At the
representation level, the approach taken in this
article distinguishes between the data that is conveyed
by a database and the metaknowledge about the area in
which the data is complete. We study the semantics of
the LCWA's and relate it to several knowledge
representation formalisms. At the reasoning level, we
study the complexity of, and algorithms for two basic
reasoning tasks: computing {\em certain\/} and {\em
possible\/} answers to queries and determining whether
a database has complete knowledge on a query. As the
complexity of these tasks is unacceptably high, we
develop efficient {\em approximate\/} methods for query
answering. We also prove that for useful classes of
queries and locally closed databases, these methods are
{\em optimal}, and thus they solve the original query
in a tractable way. As a result, we obtain classes of
queries and locally closed databases for which query
answering is tractable.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
keywords = "closed world assumption; Databases; locally closed
databases",
}
@Article{Ozsoyoglu:2010:FTI,
author = "Z. Meral {\"O}zsoyoglu",
title = "Foreword to {TODS} invited papers issue",
journal = j-TODS,
volume = "35",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862920",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ivanova:2010:ARI,
author = "Milena G. Ivanova and Martin L. Kersten and Niels J.
Nes and Romulo A. P. Gon{\c{c}}alves",
title = "An architecture for recycling intermediates in a
column-store",
journal = j-TODS,
volume = "35",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862921",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Automatic recycling of intermediate results to improve
both query response time and throughput is a grand
challenge for state-of-the-art databases. Tuples are
loaded and streamed through a tuple-at-a-time
processing pipeline, avoiding materialization of
intermediates as much as possible. This limits the
opportunities for reuse of overlapping computations to
DBA-defined materialized views and function/result
cache tuning. In contrast, the operator-at-a-time
execution paradigm produces fully materialized results
in each step of the query plan. To avoid resource
contention, these intermediates are evicted as soon as
possible. In this article we study an architecture that
harvests the byproducts of the operator-at-a-time
paradigm in a column-store system using a lightweight
mechanism, the recycler.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ghoting:2010:EAS,
author = "Amol Ghoting and Konstantin Makarychev",
title = "{I/O} efficient algorithms for serial and parallel
suffix tree construction",
journal = j-TODS,
volume = "35",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862922",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Over the past three decades, the suffix tree has
served as a fundamental data structure in string
processing. However, its widespread applicability has
been hindered due to the fact that suffix tree
construction does not scale well with the size of the
input string. With advances in data collection and
storage technologies, large strings have become
ubiquitous, especially across emerging applications
involving text, time series, and biological sequence
data. To benefit from these advances, it is imperative
that we have a scalable suffix tree construction
algorithm. The past few years have seen the emergence
of several disk-based suffix tree construction
algorithms.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Berinde:2010:SOH,
author = "Radu Berinde and Piotr Indyk and Graham Cormode and
Martin J. Strauss",
title = "Space-optimal heavy hitters with strong error bounds",
journal = j-TODS,
volume = "35",
number = "4",
pages = "26:1--26:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862923",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The problem of finding heavy hitters and approximating
the frequencies of items is at the heart of many
problems in data stream analysis. It has been observed
that several proposed solutions to this problem can
outperform their worst-case guarantees on real data.
This leads to the question of whether some stronger
bounds can be guaranteed. We answer this in the
positive by showing that a class of counter-based
algorithms (including the popular and very
space-efficient Frequent and SpacesSaving algorithms)
provides much stronger approximation guarantees than
previously known. Specifically, we show that errors in
the approximation of individual elements do not depend
on the frequencies of the most frequent elements, but
only on the frequency of the remaining tail.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2010:RIC,
author = "Wenfei Fan and Floris Geerts",
title = "Relative information completeness",
journal = j-TODS,
volume = "35",
number = "4",
pages = "27:1--27:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862924",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article investigates the question of whether a
partially closed database has complete information to
answer a query. In practice an enterprise often
maintains master data $ D m $, a closed-world database.
We say that a database $D$ is partially closed if it
satisfies a set $V$ of containment constraints of the
form $ q(D) \subset p(D m) $, where $q$ is a query in a
language $ L C $ and $p$ is a projection query. The
part of $D$ not constrained by $ (D m, V) $ is open,
from which some tuples may be missing. The database $D$
is said to be complete for a query $Q$ relative to $ (D
m, V) $ if for all partially closed extensions $ D' $
of $D$, $ Q(D') = Q(D) $, i.e., adding tuples to $D$
either violates some constraints in $V$ or does not
change the answer to $Q$.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fletcher:2010:TTS,
author = "George H. L. Fletcher and Jan {Van Den Bussche} and
Dirk {Van Gucht} and Stijn Vansummeren",
title = "Towards a theory of search queries",
journal = j-TODS,
volume = "35",
number = "4",
pages = "28:1--28:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862925",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The need to manage diverse information sources has
triggered the rise of very loosely structured data
models, known as dataspace models. Such information
management systems must allow querying in simple ways,
mostly by a form of searching. Motivated by these
developments, we propose a theory of search queries in
a general model of dataspaces. In this model, a
dataspace is a collection of data objects, where each
data object is a collection of data items. Basic search
queries are expressed using filters on data items,
following the basic model of Boolean search in
information retrieval. We characterize semantically the
class of queries that can be expressed by searching.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bjorklund:2010:IXE,
author = "Henrik Bj{\"o}rklund and Wouter Gelade and Wim
Martens",
title = "Incremental {XPath} evaluation",
journal = j-TODS,
volume = "35",
number = "4",
pages = "29:1--29:??",
month = nov,
year = "2010",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1862919.1862926",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Dec 15 10:34:39 MST 2010",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Incremental view maintenance for XPath queries asks to
maintain a materialized XPath view over an XML
database. It assumes an underlying XML database D and a
query Q. One is given a sequence of updates U to D, and
the problem is to compute the result of Q(U(D)): the
result of evaluating query Q on database D after having
applied updates U. This article initiates a systematic
study of the Boolean version of this problem. In the
Boolean version, one only wants to know whether Q(U(D))
is empty or not. In order to quickly answer this
question, we are allowed to maintain an auxiliary data
structure.",
acknowledgement = ack-nhfb,
articleno = "29",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wang:2011:OPD,
author = "Ting Wang and Ling Liu",
title = "Output privacy in data mining",
journal = j-TODS,
volume = "36",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929935",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Privacy has been identified as a vital requirement in
designing and implementing data mining systems. In
general, privacy preservation demands protecting both
input and output privacy: the former refers to
sanitizing the raw data itself before performing
mining; while the latter refers to preventing the
mining output (models or patterns) from malicious
inference attacks.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nergiz:2011:IA,
author = "Mehmet Ercan Nergiz and Acar Tamersoy and Yucel
Saygin",
title = "Instant anonymization",
journal = j-TODS,
volume = "36",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929936",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Anonymization-based privacy protection ensures that
data cannot be traced back to individuals. Researchers
working in this area have proposed a wide variety of
anonymization algorithms, many of which require a
considerable number of database accesses. This is a
problem of efficiency, especially when the released
data is subject to visualization or when the algorithm
needs to be run many times to get an acceptable ratio
of privacy/utility. In this paper, we present two
instant anonymization algorithms for the privacy
metrics k-anonymity and $ \ell $-diversity. Proposed
algorithms minimize the number of data accesses by
utilizing the summary structure already maintained by
the database management system for query selectivity.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gross-Amblard:2011:QPW,
author = "David Gross-Amblard",
title = "Query-preserving watermarking of relational databases
and {XML} documents",
journal = j-TODS,
volume = "36",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929937",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Watermarking allows robust and unobtrusive insertion
of information in a digital document. During the last
few years, techniques have been proposed for
watermarking relational databases or Xml documents,
where information insertion must preserve a specific
measure on data (for example the mean and variance of
numerical attributes). In this article we investigate
the problem of watermarking databases or Xml while
preserving a set of parametric queries in a specified
language, up to an acceptable distortion. We first show
that unrestricted databases can not be watermarked
while preserving trivial parametric queries. We then
exhibit query languages and classes of structures that
allow guaranteed watermarking capacity, namely (1)
local query languages on structures with bounded degree
Gaifman graph, and (2) monadic second-order queries on
trees or treelike structures.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Termehchy:2011:USI,
author = "Arash Termehchy and Marianne Winslett",
title = "Using structural information in {XML} keyword search
effectively",
journal = j-TODS,
volume = "36",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929938",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The popularity of XML has exacerbated the need for an
easy-to-use, high precision query interface for XML
data. When traditional document-oriented keyword search
techniques do not suffice, natural language interfaces
and keyword search techniques that take advantage of
XML structure make it very easy for ordinary users to
query XML databases. Unfortunately, current approaches
to processing these queries rely heavily on heuristics
that are intuitively appealing but ultimately ad hoc.
These approaches often retrieve false positive answers,
overlook correct answers, and cannot rank answers
appropriately. To address these problems for
data-centric XML, we propose coherency ranking (CR), a
domain- and database design-independent ranking method
for XML keyword queries that is based on an extension
of the concepts of data dependencies and mutual
information.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cautis:2011:QXD,
author = "Bogdan Cautis and Alin Deutsch and Nicola Onose and
Vasilis Vassalos",
title = "Querying {XML} data sources that export very large
sets of views",
journal = j-TODS,
volume = "36",
number = "1",
pages = "5:1--5:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929939",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problem of querying XML data sources that
accept only a limited set of queries, such as sources
accessible by Web services which can implement very
large (potentially infinite) families of XPath queries.
To compactly specify such families of queries we adopt
the Query Set Specifications, a formalism close to
context-free grammars. We say that query Q is
expressible by the specification P if it is equivalent
to some expansion of P. Q is supported by P if it has
an equivalent rewriting using some finite set of P's
expansions. We study the complexity of expressibility
and support and identify large classes of XPath queries
for which there are efficient (PTIME) algorithms.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Liu:2011:GSW,
author = "Ziyang Liu and Susan B. Davidson and Yi Chen",
title = "Generating sound workflow views for correct provenance
analysis",
journal = j-TODS,
volume = "36",
number = "1",
pages = "6:1--6:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929940",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Workflow views abstract groups of tasks in a workflow
into high level composite tasks, in order to reuse
subworkflows and facilitate provenance analysis.
However, unless a view is carefully designed, it may
not preserve the dataflow between tasks in the
workflow, that is, it may not be sound. Unsound views
can be misleading and cause incorrect provenance
analysis. This article studies the problem of
efficiently identifying and correcting unsound workflow
views with minimal changes, and constructing minimal
sound and elucidative workflow views with a set of
user-specified relevant tasks. In particular, two
related problems are investigated. First, given a
workflow view, we wish to split each unsound composite
task into the minimal number of tasks, such that the
resulting view is sound.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jin:2011:PTE,
author = "Ruoming Jin and Ning Ruan and Yang Xiang and Haixun
Wang",
title = "Path-tree: {An} efficient reachability indexing scheme
for large directed graphs",
journal = j-TODS,
volume = "36",
number = "1",
pages = "7:1--7:??",
month = mar,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1929934.1929941",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 16 09:42:23 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Reachability query is one of the fundamental queries
in graph database. The main idea behind answering
reachability queries is to assign vertices with certain
labels such that the reachability between any two
vertices can be determined by the labeling information.
Though several approaches have been proposed for
building these reachability labels, it remains open
issues on how to handle increasingly large number of
vertices in real-world graphs, and how to find the best
tradeoff among the labeling size, the query answering
time, and the construction time. In this article, we
introduce a novel graph structure, referred to as
path-tree, to help labeling very large graphs.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Law:2011:RLD,
author = "Yan-Nei Law and Haixun Wang and Carlo Zaniolo",
title = "Relational languages and data models for continuous
queries on sequences and data streams",
journal = j-TODS,
volume = "36",
number = "2",
pages = "8:1--8:??",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966386",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Most data stream management systems are based on
extensions of the relational data model and query
languages, but rigorous analyses of the problems and
limitations of this approach, and how to overcome them,
are still wanting. In this article, we elucidate the
interaction between stream-oriented extensions of the
relational model and continuous query language
constructs, and show that the resulting expressive
power problems are even more serious for data streams
than for databases. In particular, we study the loss of
expressive power caused by the loss of blocking query
operators, and characterize nonblocking queries as
monotonic functions on the database. Thus we introduce
the notion of NB-completeness to assure that a query
language is as suitable for continuous queries as it is
for traditional database queries.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gao:2011:CNN,
author = "Yunjun Gao and Baihua Zheng and Gang Chen and Chun
Chen and Qing Li",
title = "Continuous nearest-neighbor search in the presence of
obstacles",
journal = j-TODS,
volume = "36",
number = "2",
pages = "9:1--9:??",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966387",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Despite the ubiquity of physical obstacles (e.g.,
buildings, hills, and blindages, etc.) in the real
world, most of spatial queries ignore the obstacles. In
this article, we study a novel form of continuous
nearest-neighbor queries in the presence of obstacles,
namely continuous obstructed nearest-neighbor (CONN)
search, which considers the impact of obstacles on the
distance between objects. Given a data set $P$, an
obstacle set $O$, and a query line segment $q$, in a
two-dimensional space, a CONN query retrieves the
nearest neighbor $ p \in P $ of each point $ p^\prime $
on $q$ according to the obstructed distance, the
shortest path between $p$ and $ p^\prime $ without
crossing any obstacle in $O$.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yiu:2011:DAR,
author = "Man Lung Yiu and Christian S. Jensen and Jesper
M{\o}ller and Hua Lu",
title = "Design and analysis of a ranking approach to private
location-based services",
journal = j-TODS,
volume = "36",
number = "2",
pages = "10:1--10:??",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966388",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Users of mobile services wish to retrieve nearby
points of interest without disclosing their locations
to the services. This article addresses the challenge
of optimizing the query performance while satisfying
given location privacy and query accuracy requirements.
The article's proposal, SpaceTwist, aims to offer
location privacy for k nearest neighbor (kNN) queries
at low communication cost without requiring a trusted
anonymizer. The solution can be used with a
conventional DBMS as well as with a server optimized
for location-based services. In particular, we believe
that this is the first solution that expresses the
server-side functionality in a single SQL statement. In
its basic form, SpaceTwist utilizes well-known
incremental NN query processing on the server.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fagin:2011:RDE,
author = "Ronald Fagin and Phokion G. Kolaitis and Lucian Popa
and Wang-Chiew Tan",
title = "Reverse data exchange: {Coping} with nulls",
journal = j-TODS,
volume = "36",
number = "2",
pages = "11:1--11:??",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966389",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "An inverse of a schema mapping M is intended to undo
what M does, thus providing a way to perform reverse
data exchange. In recent years, three different
formalizations of this concept have been introduced and
studied, namely the notions of an inverse of a schema
mapping, a quasi-inverse of a schema mapping, and a
maximum recovery of a schema mapping. The study of
these notions has been carried out in the context in
which source instances are restricted to consist
entirely of constants, while target instances may
contain both constants and labeled nulls. This
restriction on source instances is crucial for
obtaining some of the main technical results about
these three notions, but, at the same time, limits
their usefulness, since reverse data exchange naturally
leads to source instances that may contain both
constants and labeled nulls.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Atallah:2011:AEA,
author = "Mikhail J. Atallah and Yinian Qi and Hao Yuan",
title = "Asymptotically efficient algorithms for skyline
probabilities of uncertain data",
journal = j-TODS,
volume = "36",
number = "2",
pages = "12:1--12:28",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966390",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Skyline computation is widely used in multicriteria
decision making. As research in uncertain databases
draws increasing attention, skyline queries with
uncertain data have also been studied. Some earlier
work focused on probabilistic skylines with a given
threshold; Atallah and Qi [2009] studied the problem to
compute skyline probabilities for all instances of
uncertain objects without the use of thresholds, and
proposed an algorithm with subquadratic time
complexity. In this work, we propose a new algorithm
for computing all skyline probabilities that is
asymptotically faster: worst-case $ O(n \sqrt {n} \log
n) $ time and $ O(n) $ space for 2D data; $ O(n^{2 - 1
/ d} \log^{d - 1} n) $ time and $ O(n \log^{d - 2} n) $
space for $d$-dimensional data. Furthermore, we study
the online version of the problem: Given any query
point $p$ (unknown until the query time), return the
probability that no instance in the given data set
dominates $p$. We propose an algorithm for answering
such an online query for $d$-dimensional data in $
O(n^{1 1 / d} \log^{d 1} n) $ time after preprocessing
the data in $ O(n^{2 1 / d} \log^{d 1}) $ time and
space.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lee:2011:RAF,
author = "Tony T. Lee and Tong Ye",
title = "A relational approach to functional decomposition of
logic circuits",
journal = j-TODS,
volume = "36",
number = "2",
pages = "13:1--13:??",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966391",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Functional decomposition of Boolean functions has a
profound influence on all quality aspects of
cost-effectively implementing modern digital systems
and data-mining. The relational databases are
multivalued tables, which include any truth tables of
logic functions as special cases. In this article, we
propose a relational database approach to the
decomposition of logic circuits. The relational algebra
consists of a set of well-defined algebraic operations
that can be performed on multivalued tables. Our
approach shows that the functional decomposition of
logic circuits is similar to the normalization of
relational databases; they are governed by the same
concepts of functional dependency (FD) and multivalued
dependency (MVD).",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hernich:2011:CWD,
author = "Andr{\'e} Hernich and Leonid Libkin and Nicole
Schweikardt",
title = "Closed world data exchange",
journal = j-TODS,
volume = "36",
number = "2",
pages = "14:1--14:40",
month = may,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/1966385.1966392",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 3 18:41:49 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data exchange deals with translating data structured
in some source format into data structured in some
target format, given a specification of the
relationship between the source and the target and
possibly constraints on the target; and answering
queries over the target in a way that is semantically
consistent with the information in the source.
Theoretical foundations of data exchange have been
actively explored recently. It was also noticed that
the standard semantics for query answering in data
exchange may lead to counterintuitive or anomalous
answers. In the present article, we explain that this
behavior is due to the fact that solutions can contain
invented information (information that is not related
to the source instance), and that the presence of
incomplete information in target instances has been
ignored.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Xiao:2011:ESJ,
author = "Chuan Xiao and Wei Wang and Xuemin Lin and Jeffrey Xu
Yu and Guoren Wang",
title = "Efficient similarity joins for near-duplicate
detection",
journal = j-TODS,
volume = "36",
number = "3",
pages = "15:1--15:41",
month = aug,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2000824.2000825",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Aug 23 18:27:45 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "With the increasing amount of data and the need to
integrate data from multiple data sources, one of the
challenging issues is to identify near-duplicate
records efficiently. In this article, we focus on
efficient algorithms to find a pair of records such
that their similarities are no less than a given
threshold. Several existing algorithms rely on the
prefix filtering principle to avoid computing
similarity values for all possible pairs of records. We
propose new filtering techniques by exploiting the
token ordering information; they are integrated into
the existing methods and drastically reduce the
candidate sizes and hence improve the efficiency.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Song:2011:DDR,
author = "Shaoxu Song and Lei Chen",
title = "Differential dependencies: Reasoning and discovery",
journal = j-TODS,
volume = "36",
number = "3",
pages = "16:1--16:41",
month = aug,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2000824.2000826",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Aug 23 18:27:45 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See comments \cite{Vincent:2015:TCD} and response
\cite{Song:2017:RDD}.",
abstract = "The importance of difference semantics (e.g.,
``similar'' or ``dissimilar'') has been recently
recognized for declaring dependencies among various
types of data, such as numerical values or text values.
We propose a novel form of Differential Dependencies
(dds), which specifies constraints on difference,
called differential functions, instead of
identification functions in traditional dependency
notations like functional dependencies. Informally, a
differential dependency states that if two tuples have
distances on attributes X agreeing with a certain
differential function, then their distances on
attributes Y should also agree with the corresponding
differential function on Y. For example, [date($ \leq 7
$ )] $ \rightarrow $ [price($ < 100 $ )] states that
the price difference of any two days within a week
length should be no greater than 100 dollars.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papapetrou:2011:EBS,
author = "Panagiotis Papapetrou and Vassilis Athitsos and
Michalis Potamias and George Kollios and Dimitrios
Gunopulos",
title = "Embedding-based subsequence matching in time-series
databases",
journal = j-TODS,
volume = "36",
number = "3",
pages = "17:1--17:39",
month = aug,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2000824.2000827",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Aug 23 18:27:45 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We propose an embedding-based framework for
subsequence matching in time-series databases that
improves the efficiency of processing subsequence
matching queries under the Dynamic Time Warping (DTW)
distance measure. This framework partially reduces
subsequence matching to vector matching, using an
embedding that maps each query sequence to a vector and
each database time series into a sequence of vectors.
The database embedding is computed offline, as a
preprocessing step. At runtime, given a query object,
an embedding of that object is computed online.
Relatively few areas of interest are efficiently
identified in the database sequences by comparing the
embedding of the query with the database vectors.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jampani:2011:MCD,
author = "Ravi Jampani and Fei Xu and Mingxi Wu and Luis Perez
and Chris Jermaine and Peter J. Haas",
title = "The {Monte Carlo} database system: Stochastic analysis
close to the data",
journal = j-TODS,
volume = "36",
number = "3",
pages = "18:1--18:41",
month = aug,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2000824.2000828",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Aug 23 18:27:45 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The application of stochastic models and analysis
techniques to large datasets is now commonplace.
Unfortunately, in practice this usually means
extracting data from a database system into an external
tool (such as SAS, R, Arena, or Matlab), and then
running the analysis there. This extract-and-model
paradigm is typically error-prone, slow, does not
support fine-grained modeling, and discourages what-if
and sensitivity analyses. In this article we describe
MCDB, a database system that permits a wide spectrum of
stochastic models to be used in conjunction with the
data stored in a large database, without ever
extracting the data. MCDB facilitates in-database
execution of tasks such as risk assessment, prediction,
and imputation of missing data, as well as management
of errors due to data integration, information
extraction, and privacy-preserving data
anonymization.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Stefanidis:2011:SRC,
author = "Kostas Stefanidis and Georgia Koutrika and Evaggelia
Pitoura",
title = "A survey on representation, composition and
application of preferences in database systems",
journal = j-TODS,
volume = "36",
number = "3",
pages = "19:1--19:45",
month = aug,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2000824.2000829",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Aug 23 18:27:45 MDT 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Preferences have been traditionally studied in
philosophy, psychology, and economics and applied to
decision making problems. Recently, they have attracted
the attention of researchers in other fields, such as
databases where they capture soft criteria for queries.
Databases bring a whole fresh perspective to the study
of preferences, both computational and
representational. From a representational perspective,
the central question is how we can effectively
represent preferences and incorporate them in database
querying. From a computational perspective, we can look
at how we can efficiently process preferences in the
context of database queries. Several approaches have
been proposed but a systematic study of these works is
missing.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ozsoyoglu:2011:FTI,
author = "Z. Meral {\"O}zsoyoglu",
title = "Foreword to {TODS} invited papers issue 2011",
journal = j-TODS,
volume = "36",
number = "4",
pages = "20:1--20:2",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043653",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cheng:2011:FMC,
author = "James Cheng and Yiping Ke and Ada Wai-Chee Fu and
Jeffrey Xu Yu and Linhong Zhu",
title = "Finding maximal cliques in massive networks",
journal = j-TODS,
volume = "36",
number = "4",
pages = "21:1--21:34",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043654",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Maximal clique enumeration is a fundamental problem in
graph theory and has important applications in many
areas such as social network analysis and
bioinformatics. The problem is extensively studied;
however, the best existing algorithms require memory
space linear in the size of the input graph. This has
become a serious concern in view of the massive volume
of today's fast-growing networks. We propose a general
framework for designing external-memory algorithms for
maximal clique enumeration in large graphs. The general
framework enables maximal clique enumeration to be
processed recursively in small subgraphs of the input
graph, thus allowing in-memory computation of maximal
cliques without the costly random disk access.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kim:2011:DFA,
author = "Changkyu Kim and Jatin Chhugani and Nadathur Satish
and Eric Sedlar and Anthony D. Nguyen and Tim Kaldewey
and Victor W. Lee and Scott A. Brandt and Pradeep
Dubey",
title = "Designing fast architecture-sensitive tree search on
modern multicore\slash many-core processors",
journal = j-TODS,
volume = "36",
number = "4",
pages = "22:1--22:34",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043655",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In-memory tree structured index search is a
fundamental database operation. Modern processors
provide tremendous computing power by integrating
multiple cores, each with wide vector units. There has
been much work to exploit modern processor
architectures for database primitives like scan, sort,
join, and aggregation. However, unlike other
primitives, tree search presents significant challenges
due to irregular and unpredictable data accesses in
tree traversal. In this article, we present FAST, an
extremely fast architecture-sensitive layout of the
index tree. FAST is a binary tree logically organized
to optimize for architecture features like page size,
cache line size, and Single Instruction Multiple Data
(SIMD) width of the underlying hardware.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Alexe:2011:CSM,
author = "Bogdan Alexe and Balder ten Cate and Phokion G.
Kolaitis and Wang-Chiew Tan",
title = "Characterizing schema mappings via data examples",
journal = j-TODS,
volume = "36",
number = "4",
pages = "23:1--23:48",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043656",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Schema mappings are high-level specifications that
describe the relationship between two database schemas;
they are considered to be the essential building blocks
in data exchange and data integration, and have been
the object of extensive research investigations. Since
in real-life applications schema mappings can be quite
complex, it is important to develop methods and tools
for understanding, explaining, and refining schema
mappings. A promising approach to this effect is to use
``good'' data examples that illustrate the schema
mapping at hand. We develop a foundation for the
systematic investigation of data examples and obtain a
number of results on both the capabilities and the
limitations of data examples in explaining and
understanding schema mappings.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cohen:2011:BET,
author = "Sara Cohen and Yaacov Y. Weiss",
title = "Bag equivalence of tree patterns",
journal = j-TODS,
volume = "36",
number = "4",
pages = "24:1--24:35",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043657",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "When a query is evaluated under bag semantics, each
answer is returned as many times as it has derivations.
Bag semantics has long been recognized as important,
especially when aggregation functions will be applied
to query results. This article is the first to focus on
bag semantics for tree pattern queries. In particular,
the problem of bag equivalence of a large class of tree
pattern queries (which can be used to model XPath) is
explored. The queries can contain unions, branching,
label wildcards, the vertical child and descendant
axes, the horizontal following and following-sibling
axes, as well as positional (i.e., first and last)
axes.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Abiteboul:2011:CCD,
author = "Serge Abiteboul and T.-H. Hubert Chan and Evgeny
Kharlamov and Werner Nutt and Pierre Senellart",
title = "Capturing continuous data and answering aggregate
queries in probabilistic {XML}",
journal = j-TODS,
volume = "36",
number = "4",
pages = "25:1--25:45",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043658",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Sources of data uncertainty and imprecision are
numerous. A way to handle this uncertainty is to
associate probabilistic annotations to data. Many such
probabilistic database models have been proposed, both
in the relational and in the semi-structured setting.
The latter is particularly well adapted to the
management of uncertain data coming from a variety of
automatic processes. An important problem, in the
context of probabilistic XML databases, is that of
answering aggregate queries (count, sum, avg, etc.),
which has received limited attention so far. In a model
unifying the various (discrete) semi-structured
probabilistic models studied up to now, we present
algorithms to compute the distribution of the
aggregation values (exploiting some regularity
properties of the aggregate functions) and
probabilistic moments (especially expectation and
variance) of this distribution.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bai:2011:CPT,
author = "Xiao Bai and Rachid Guerraoui and Anne-Marie Kermarrec
and Vincent Leroy",
title = "Collaborative personalized top-$k$ processing",
journal = j-TODS,
volume = "36",
number = "4",
pages = "26:1--26:38",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043659",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article presents P4Q, a fully decentralized
gossip-based protocol to personalize query processing
in social tagging systems. P4Q dynamically associates
each user with social acquaintances sharing similar
tagging behaviors. Queries are gossiped among such
acquaintances, computed on-the-fly in a collaborative,
yet partitioned manner, and results are iteratively
refined and returned to the querier. Analytical and
experimental evaluations convey the scalability of P4Q
for top-k query processing, as well its inherent
ability to cope with users updating profiles and
departing.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Goncalves:2011:DCQ,
author = "Romulo Goncalves and Martin Kersten",
title = "The {Data Cyclotron} query processing scheme",
journal = j-TODS,
volume = "36",
number = "4",
pages = "27:1--27:35",
month = dec,
year = "2011",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2043652.2043660",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Dec 20 07:23:02 MST 2011",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A grand challenge of distributed query processing is
to devise a self-organizing architecture which exploits
all hardware resources optimally to manage the database
hot set, minimize query response time, and maximize
throughput without single point global coordination.
The Data Cyclotron architecture [Goncalves and Kersten
2010] addresses this challenge using turbulent data
movement through a storage ring built from distributed
main memory and capitalizing on the functionality
offered by modern remote-DMA network facilities.
Queries assigned to individual nodes interact with the
storage ring by picking up data fragments, which are
continuously flowing around, that is, the hot set. The
storage ring is steered by the Level Of Interest (LOI)
attached to each data fragment, which represents the
cumulative query interest as it passes around the ring
multiple times.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Graefe:2012:SBT,
author = "Goetz Graefe",
title = "A survey of {B}-tree logging and recovery techniques",
journal = j-TODS,
volume = "37",
number = "1",
pages = "1:1--1:35",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109197",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "B-trees have been ubiquitous in database management
systems for several decades, and they serve in many
other storage systems as well. Their basic structure
and their basic operations are well understood
including search, insertion, and deletion. However,
implementation of transactional guarantees such as
all-or-nothing failure atomicity and durability in
spite of media and system failures seems to be
difficult. High-performance techniques such as
pseudo-deleted records, allocation-only logging, and
transaction processing during crash recovery are widely
used in commercial B-tree implementations but not
widely understood. This survey collects many of these
techniques as a reference for students, researchers,
system architects, and software developers. Central in
this discussion are physical data independence,
separation of logical database contents and physical
representation, and the concepts of user transactions
and system transactions. Many of the techniques
discussed are applicable beyond B-trees.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Martinenghi:2012:PMR,
author = "Davide Martinenghi and Marco Tagliasacchi",
title = "Proximity measures for rank join",
journal = j-TODS,
volume = "37",
number = "1",
pages = "2:1--2:46",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109198",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We introduce the proximity rank join problem, where we
are given a set of relations whose tuples are equipped
with a score and a real-valued feature vector. Given a
target feature vector, the goal is to return the K
combinations of tuples with high scores that are as
close as possible to the target and to each other,
according to some notion of distance or dissimilarity.
The setting closely resembles that of traditional rank
join, but the geometry of the vector space plays a
distinctive role in the computation of the overall
score of a combination. Also, the input relations
typically return their results either by distance from
the target or by score. Because of these aspects, it
turns out that traditional rank join algorithms, such
as the well-known HRJN, have shortcomings in solving
the proximity rank join problem, as they may read more
input than needed. To overcome this weakness, we define
a tight bound (used as a stopping criterion) that
guarantees instance optimality, that is, an I/O cost is
achieved that is always within a constant factor of
optimal. The tight bound can also be used to drive an
adaptive pulling strategy, deciding at each step which
relation to access next. For practically relevant
classes of problems, we show how to compute the tight
bound efficiently. An extensive experimental study
validates our results and demonstrates significant
gains over existing solutions.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nuray-Turan:2012:AOS,
author = "Rabia Nuray-Turan and Dmitri V. Kalashnikov and Sharad
Mehrotra and Yaming Yu",
title = "Attribute and object selection queries on objects with
probabilistic attributes",
journal = j-TODS,
volume = "37",
number = "1",
pages = "3:1--3:??",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109199",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Modern data processing techniques such as entity
resolution, data cleaning, information extraction, and
automated tagging often produce results consisting of
objects whose attributes may contain uncertainty. This
uncertainty is frequently captured in the form of a set
of multiple mutually exclusive value choices for each
uncertain attribute along with a measure of probability
for alternative values. However, the lay end-user, as
well as some end-applications, might not be able to
interpret the results if outputted in such a form.
Thus, the question is how to present such results to
the user in practice, for example, to support
attribute-value selection and object selection queries
the user might be interested in. Specifically, in this
article we study the problem of maximizing the quality
of these selection queries on top of such a
probabilistic representation. The quality is measured
using the standard and commonly used set-based quality
metrics. We formalize the problem and then develop
efficient approaches that provide high-quality answers
for these queries. The comprehensive empirical
evaluation over three different domains demonstrates
the advantage of our approach over existing
techniques.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Liu:2012:DSR,
author = "Ziyang Liu and Yi Chen",
title = "Differentiating search results on structured data",
journal = j-TODS,
volume = "37",
number = "1",
pages = "4:1--4:??",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109200",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Studies show that about 50\% of Web search is for
information exploration purposes, where a user would
like to investigate, compare, evaluate, and synthesize
multiple relevant results. Due to the absence of
general tools that can effectively analyze and
differentiate multiple results, a user has to manually
read and comprehend potential large results in an
exploratory search. Such a process is time consuming,
labor intensive and error prone. Interestingly, we find
that the metadata information embedded in structured
data provides a potential for automating or
semi-automating the comparison of multiple results. In
this article we present an approach for structured data
search result differentiation. We define the
differentiability of query results and quantify the
degree of difference. Then we define the problem of
identifying a limited number of valid features in a
result that can maximally differentiate this result
from the others, which is proved NP-hard. We propose
two local optimality conditions, namely single-swap and
multi-swap, and design efficient algorithms to achieve
local optimality. We then present a feature type-based
approach, which further improves the quality of the
features identified for result differentiation. To show
the usefulness of our approach, we implemented a system
CompareIt, which can be used to compare structured
search results as well as any objects. Our empirical
evaluation verifies the effectiveness and efficiency of
the proposed approach.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yang:2012:SES,
author = "Di Yang and Elke A. Rundensteiner and Matthew O.
Ward",
title = "Shared execution strategy for neighbor-based pattern
mining requests over streaming windows",
journal = j-TODS,
volume = "37",
number = "1",
pages = "5:1--5:??",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109201",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In diverse applications ranging from stock trading to
traffic monitoring, data streams are continuously
monitored by multiple analysts for extracting patterns
of interest in real time. These analysts often submit
similar pattern mining requests yet customized with
different parameter settings. In this work, we present
shared execution strategies for processing a large
number of neighbor-based pattern mining requests of the
same type yet with arbitrary parameter settings. Such
neighbor-based pattern mining requests cover a broad
range of popular mining query types, including
detection of clusters, outliers, and nearest neighbors.
Given the high algorithmic complexity of the mining
process, serving multiple such queries in a single
system is extremely resource intensive. The naive
method of detecting and maintaining patterns for
different queries independently is often infeasible in
practice, as its demands on system resources increase
dramatically with the cardinality of the query
workload. In order to maximize the efficiency of the
system resource utilization for executing multiple
queries simultaneously, we analyze the commonalities of
the neighbor-based pattern mining queries, and identify
several general optimization principles which lead to
significant system resource sharing among multiple
queries. In particular, as a preliminary sharing
effort, we observe that the computation needed for the
range query searches (the process of searching the
neighbors for each object) can be shared among multiple
queries and thus saves the CPU consumption. Then we
analyze the interrelations between the patterns
identified by queries with different parameters
settings, including both pattern-specific and
window-specific parameters. For that, we first
introduce an incremental pattern representation, which
represents the patterns identified by queries with
different pattern-specific parameters within a single
compact structure. This enables integrated pattern
maintenance for multiple queries. Second, by leveraging
the potential overlaps among sliding windows, we
propose a metaquery strategy which utilizes a single
query to answer multiple queries with different
window-specific parameters. By combining these three
techniques, namely the range query search sharing,
integrated pattern maintenance, and metaquery strategy,
our framework realizes fully shared execution of
multiple queries with arbitrary parameter settings. It
achieves significant savings of computational and
memory resources due to shared execution. Our
comprehensive experimental study, using real data
streams from domains of stock trades and moving object
monitoring, demonstrates that our solution is
significantly faster than the independent execution
strategy, while using only a small portion of memory
space compared to the independent execution. We also
show that our solution scales in handling large numbers
of queries in the order of hundreds or even thousands
under high input data rates.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Re:2012:UCE,
author = "Christopher R{\'e} and D. Suciu",
title = "Understanding cardinality estimation using entropy
maximization",
journal = j-TODS,
volume = "37",
number = "1",
pages = "6:1--6:??",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109202",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Cardinality estimation is the problem of estimating
the number of tuples returned by a query; it is a
fundamentally important task in data management, used
in query optimization, progress estimation, and
resource provisioning. We study cardinality estimation
in a principled framework: given a set of statistical
assertions about the number of tuples returned by a
fixed set of queries, predict the number of tuples
returned by a new query. We model this problem using
the probability space, over possible worlds, that
satisfies all provided statistical assertions and
maximizes entropy. We call this the Entropy
Maximization model for statistics (MaxEnt). In this
article we develop the mathematical techniques needed
to use the MaxEnt model for predicting the cardinality
of conjunctive queries.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nuray-Turan:2012:EWQ,
author = "Rabia Nuray-Turan and Dmitri V. Kalashnikov and Sharad
Mehrotra",
title = "Exploiting {Web} querying for {Web} people search",
journal = j-TODS,
volume = "37",
number = "1",
pages = "7:1--7:??",
month = feb,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2109196.2109203",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:17 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Searching for people on the Web is one of the most
common query types submitted to Web search engines
today. However, when a person name is queried, the
returned Webpages often contain documents related to
several distinct namesakes who have the queried name.
The task of disambiguating and finding the Webpages
related to the specific person of interest is left to
the user. Many Web People Search (WePS) approaches have
been developed recently that attempt to automate this
disambiguation process. Nevertheless, the
disambiguation quality of these techniques leaves major
room for improvement. In this article, we present a new
WePS approach. It is based on issuing additional
auxiliary queries to the Web to gain additional
knowledge about the Webpages that need to be
disambiguated. Thus, the approach uses the Web as an
external data source by issuing queries to collect
co-occurrence statistics. These statistics are used to
assess the overlap of the contextual entities extracted
from the Webpages. The article also proposes a
methodology to make this Web querying technique
efficient. Further, the article proposes an approach
that is capable of combining various types of
disambiguating information, including other common
types of similarities, by applying a correlation
clustering approach with after-clustering of singleton
clusters. These properties allow the framework to get
an advantage in terms of result quality over other
state-of-the-art WePS techniques.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schneider:2012:CDB,
author = "Markus Schneider and Tao Chen and Ganesh Viswanathan
and Wenjie Yuan",
title = "Cardinal directions between complex regions",
journal = j-TODS,
volume = "37",
number = "2",
pages = "8:1--8:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188350",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Besides topological relationships and approximate
relationships, cardinal directions like north and
southwest have turned out to be an important class of
qualitative spatial relationships. They are of
interdisciplinary interest in fields like cognitive
science, robotics, artificial intelligence, and
qualitative spatial reasoning. In spatial databases and
Geographic Information Systems (GIS) they are
frequently used as join and selection criteria in
spatial queries. However, the available computational
models of cardinal directions suffer a number of
problems like the use of too coarse approximations of
the two spatial operand objects in terms of single
representative points or minimum bounding rectangles,
the lacking property of converseness of the cardinal
directions computed, and the limited applicability to
simple instead of complex regions only. This article
proposes and formally defines a novel two-phase model,
called the Objects Interaction Matrix (OIM) model, that
solves these problems, and determines cardinal
directions for even complex regions. The model consists
of a tiling phase and an interpretation phase. In the
tiling phase, a tiling strategy first determines the
zones belonging to the nine cardinal directions of each
individual region object and then intersects them. The
result leads to a bounded grid called objects
interaction grid. For each grid cell the information
about the region objects that intersect it is stored in
an objects interaction matrix. In the subsequent
interpretation phase, a well-defined interpretation
method is applied to such a matrix and determines the
cardinal direction. Spatial example queries illustrate
our new cardinal direction concept that is embedded in
a spatial extension of SQL and provides user-defined
cardinal direction predicates.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wijsen:2012:CCQ,
author = "Jef Wijsen",
title = "Certain conjunctive query answering in first-order
logic",
journal = j-TODS,
volume = "37",
number = "2",
pages = "9:1--9:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188351",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Primary key violations provide a natural means for
modeling uncertainty in the relational data model. A
repair (or possible world) of a database is then
obtained by selecting a maximal number of tuples
without ever selecting two distinct tuples that have
the same primary key value. For a Boolean query q, the
problem CERTAINTY( q ) takes as input a database db and
asks whether q evaluates to true on every repair of db.
We are interested in determining queries q for which
CERTAINTY( q ) is first-order expressible (and hence in
the low complexity class AC ${}^\circ $ ). For queries
q in the class of conjunctive queries without
self-join, we provide a necessary syntactic condition
for first-order expressibility of CERTAINTY( q ). For
acyclic queries (in the sense of Beeri et al. [1983]),
this necessary condition is also a sufficient
condition. So we obtain a decision procedure for
first-order expressibility of CERTAINTY( q ) when q is
acyclic and without self-join. We also show that if
CERTAINTY( q ) is first-order expressible, its
first-order definition, commonly called certain
first-order rewriting, can be constructed in a rather
straightforward way.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Abiteboul:2012:CWS,
author = "Serge Abiteboul and Pierre Bourhis and Victor Vianu",
title = "Comparing workflow specification languages: a matter
of views",
journal = j-TODS,
volume = "37",
number = "2",
pages = "10:1--10:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188352",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We address the problem of comparing the expressiveness
of workflow specification formalisms using a notion of
view of a workflow. Views allow to compare widely
different workflow systems by mapping them to a common
representation capturing the observables relevant to
the comparison. Using this framework, we compare the
expressiveness of several workflow specification
mechanisms, including automata, temporal constraints,
and pre-and postconditions, with XML and relational
databases as underlying data models. One surprising
result shows the considerable power of static
constraints to simulate apparently much richer workflow
control mechanisms.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tassa:2012:SDC,
author = "Tamir Tassa and Ehud Gudes",
title = "Secure distributed computation of anonymized views of
shared databases",
journal = j-TODS,
volume = "37",
number = "2",
pages = "11:1--11:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188353",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider the problem of computing efficient
anonymizations of partitioned databases. Given a
database that is partitioned between several sites,
either horizontally or vertically, we devise secure
distributed algorithms that allow the different sites
to obtain a k -anonymized and l-diverse view of the
union of their databases, without disclosing sensitive
information. Our algorithms are based on the sequential
algorithm [Goldberger and Tassa 2010] that offers
anonymizations with utility that is significantly
better than other anonymization algorithms, and in
particular those that were implemented so far in the
distributed setting. Our algorithms can apply to
different generalization techniques and utility
measures and to any number of sites. While previous
distributed algorithms depend on costly cryptographic
primitives, the cryptographic assumptions of our
solution are surprisingly minimal.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sheng:2012:EAA,
author = "Cheng Sheng and Yufei Tao and Jianzhong Li",
title = "Exact and approximate algorithms for the most
connected vertex problem",
journal = j-TODS,
volume = "37",
number = "2",
pages = "12:1--12:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188354",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "An (edge) hidden graph is a graph whose edges are
notexplicitly given. Detecting the presence of an edge
requires an expensive edge probing query. We consider
the $k$ Most Connected Vertex ($k$-MCV) problem on
hidden bipartite graphs. Given a bipartite graph $G$
with independent vertex sets $B$ and $W$, the goal is
to find the $k$ vertices in $B$ with the largest
degrees using the minimum number of queries. This
problem can be regarded as a top-$k$ extension of
semi-join, and is encountered in several applications
in practice. If $B$ and $W$ have $n$ and $m$ vertices,
respectively, the number of queries needed to solve the
problem is $ n m $ in the worst case. This, however, is
a pessimistic estimate on how many queries are
necessary on practical data. In fact, on some inputs,
the problem may be settled with only $ k m + n $
queries, which is significantly lower than $ n m $ for
$ k \ll n $. The huge difference between $ k m + n $
and $ n m $ makes it interesting to design an adaptive
algorithm that is guaranteed to achieve the best
possible performance on every input $G$. For $ k \leq n
/ 2 $, we give an algorithm that is instance optimal
among a broad class of solutions. This means that, for
any $G$, our algorithm can perform more queries than
the optimal solution (which is unknown) by only a
constant factor, which can be shown at most $2$. As a
second step, we study an $ \epsilon $-approximate
version of the $k$-MCV problem, where $ \epsilon $ is a
parameter satisfying $ 0 < \epsilon < 1 $. The goal is
to return $k$ black vertices $ b_1, \ldots, b_k $ such
that the degree of $ b_i (i \leq k) $ can be smaller
than $ t_i $ by a factor of at most $ \epsilon $, where
$ t_i, \ldots, t_k $ (in nonascending order) are the
degrees of the $k$ most connected black vertices. We
give an efficient randomized algorithm that
successfully finds the correct answer with high
probability. In particular, for a fixed $ \epsilon $
and a fixed success probability, our algorithm performs
$ o(n m) $ queries in expectation for $ t_k = \omega
(\log n) $. In other words, whenever $ t_k $ is greater
than $ \log n $ by more than a constant, our algorithm
beats the $ \Omega (n m) $ lower bound for solving the
$k$-MCV problem exactly. All the proposed algorithms,
despite the complication of their underlying theory,
are simple enough for easy implementation in practice.
Extensive experiments have confirmed that their
performance in reality agrees with our theoretical
findings very well.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hartmann:2012:IPD,
author = "Sven Hartmann and Sebastian Link",
title = "The implication problem of data dependencies over
{SQL} table definitions: {Axiomatic}, algorithmic and
logical characterizations",
journal = j-TODS,
volume = "37",
number = "2",
pages = "13:1--13:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188355",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We investigate the implication problem for classes of
data dependencies over SQL table definitions. Under
Zaniolo's ``no information'' interpretation of null
markers we establish an axiomatization and algorithms
to decide the implication problem for the combined
class of functional and multivalued dependencies in the
presence of NOT NULL constraints. The resulting theory
subsumes three previously orthogonal frameworks. We
further show that the implication problem of this class
is equivalent to that in a propositional fragment of
Schaerf and Cadoli's [1995] family of para-consistent
S-3 logics. In particular, S is the set of variables
that correspond to attributes declared NOT NULL. We
also show how our equivalences for multivalued
dependencies can be extended to Delobel's class of full
first-order hierarchical decompositions, and the
equivalences for functional dependencies can be
extended to arbitrary Boolean dependencies. These
dualities allow us to transfer several findings from
the propositional fragments to the corresponding
classes of data dependencies, and vice versa. We show
that our results also apply to Codd's null
interpretation ``value unknown at present'', but not to
Imielinski's [1989] or-relations utilizing Levene and
Loizou's weak possible world semantics [Levene and
Loizou 1998]. Our findings establish NOT NULL
constraints as an effective mechanism to balance not
only the certainty in database relations but also the
expressiveness with the efficiency of entailment
relations. They also control the degree by which the
implication of data dependencies over total relations
is soundly approximated in SQL table definitions.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhang:2012:SS,
author = "Wenjie Zhang and Xuemin Lin and Ying Zhang and
Muhammad Aamir Cheema and Qing Zhang",
title = "Stochastic skylines",
journal = j-TODS,
volume = "37",
number = "2",
pages = "14:1--14:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188356",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In many applications involving multiple criteria
optimal decision making, users may often want to make a
personal trade-off among all optimal solutions for
selecting one object that fits best their personal
needs. As a key feature, the skyline in a
multidimensional space provides the minimum set of
candidates for such purposes by removing all points not
preferred by any (monotonic) utility/scoring functions;
that is, the skyline removes all objects not preferred
by any user no matter how their preferences vary.
Driven by many recent applications with uncertain data,
the probabilistic skyline model is proposed to retrieve
uncertain objects based on skyline probabilities.
Nevertheless, skyline probabilities cannot capture the
preferences of monotonic utility functions. Motivated
by this, in this article we propose a novel skyline
operator, namely stochastic skylines. In the light of
the expected utility principle, stochastic skylines
guarantee to provide the minimum set of candidates to
optimal solutions over a family of utility functions.
We first propose the lskyline operator based on the
lower orthant orders. lskyline guarantees to provide
the minimum set of candidates to the optimal solutions
for the family of monotonic multiplicative utility
functions. While lskyline works very effectively for
the family of multiplicative functions, it may miss
optimal solutions for other utility /scoring functions
(e.g., linear functions). To resolve this, we also
propose a general stochastic skyline operator,
gskyline, based on the usual orders. gskyline provides
the minimum candidate set to the optimal solutions for
all monotonic functions. For the first time regarding
the existing literature, we investigate the
complexities of determining a stochastic order between
two uncertain objects whose probability distributions
are described discretely. We firstly show that
determining the lower orthant order is NP-complete with
respect to the dimensionality; consequently the problem
of computing lskyline is NP-complete. We also show an
interesting result as follows. While the usual order
involves more complicated geometric forms than the
lower orthant order, the usual order may be determined
in polynomial time regarding all the inputs, including
the dimensionality; this implies that gskyline can be
computed in polynomial time. A general framework is
developed for efficiently and effectively retrieving
lskyline and gskyline from a set of uncertain objects,
respectively, together with efficient and effective
filtering techniques. Novel and efficient verification
algorithms are developed to efficiently compute
lskyline over multidimensional uncertain data, which
run in polynomial time if the dimensionality is fixed,
and to efficiently compute gskyline in polynomial time
regarding all inputs. We also show, by theoretical
analysis and experiments, that the sizes of lskyline
and gskyline are both quite similar to that of
conventional skyline over certain data. Comprehensive
experiments demonstrate that our techniques are
efficient and scalable regarding both CPU and IO
costs.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Xia:2012:OSS,
author = "Tian Xia and Donghui Zhang and Zheng Fang and Cindy
Chen and Jie Wang",
title = "Online subspace skyline query processing using the
{Compressed SkyCube}",
journal = j-TODS,
volume = "37",
number = "2",
pages = "15:1--15:??",
month = may,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2188349.2188357",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 1 17:45:19 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The skyline query can help identify the ``best''
objects in a multi-attribute dataset. During the past
decade, this query has received considerable attention
in the database research community. Most research
focused on computing the ``skyline'' of a dataset, or
the set of ``skyline objects'' that are not dominated
by any other object. Such algorithms are not
appropriate in an online system, which should respond
in real time to skyline query requests with arbitrary
subsets of the attributes (also called subspaces). To
guarantee real-time response, an online system should
precompute the skylines for all subspaces, and look up
a skyline upon query. Unfortunately, because the number
of subspaces is exponential to the number of
attributes, such pre computation has very expensive
storage cost and update cost. We propose the Compressed
SkyCube (CSC) that is much more compact, yet can still
return the skyline of any subspace without consulting
the base table. The CSC therefore combines the
advantage of precomputation in that it can respond to
queries in real time, and the advantage of
no-precomputation in that it has efficient space cost
and update cost. This article presents the CSC data
structures, the CSC query algorithm, the CSC update
algorithm, and the CSC initial computation scheme. A
solution to extend to high-dimensional data is also
proposed.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ozsoyoglu:2012:Fa,
author = "Z. Meral {\"O}zsoyoglu",
title = "Foreword",
journal = j-TODS,
volume = "37",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338627",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Graefe:2012:FBT,
author = "Goetz Graefe and Hideaki Kimura and Harumi Kuno",
title = "{Foster} {B}-trees",
journal = j-TODS,
volume = "37",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338630",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Foster B-trees are a new variant of B-trees that
combines advantages of prior B-tree variants optimized
for many-core processors and modern memory hierarchies
with flash storage and nonvolatile memory. Specific
goals include: (i) minimal concurrency control
requirements for the data structure, (ii) efficient
migration of nodes to new storage locations, and (iii)
support for continuous and comprehensive self-testing.
Like B$^{\rm link}$-trees, Foster B-trees optimize
latching without imposing restrictions or specific
designs on transactional locking, for example, key
range locking. Like write-optimized B-trees, and unlike
B$^{\rm link}$-trees, Foster B-trees enable large
writes on RAID and flash devices as well as wear
leveling and efficient defragmentation. Finally, they
support continuous and inexpensive yet comprehensive
verification of all invariants, including all
cross-node invariants of the B-tree structure. An
implementation and a performance evaluation show that
the Foster B-tree supports high concurrency and high
update rates without compromising consistency,
correctness, or read performance.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wang:2012:RAT,
author = "Junhu Wang and Jeffrey Xu Yu",
title = "Revisiting answering tree pattern queries using
views",
journal = j-TODS,
volume = "37",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338631",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We revisit the problem of answering tree pattern
queries using views. We first show that, for queries
and views that do not have nodes labeled with the
wildcard *, there is an approach which does not require
us to find any rewritings explicitly, yet which
produces the same answers as the maximal contained
rewriting. Then, using the new approach, we give simple
conditions and a corresponding algorithm for
identifying redundant view answers, which are view
answers that can be ignored when evaluating the maximal
contained rewriting. We also consider redundant view
answers in the case where there are multiple views, the
relationship between redundant views and redundant view
answers, and discuss how to combine the removal of
redundant view answers and redundant rewritings. We
show that the aforesaid results can be extended to a
number of other special cases. Finally, for arbitrary
queries and views in P$^{{/, / /, ., []}}$, we provide
a method to find the maximal contained rewriting and
show how to answer the query using views without
explicitly finding the rewritings.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{David:2012:ERA,
author = "Claire David and Leonid Libkin and Tony Tan",
title = "Efficient reasoning about data trees via integer
linear programming",
journal = j-TODS,
volume = "37",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338632",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data trees provide a standard abstraction of XML
documents with data values: they are trees whose nodes,
in addition to the usual labels, can carry labels from
an infinite alphabet (data). Therefore, one is
interested in decidable formalisms for reasoning about
data trees. While some are known-such as the
two-variable logic-they tend to be of very high
complexity, and most decidability proofs are highly
nontrivial. We are therefore interested in reasonable
complexity formalisms as well as better techniques for
proving decidability. Here we show that many decidable
formalisms for data trees are subsumed-fully or
partially-by the power of tree automata together with
set constraints and linear constraints on cardinalities
of various sets of data values. All these constraints
can be translated into instances of integer linear
programming, giving us an NP upper bound on the
complexity of the reasoning tasks. We prove that this
bound, as well as the key encoding technique, remain
very robust, and allow the addition of features such as
counting of paths and patterns, and even a concise
encoding of constraints, without increasing the
complexity. The NP bound is tight, as we also show that
the satisfiability of a single set constraint is
already NP-hard. We then relate our results to several
reasoning tasks over XML documents, such as
satisfiability of schemas and data dependencies and
satisfiability of the two-variable logic. As a final
contribution, we describe experimental results based on
the implementation of some reasoning tasks using the
SMT solver Z3.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lemire:2012:RRB,
author = "Daniel Lemire and Owen Kaser and Eduardo Gutarra",
title = "Reordering rows for better compression: {Beyond} the
lexicographic order",
journal = j-TODS,
volume = "37",
number = "3",
pages = "20:1--20:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338633",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Sorting database tables before compressing them
improves the compression rate. Can we do better than
the lexicographical order? For minimizing the number of
runs in a run-length encoding compression scheme, the
best approaches to row-ordering are derived from
traveling salesman heuristics, although there is a
significant trade-off between running time and
compression. A new heuristic, Multiple Lists, which is
a variant on Nearest Neighbor that trades off
compression for a major running-time speedup, is a good
option for very large tables. However, for some
compression schemes, it is more important to generate
long runs rather than few runs. For this case, another
novel heuristic, Vortex, is promising. We find that we
can improve run-length encoding up to a factor of 3
whereas we can improve prefix coding by up to 80\%:
these gains are on top of the gains due to
lexicographically sorting the table. We prove that the
new row reordering is optimal (within 10\%) at
minimizing the runs of identical values within columns,
in a few cases.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gupta:2012:EQE,
author = "Nitin Gupta and Lucja Kot and Sudip Roy and Gabriel
Bender and Johannes Gehrke and Christoph Koch",
title = "Entangled queries: {Enabling} declarative data-driven
coordination",
journal = j-TODS,
volume = "37",
number = "3",
pages = "21:1--21:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338629",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many data-driven social and Web applications involve
collaboration and coordination. The vision of
Declarative Data-Driven Coordination (D3C), proposed in
Kot et al. [2010], is to support coordination in the
spirit of data management: to make it data-centric and
to specify it using convenient declarative languages.
This article introduces entangled queries, a language
that extends SQL by constraints that allow for the
coordinated choice of result tuples across queries
originating from different users or applications. It is
nontrivial to define a declarative coordination
formalism without arriving at the general (NP-complete)
Constraint Satisfaction Problem from AI. In this
article, we propose an efficiently enforceable
syntactic safety condition that we argue is at the
sweet spot where interesting declarative power meets
applicability in large-scale data management systems
and applications. The key computational problem of D3C
is to match entangled queries to achieve coordination.
We present an efficient matching algorithm which
statically analyzes query workloads and merges
coordinating entangled queries into compound SQL
queries. These can be sent to a standard database
system and return only coordinated results. We present
the overall architecture of an implemented system that
contains our evaluation algorithm. We also describe a
proof-of-concept Facebook application we have built on
top of this system to allow friends to coordinate
flight plans. Finally, we evaluate the performance of
the matching algorithm experimentally on realistic
coordination workloads.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Damaggio:2012:ASD,
author = "Elio Damaggio and Alin Deutsch and Victor Vianu",
title = "Artifact systems with data dependencies and
arithmetic",
journal = j-TODS,
volume = "37",
number = "3",
pages = "22:1--22:??",
month = aug,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2338626.2338628",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Sep 6 09:52:39 MDT 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the static verification problem for
data-centric business processes, specified in a variant
of IBM's ``business artifact'' model. Artifacts are
records of variables that correspond to
business-relevant objects and are updated by a set of
services equipped with pre- and postconditions, that
implement business process tasks. The verification
problem consists in statically checking whether all
runs of an artifact system satisfy desirable properties
expressed in a first-order extension of linear-time
temporal logic. Previous work identified the class of
guarded artifact systems and properties, for which
verification is decidable. However, the results suffer
an important limitation: they fail in the presence of
even very simple data dependencies or arithmetic, both
crucial to real-life business processes. In this
article, we extend the artifact model and verification
results to alleviate this limitation. We identify a
practically significant class of business artifacts
with data dependencies and arithmetic, for which
verification is decidable. The technical machinery
needed to establish the results is fundamentally
different from previous work. While the worst-case
complexity of verification is nonelementary, we
identify various realistic restrictions yielding more
palatable upper bounds.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ozsoyoglu:2012:Fb,
author = "Z. Meral {\"O}zsoyoglu",
title = "Foreword",
journal = j-TODS,
volume = "37",
number = "4",
pages = "23:1--23:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389242",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kimelfeld:2012:MCV,
author = "Benny Kimelfeld and Jan Vondr{\'a}k and Ryan
Williams",
title = "Maximizing Conjunctive Views in Deletion Propagation",
journal = j-TODS,
volume = "37",
number = "4",
pages = "24:1--24:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389243",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In deletion propagation, tuples from the database are
deleted in order to reflect the deletion of a tuple
from the view. Such an operation may result in the
(often necessary) deletion of additional tuples from
the view, besides the intentionally deleted one. The
article studies the complexity of deletion propagation,
where the view is defined by a conjunctive query (CQ),
and the goal is to maximize the number of tuples that
remain in the view. Buneman et al. showed that for some
simple CQs, this problem can be solved by a
straightforward algorithm, which is called here the
unidimensional algorithm. The article identifies
additional cases of CQs where the unidimensional
algorithm succeeds, and in contrast, shows that for
some other CQs the problem is NP-hard to approximate
better than some constant ratio. In fact, it is shown
here that among the CQs without self joins, the hard
CQs are exactly the ones that the unidimensional
algorithm fails on. In other words, the following
dichotomy result is proved: for every CQ without self
joins, deletion propagation is either APX-hard or
solvable (in polynomial time) by the unidimensional
algorithm. The article then presents approximation
algorithms for certain CQs where deletion propagation
is APX-hard. Specifically, two constant-ratio (and
polynomial-time) approximation algorithms are given for
the class of sunflower CQs (i.e., CQs having a
sunflower hypergraph) without self joins. The first
algorithm, providing the approximation ratio $ 1 - 1 /
e $, is obtained by formulating the problem at hand as
that of maximizing a monotone submodular function
subject to a matroid constraint, and then using a known
algorithm for such maximization. The second algorithm
gives a smaller approximation ratio, $ 1 / 2 $, yet in
polynomial time even under combined complexity.
Finally, it is shown that self joins can significantly
harden approximation in deletion propagation.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2012:DCD,
author = "Wenfei Fan and Floris Geerts and Jef Wijsen",
title = "Determining the Currency of Data",
journal = j-TODS,
volume = "37",
number = "4",
pages = "25:1--25:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389244",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data in real-life databases become obsolete rapidly.
One often finds that multiple values of the same entity
reside in a database. While all of these values were
once correct, most of them may have become stale and
inaccurate. Worse still, the values often do not carry
reliable timestamps. With this comes the need for
studying data currency, to identify the current value
of an entity in a database and to answer queries with
the current values, in the absence of reliable
timestamps. This article investigates the currency of
data. (1) We propose a model that specifies partial
currency orders in terms of simple constraints. The
model also allows us to express what values are copied
from other data sources, bearing currency orders in
those sources, in terms of copy functions defined on
correlated attributes. (2) We study fundamental
problems for data currency, to determine whether a
specification is consistent, whether a value is more
current than another, and whether a query answer is
certain no matter how partial currency orders are
completed. (3) Moreover, we identify several problems
associated with copy functions, to decide whether a
copy function imports sufficient current data to answer
a query, whether a copy function can be extended to
import necessary current data for a query while
respecting the constraints, and whether it suffices to
copy data of a bounded size. (4) We establish upper and
lower bounds of these problems, all matching, for
combined complexity and data complexity, and for a
variety of query languages. We also identify special
cases that warrant lower complexity.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sheng:2012:WCE,
author = "Cheng Sheng and Yufei Tao",
title = "Worst-Case {I/O}-Efficient Skyline Algorithms",
journal = j-TODS,
volume = "37",
number = "4",
pages = "26:1--26:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389245",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider the skyline problem (aka the maxima
problem), which has been extensively studied in the
database community. The input is a set $P$ of $d$
dimensional points. A point dominates another if the
coordinate of the former is at most that of the latter
on every dimension. The goal is to find the skyline,
which is the set of points $ p \in P $ such that $p$ is
not dominated by any other point in $P$. The main
result of this article is that, for any fixed
dimensionality $ d \geq 3 $, in external memory the
skyline problem can be settled by performing $ O((N /
B) \log_{M / B}^{d - 2}(N / B)) $ I/Os in the worst
case, where $N$ is the cardinality of $P$, $B$ the size
of a disk block, and $M$ the capacity of main memory.
Similar bounds can also be achieved for computing
several skyline variants, including the $k$-dominant
skyline, $k$-skyband, and $ \alpha $ skyline.
Furthermore, the performance can be improved if some
dimensions of the data space have small domains. When
the dimensionality $d$ is not fixed, the challenge is
to outperform the naive algorithm that simply checks
all pairs of points in $ P \times P $. We give an
algorithm that terminates in $ O((N / B) \log^{d - 2}
N) $ I/Os, thus beating the naive solution for any $ d
= O(\log N / \log \log N) $.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2012:SPS,
author = "Boduo Li and Edward Mazur and Yanlei Diao and Andrew
McGregor and Prashant Shenoy",
title = "{SCALLA}: a Platform for Scalable One-Pass Analytics
Using {MapReduce}",
journal = j-TODS,
volume = "37",
number = "4",
pages = "27:1--27:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389246",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Today's one-pass analytics applications tend to be
data-intensive in nature and require the ability to
process high volumes of data efficiently. MapReduce is
a popular programming model for processing large
datasets using a cluster of machines. However, the
traditional MapReduce model is not well-suited for
one-pass analytics, since it is geared towards batch
processing and requires the dataset to be fully loaded
into the cluster before running analytical queries.
This article examines, from a systems standpoint, what
architectural design changes are necessary to bring the
benefits of the MapReduce model to incremental one-pass
analytics. Our empirical and theoretical analyses of
Hadoop-based MapReduce systems show that the widely
used sort-merge implementation for partitioning and
parallel processing poses a fundamental barrier to
incremental one-pass analytics, despite various
optimizations. To address these limitations, we propose
a new data analysis platform that employs hash
techniques to enable fast in-memory processing, and a
new frequent key based technique to extend such
processing to workloads that require a large key-state
space. Evaluation of our Hadoop-based prototype using
real-world workloads shows that our new platform
significantly improves the progress of map tasks,
allows the reduce progress to keep up with the map
progress, with up to 3 orders of magnitude reduction of
internal data spills, and enables results to be
returned continuously during the job.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2012:WHT,
author = "Yinan Li and Jignesh M. Patel and Allison Terrell",
title = "{WHAM}: a High-Throughput Sequence Alignment Method",
journal = j-TODS,
volume = "37",
number = "4",
pages = "28:1--28:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389247",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Over the last decade, the cost of producing genomic
sequences has dropped dramatically due to the current
so-called next-generation sequencing methods. However,
these next-generation sequencing methods are critically
dependent on fast and sophisticated data processing
methods for aligning a set of query sequences to a
reference genome using rich string matching models. The
focus of this work is on the design, development and
evaluation of a data processing system for this crucial
``short read alignment'' problem. Our system, called
WHAM, employs hash-based indexing methods and bitwise
operations for sequence alignments. It allows rich
match models and it is significantly faster than the
existing state-of-the-art methods. In addition, its
relative speedup over the existing method is poised to
increase in the future in which read sequence lengths
will increase.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Xie:2012:FAS,
author = "Kexin Xie and Ke Deng and Shuo Shang and Xiaofang Zhou
and Kai Zheng",
title = "Finding Alternative Shortest Paths in Spatial
Networks",
journal = j-TODS,
volume = "37",
number = "4",
pages = "29:1--29:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389248",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Shortest path query is one of the most fundamental
queries in spatial network databases. There exist
algorithms that can process shortest path queries in
real time. However, many complex applications require
more than just the calculation of a single shortest
path. For example, one of the common ways to determine
the importance (or price) of a vertex or an edge in
spatial network is to use Vickrey pricing, which
intuitively values the vertex $v$ (or edge $e$ ) based
on how much harder for travelling from the sources to
the destinations without using $v$ (or $e$ ). In such
cases, the alternative shortest paths without using $v$
(or $e$ ) are required. In this article, we propose
using a precomputation based approach for both single
pair alternative shortest path and all pairs shortest
paths processing. To compute the alternative shortest
path between a source and a destination efficiently, a
na{\"\i}ive way is to precompute and store all
alternative shortest paths between every pair of
vertices avoiding every possible vertex (or edge),
which requires $ O(n^4) $ space. Currently, the state
of the art approach for reducing the storage cost is to
choose a subset of the vertices as center points, and
only store the single-source alternative shortest paths
from those center points. Such approach has the space
complexity of $ O(n^2 \log n) $. We propose a storage
scheme termed iSPQF, which utilizes shortest path
quadtrees by observing the relationships between each
avoiding vertex and its corresponding alternative
shortest paths. We have reduced the space complexity
from the na{\"\i}ive $ O(n^4) $ (or the state of the
art $ O(n^4 \log n) $) to $ O(\min (\gamma, L) n^{1.5})
$ with comparable query performance of $ O(K) $, where
$K$ is the number of vertices in the returned paths,
$L$ is the diameter of the spatial network, and $
\gamma $ is a value that depends on the structure of
the spatial network, which is empirically estimated to
be 40 for real road networks. Experiments on real road
networks have shown that the space cost of the proposed
iSPQF is scalable, and both the algorithms based on
iSPQF are efficient.",
acknowledgement = ack-nhfb,
articleno = "29",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Amsterdamer:2012:PM,
author = "Yael Amsterdamer and Daniel Deutch and Tova Milo and
Val Tannen",
title = "On Provenance Minimization",
journal = j-TODS,
volume = "37",
number = "4",
pages = "30:1--30:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389249",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Provenance information has been proved to be very
effective in capturing the computational process
performed by queries, and has been used extensively as
the input to many advanced data management tools (e.g.,
view maintenance, trust assessment, or query answering
in probabilistic databases). We observe here that while
different (set-)equivalent queries may admit different
provenance expressions when evaluated on the same
database, there is always some part of these
expressions that is common to all. We refer to this
part as the core provenance. In addition to being
informative, the core provenance is also useful as a
compact input to the aforementioned data management
tools. We formally define the notion of core
provenance. We study algorithms that, given a query,
compute an equivalent (called p-minimal) query that for
every input database, the provenance of every result
tuple is the core provenance. We study such algorithms
for queries of varying expressive power (namely
conjunctive queries with disequalities and unions
thereof). Finally, we observe that, in general, one
would not want to require database systems to execute a
specific p-minimal query, but instead to be able to
find, possibly off-line, the core provenance of a given
tuple in the output (computed by an arbitrary
equivalent query), without reevaluating the query. We
provide algorithms for such direct computation of the
core provenance.",
acknowledgement = ack-nhfb,
articleno = "30",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Barcelo:2012:ELP,
author = "Pablo Barcel{\'o} and Leonid Libkin and Anthony W. Lin
and Peter T. Wood",
title = "Expressive Languages for Path Queries over
Graph-Structured Data",
journal = j-TODS,
volume = "37",
number = "4",
pages = "31:1--31:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389250",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "For many problems arising in the setting of graph
querying (such as finding semantic associations in RDF
graphs, exact and approximate pattern matching,
sequence alignment, etc.), the power of standard
languages such as the widely studied conjunctive
regular path queries (CRPQs) is insufficient in at
least two ways. First, they cannot output paths and
second, more crucially, they cannot express
relationships among paths. We thus propose a class of
extended CRPQs, called ECRPQs, which add regular
relations on tuples of paths, and allow path variables
in the heads of queries. We provide several examples of
their usefulness in querying graph structured data, and
study their properties. We analyze query evaluation and
representation of tuples of paths in the output by
means of automata. We present a detailed analysis of
data and combined complexity of queries, and consider
restrictions that lower the complexity of ECRPQs to
that of relational conjunctive queries. We study the
containment problem, and look at further extensions
with first-order features, and with nonregular
relations that add arithmetic constraints on the
lengths of paths and numbers of occurrences of
labels.",
acknowledgement = ack-nhfb,
articleno = "31",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cong:2012:PED,
author = "Gao Cong and Wenfei Fan and Anastasios Kementsietsidis
and Jianzhong Li and Xianmin Liu",
title = "Partial Evaluation for Distributed {XPath} Query
Processing and Beyond",
journal = j-TODS,
volume = "37",
number = "4",
pages = "32:1--32:??",
month = dec,
year = "2012",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2389241.2389251",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Dec 20 19:03:29 MST 2012",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article proposes algorithms for evaluating XPath
queries over an XML tree that is partitioned
horizontally and vertically, and is distributed across
a number of sites. The key idea is based on partial
evaluation: it is to send the whole query to each site
that partially evaluates the query, in parallel, and
sends the results as compact (Boolean) functions to a
coordinator that combines these to obtain the result.
This approach possesses the following performance
guarantees. First, each site is visited at most twice
for data-selecting XPath queries, and only once for
Boolean XPath queries. Second, the network traffic is
determined by the answer to the query, rather than the
size of the tree. Third, the total computation is
comparable to that of centralized algorithms on the
tree stored in a single site, regardless of how the
tree is fragmented and distributed. We also present a
MapReduce algorithm for evaluating Boolean XPath
queries, based on partial evaluation. In addition, we
provide algorithms to evaluate XPath queries on very
large XML trees, in a centralized setting. We show both
analytically and empirically that our techniques are
scalable with large trees and complex XPath queries.
These results, we believe, illustrate the usefulness
and potential of partial evaluation in distributed
systems as well as centralized XML stores for
evaluating XPath queries and beyond.",
acknowledgement = ack-nhfb,
articleno = "32",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papavasileiou:2013:HLC,
author = "Vicky Papavasileiou and Giorgos Flouris and Irini
Fundulaki and Dimitris Kotzinos and Vassilis
Christophides",
title = "High-level change detection in {RDF(S) KBs}",
journal = j-TODS,
volume = "38",
number = "1",
pages = "1:1--1:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "With the increasing use of Web 2.0 to create,
disseminate, and consume large volumes of data, more
and more information is published and becomes available
for potential data consumers, that is,
applications/services, individual users and
communities, outside their production site. The most
representative example of this trend is Linked Open
Data (LOD), a set of interlinked data and knowledge
bases. The main challenge in this context is data
governance within loosely coordinated organizations
that are publishing added-value interlinked data on the
Web, bringing together issues related to data
management and data quality, in order to support the
full lifecycle of data production, consumption, and
management. In this article, we are interested in
curation issues for RDF(S) data, which is the default
data model for LOD. In particular, we are addressing
change management for RDF(S) data maintained by large
communities (scientists, librarians, etc.) which act as
curators to ensure high quality of data. Such curated
Knowledge Bases (KBs) are constantly evolving for
various reasons, such as the inclusion of new
experimental evidence or observations, or the
correction of erroneous conceptualizations. Managing
such changes poses several research problems, including
the problem of detecting the changes (delta) between
versions of the same KB developed and maintained by
different groups of curators, a crucial task for
assisting them in understanding the involved changes.
This becomes all the more important as curated KBs are
interconnected (through copying or referencing) and
thus changes need to be propagated from one KB to
another either within or across communities. This
article addresses this problem by proposing a change
language which allows the formulation of concise and
intuitive deltas. The language is expressive enough to
describe unambiguously any possible change encountered
in curated KBs expressed in RDF(S), and can be
efficiently and deterministically detected in an
automated way. Moreover, we devise a change detection
algorithm which is sound and complete with respect to
the aforementioned language, and study appropriate
semantics for executing the deltas expressed in our
language in order to move backwards and forwards in a
multiversion repository, using only the corresponding
deltas. Finally, we evaluate through experiments the
effectiveness and efficiency of our algorithms using
real ontologies from the cultural, bioinformatics, and
entertainment domains.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jaiswal:2013:SME,
author = "Anuj Jaiswal and David J. Miller and Prasenjit Mitra",
title = "Schema matching and embedded value mapping for
databases with opaque column names and mixed continuous
and discrete-valued data fields",
journal = j-TODS,
volume = "38",
number = "1",
pages = "2:1--2:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Schema matching and value mapping across two
information sources, such as databases, are critical
information aggregation tasks. Before data can be
integrated from multiple tables, the columns and values
within the tables must be matched. The complexities of
both these problems grow quickly with the number of
attributes to be matched and due to multiple semantics
of data values. Traditional research has mostly tackled
schema matching and value mapping independently, and
for categorical (discrete-valued) attributes. We
propose novel methods that leverage value mappings to
enhance schema matching in the presence of opaque
column names for schemas consisting of both continuous
and discrete-valued attributes. An additional source of
complexity is that a discrete-valued attribute in one
schema could in fact be a quantized, encoded version of
a continuous-valued attribute in the other schema. In
our approach, which can tackle both ``onto'' and
bijective schema matching, the fitness objective for
matching a pair of attributes from two schemas exploits
the statistical distribution over values within the two
attributes. Suitable fitness objectives are based on
Euclidean-distance and the data log-likelihood, both of
which are applied in our experimental study. A
heuristic local descent optimization strategy that uses
two-opt switching to optimize attribute matches, while
simultaneously embedding value mappings, is applied for
our matching methods. Our experiments show that the
proposed techniques matched mixed continuous and
discrete-valued attribute schemas with high accuracy
and, thus, should be a useful addition to a framework
of (semi) automated tools for data alignment.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Grust:2013:OSQ,
author = "Torsten Grust and Jan Rittinger",
title = "Observing {SQL} queries in their natural habitat",
journal = j-TODS,
volume = "38",
number = "1",
pages = "3:1--3:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We describe Habitat, a declarative observational
debugger for SQL. Habitat facilitates true
language-level (not: plan-level) debugging of, probably
flawed, SQL queries that yield unexpected results.
Users mark SQL subexpressions of arbitrary size and
then observe whether these evaluate as expected.
Habitat understands query nesting and free row
variables in correlated subqueries, and generally aims
to not constrain users while suspect subexpressions are
marked for observation. From the marked SQL text,
Habitat's algebraic compiler derives a new query whose
result represents the values of the desired
observations. These observations are generated by the
target SQL database host itself and are derived from
the original data: Habitat does not require prior data
extraction or extra debugging middleware. Experiments
with TPC-H database instances indicate that
observations impose a runtime overhead sufficiently low
to allow for interactive debugging sessions.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Benzaken:2013:OXQ,
author = "V{\'e}ronique Benzaken and Giuseppe Castagna and Dario
Colazzo and Kim Nguy{\'{\^e}}n",
title = "Optimizing {XML} querying using type-based document
projection",
journal = j-TODS,
volume = "38",
number = "1",
pages = "4:1--4:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "XML data projection (or pruning) is a natural
optimization for main memory query engines: given a
query Q over a document D, the subtrees of D that are
not necessary to evaluate Q are pruned, thus producing
a smaller document D'; the query Q is then executed on
D', hence avoiding to allocate and process nodes that
will never be reached by Q. In this article, we propose
a new approach, based on types, that greatly improves
current solutions. Besides providing comparable or
greater precision and far lesser pruning overhead, our
solution-unlike current approaches-takes into account
backward axes, predicates, and can be applied to
multiple queries rather than just to single ones. A
side contribution is a new type system for XPath able
to handle backward axes. The soundness of our approach
is formally proved. Furthermore, we prove that the
approach is also complete (i.e., yields the best
possible type-driven pruning) for a relevant class of
queries and Schemas. We further validate our approach
using the XMark and XPathMark benchmarks and show that
pruning not only improves the main memory query
engine's performances (as expected) but also those of
state of the art native XML databases.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Das:2013:EES,
author = "Sudipto Das and Divyakant Agrawal and Amr {El
Abbadi}",
title = "{ElasTraS}: an elastic, scalable, and self-managing
transactional database for the cloud",
journal = j-TODS,
volume = "38",
number = "1",
pages = "5:1--5:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A database management system (DBMS) serving a cloud
platform must handle large numbers of application
databases (or tenants) that are characterized by
diverse schemas, varying footprints, and unpredictable
load patterns. Scaling out using clusters of commodity
servers and sharing resources among tenants (i.e.,
multitenancy) are important features of such systems.
Moreover, when deployed on a pay-per-use
infrastructure, minimizing the system's operating cost
while ensuring good performance is also an important
goal. Traditional DBMSs were not designed for such
scenarios and hence do not possess the mentioned
features critical for DBMSs in the cloud. We present
ElasTraS, which combines three design principles to
build an elastically-scalable multitenant DBMS for
transaction processing workloads. These design
principles are gleaned from a careful analysis of the
years of research in building scalable key-value stores
and decades of research in high performance transaction
processing systems. ElasTraS scales to thousands of
tenants, effectively consolidates tenants with small
footprints while scaling-out large tenants across
multiple servers in a cluster. ElasTraS also supports
low-latency multistep ACID transactions, is
fault-tolerant, self-managing, and highly available to
support mission critical applications. ElasTraS
leverages Albatross, a low overhead on-demand live
database migration technique, for elastic load
balancing by adding more servers during high load and
consolidating to fewer servers during usage troughs.
This elastic scaling minimizes the operating cost and
ensures good performance even in the presence of
unpredictable changes to the workload. We elucidate the
design principles, explain the architecture, describe a
prototype implementation, present the detailed design
and implementation of Albatross, and experimentally
evaluate the implementation using a variety of
transaction processing workloads. On a cluster of 20
commodity servers, our prototype serves thousands of
tenants and serves more than 1 billion transactions per
day while migrating tenant databases with minimal
overhead to allow lightweight elastic scaling. Using a
cluster of 30 commodity servers, ElasTraS can scale-out
a terabyte TPC-C database serving an aggregate
throughput of approximately one quarter of a million
TPC-C transactions per minute.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Franceschet:2013:GTA,
author = "Massimo Franceschet and Donatella Gubiani and Angelo
Montanari and Carla Piazza",
title = "A graph-theoretic approach to map conceptual designs
to {XML} schemas",
journal = j-TODS,
volume = "38",
number = "1",
pages = "6:1--6:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We propose a mapping from a database conceptual design
to a schema for XML that produces highly connected and
nested XML structures. We first introduce two
alternative definitions of the mapping, one modeling
entities as global XML elements and expressing
relationships among them in terms of keys and key
references (flat design), the other one encoding
relationships by properly including the elements for
some entities into the elements for other entities
(nest design). Then we provide a benchmark evaluation
of the two solutions showing that the nest approach,
compared to the flat one, leads to improvements in both
query and validation performances. This motivates us to
systematically investigate the best way to nest XML
structures. We identify two different nesting
solutions: a maximum depth nesting, that keeps low the
number of costly join operations that are necessary to
reconstruct information at query time using the mapped
schema, and a maximum density nesting, that minimizes
the number of schema constraints used in the mapping of
the conceptual schema, thus reducing the validation
overhead. On the one hand, the problem of finding a
maximum depth nesting turns out to be NP-complete and,
moreover, it admits no constant ratio approximation
algorithm. On the other hand, we devise a
graph-theoretic algorithm, NiduX, that solves the
maximum density problem in linear time. Interestingly,
NiduX finds the optimal solution for the harder maximum
depth problem whenever the conceptual design graph is
either acyclic or complete. In randomly generated
intermediate cases of the graph topology, we
experimentally show that NiduX finds a good
approximation of the optimal solution.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wu:2013:MSK,
author = "Dingming Wu and Man Lung Yiu and Christian S. Jensen",
title = "Moving spatial keyword queries: Formulation, methods,
and analysis",
journal = j-TODS,
volume = "38",
number = "1",
pages = "7:1--7:??",
month = apr,
year = "2013",
CODEN = "ATDSD3",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Apr 23 18:06:18 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Web users and content are increasingly being
geo-positioned. This development gives prominence to
spatial keyword queries, which involve both the
locations and textual descriptions of content. We study
the efficient processing of continuously moving top- k
spatial keyword (M k SK) queries over spatial text
data. State-of-the-art solutions for moving queries
employ safe zones that guarantee the validity of
reported results as long as the user remains within the
safe zone associated with a result. However, existing
safe-zone methods focus solely on spatial locations and
ignore text relevancy. We propose two algorithms for
computing safe zones that guarantee correct results at
any time and that aim to optimize the server-side
computation as well as the communication between the
server and the client. We exploit tight and
conservative approximations of safe zones and
aggressive computational space pruning. We present
techniques that aim to compute the next safe zone
efficiently, and we present two types of conservative
safe zones that aim to reduce the communication cost.
Empirical studies with real data suggest that the
proposals are efficient. To understand the
effectiveness of the proposed safe zones, we study
analytically the expected area of a safe zone, which
indicates on average for how long a safe zone remains
valid, and we study the expected number of influence
objects needed to define a safe zone, which gives an
estimate of the average communication cost. The
analytical modeling is validated through empirical
studies.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sadoghi:2013:AOB,
author = "Mohammad Sadoghi and Hans-Arno Jacobsen",
title = "Analysis and optimization for {Boolean} expression
indexing",
journal = j-TODS,
volume = "38",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487260",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "BE-Tree is a novel dynamic data structure designed to
efficiently index Boolean expressions over a
high-dimensional discrete space. BE Tree-copes with
both high-dimensionality and expressiveness of Boolean
expressions by introducing an effective two-phase
space-cutting technique that specifically utilizes the
discrete and finite domain properties of the space.
Furthermore, BE-Tree employs self-adjustment policies
to dynamically adapt the tree as the workload changes.
Moreover, in BE-Tree, we develop two novel
cache-conscious predicate evaluation techniques,
namely, lazy and bitmap evaluations, that also exploit
the underlying discrete and finite space to
substantially reduce BE-Tree's matching time by up to
75\% BE-Tree is a general index structure for matching
Boolean expression which has a wide range of
applications including (complex) event processing,
publish/subscribe matching, emerging applications in
cospaces, profile matching for targeted web
advertising, and approximate string matching. Finally,
the superiority of BE-Tree is proven through a
comprehensive evaluation with state-of-the-art index
structures designed for matching Boolean expressions.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2013:PBM,
author = "Guoliang Li and Dong Deng and Jianhua Feng",
title = "A partition-based method for string similarity joins
with edit-distance constraints",
journal = j-TODS,
volume = "38",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487261",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "As an essential operation in data cleaning, the
similarity join has attracted considerable attention
from the database community. In this article, we study
string similarity joins with edit-distance constraints,
which find similar string pairs from two large sets of
strings whose edit distance is within a given
threshold. Existing algorithms are efficient either for
short strings or for long strings, and there is no
algorithm that can efficiently and adaptively support
both short strings and long strings. To address this
problem, we propose a new filter, called the segment
filter. We partition a string into a set of segments
and use the segments as a filter to find similar string
pairs. We first create inverted indices for the
segments. Then for each string, we select some of its
substrings, identify the selected substrings from the
inverted indices, and take strings on the inverted
lists of the found substrings as candidates of this
string. Finally, we verify the candidates to generate
the final answer. We devise efficient techniques to
select substrings and prove that our method can
minimize the number of selected substrings. We develop
novel pruning techniques to efficiently verify the
candidates. We also extend our techniques to support
normalized edit distance. Experimental results show
that our algorithms are efficient for both short
strings and long strings, and outperform
state-of-the-art methods on real-world datasets.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Catallo:2013:TKD,
author = "Ilio Catallo and Eleonora Ciceri and Piero Fraternali
and Davide Martinenghi and Marco Tagliasacchi",
title = "Top-$k$ diversity queries over bounded regions",
journal = j-TODS,
volume = "38",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487262",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Top-k diversity queries over objects embedded in a
low-dimensional vector space aim to retrieve the best k
objects that are both relevant to given user's criteria
and well distributed over a designated region. An
interesting case is provided by spatial Web objects,
which are produced in great quantity by location-based
services that let users attach content to places and
are found also in domains like trip planning, news
analysis, and real estate. In this article we present a
technique for addressing such queries that, unlike
existing methods for diversified top- k queries, does
not require accessing and scanning all relevant objects
in order to find the best k results. Our Space
Partitioning and Probing (SPP) algorithm works by
progressively exploring the vector space, while keeping
track of the already seen objects and of their
relevance and position. The goal is to provide a good
quality result set in terms of both relevance and
diversity. We assess quality by using as a baseline the
result set computed by MMR, one of the most popular
diversification algorithms, while minimizing the number
of accessed objects. In order to do so, SPP exploits
score-based and distance-based access methods, which
are available, for instance, in most geo-referenced Web
data sources. Experiments with both synthetic and real
data show that SPP produces results that are relevant
and spatially well distributed, while significantly
reducing the number of accessed objects and incurring a
very low computational overhead.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fazzinga:2013:RDC,
author = "Bettina Fazzinga and Sergio Flesca and Filippo Furfaro
and Elio Masciari",
title = "{RFID}-data compression for supporting aggregate
queries",
journal = j-TODS,
volume = "38",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487263",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "RFID-based systems for object tracking and supply
chain management have been emerging since the RFID
technology proved effective in monitoring movements of
objects. The monitoring activity typically results in
huge numbers of readings, thus making the problem of
efficiently retrieving aggregate information from the
collected data a challenging issue. In fact, tackling
this problem is of crucial importance, as fast answers
to aggregate queries are often mandatory to support the
decision making process. In this regard, a compression
technique for RFID data is proposed, and used as the
core of a system supporting the efficient estimation of
aggregate queries. Specifically, this technique aims at
constructing a lossy synopsis of the data over which
aggregate queries can be estimated, without accessing
the original data. Owing to the lossy nature of the
compression, query estimates are approximate, and are
returned along with intervals that are guaranteed to
contain the exact query answers. The effectiveness of
the proposed approach has been experimentally
validated, showing a remarkable trade-off between the
efficiency and the accuracy of the query estimation.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pavlou:2013:GDF,
author = "Kyriacos E. Pavlou and Richard T. Snodgrass",
title = "Generalizing database forensics",
journal = j-TODS,
volume = "38",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487264",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article we present refinements on previously
proposed approaches to forensic analysis of database
tampering. We significantly generalize the basic
structure of these algorithms to admit new
characterizations of the ``where'' axis of the
corruption diagram. Specifically, we introduce
page-based partitioning as well as attribute-based
partitioning along with their associated corruption
diagrams. We compare the structure of all the forensic
analysis algorithms and discuss the various design
choices available with respect to forensic analysis. We
characterize the forensic cost of the newly introduced
algorithms, compare their forensic cost, and give our
recommendations. We then introduce a comprehensive
taxonomy of the types of possible corruption events,
along with an associated forensic analysis protocol
that consolidates all extant forensic algorithms and
the corresponding type(s) of corruption events they
detect. The result is a generalization of these
algorithms and an overarching characterization of the
process of database forensic analysis, thus providing a
context within the overall operation of a DBMS for all
existing forensic analysis algorithms.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cheney:2013:RFN,
author = "James Cheney",
title = "Revisiting ``forward node-selecting queries over
trees''",
journal = j-TODS,
volume = "38",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2487259.2487265",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 1 18:44:25 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In ``Forward Node-Selecting Queries over Trees,''
Olteanu [2007] gives three rewriting systems for
eliminating reverse XPath axis steps from
node-selecting queries over trees, together with
arguments for their correctness and termination for a
large class of input graphs, including cyclic ones.
These proofs are valid for tree or acyclic formulas,
but two of the rewrite systems ( TRS$_2$ and TRS$_3$ )
do not terminate on cyclic graphs; that is, there are
infinite rewrite sequences that never yield a normal
form. We investigate the reasons why the termination
arguments do not work for general cyclic formulas, and
develop alternative algorithms that can be used
instead. We prove that TRS$_2$ is weakly normalizing,
while TRS$_3$ is not weakly normalizing, but it can be
extended to a weakly normalizing system TRS$_3^\ocirc
$. The algorithms and proof techniques illustrate
unforeseen subtleties in the handling of cyclic
queries.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bonifati:2013:AIM,
author = "Angela Bonifati and Martin Goodfellow and Ioana
Manolescu and Domenica Sileo",
title = "Algebraic incremental maintenance of {XML} views",
journal = j-TODS,
volume = "38",
number = "3",
pages = "14:1--14:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2508020.2508021",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Materialized views can bring important performance
benefits when querying XML documents. In the presence
of XML document changes, materialized views need to be
updated to faithfully reflect the changed document. In
this work, we present an algebraic approach for
propagating source updates to XML materialized views
expressed in a powerful XML tree pattern formalism. Our
approach differs from the state-of-the-art in the area
in two important ways. First, it relies on
set-oriented, algebraic operations, to be contrasted
with node-based previous approaches. Second, it
exploits state-of-the-art features of XML stores and
XML query evaluation engines, notably XML structural
identifiers and associated structural join algorithms.
We present algorithms for determining how updates
should be propagated to views, and highlight the
benefits of our approach over existing algorithms
through a series of experiments.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Colazzo:2013:ALI,
author = "Dario Colazzo and Giorgio Ghelli and Luca Pardini and
Carlo Sartiani",
title = "Almost-linear inclusion for {XML} regular expression
types",
journal = j-TODS,
volume = "38",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2508020.2508022",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Type inclusion is a fundamental operation in every
type-checking compiler, but it is quite expensive for
XML manipulation languages. A polynomial inclusion
checking algorithm for an expressive family of XML type
languages is known, but it runs in quadratic time both
in the best and in the worst cases. We present here an
algorithm that has a linear-time backbone, and resorts
to the quadratic approach for some specific parts of
the compared types. Our experiments show that the new
algorithm is much faster than the quadratic one, and
that it typically runs in linear time, hence it can be
used as a building block for a practical type-checking
compiler.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Qin:2013:ASS,
author = "Jianbin Qin and Wei Wang and Chuan Xiao and Yifei Lu
and Xuemin Lin and Haixun Wang",
title = "Asymmetric signature schemes for efficient exact edit
similarity query processing",
journal = j-TODS,
volume = "38",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2508020.2508023",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Given a query string Q, an edit similarity search
finds all strings in a database whose edit distance
with {$Q$} is no more than a given threshold $ \tau $.
Most existing methods answering edit similarity queries
employ schemes to generate string subsequences as
signatures and generate candidates by set overlap
queries on query and data signatures. In this article,
we show that for any such signature scheme, the lower
bound of the minimum number of signatures is $ \tau + 1
$, which is lower than what is achieved by existing
methods. We then propose several asymmetric signature
schemes, that is, extracting different numbers of
signatures for the data and query strings, which
achieve this lower bound. A basic asymmetric scheme is
first established on the basis of matching $q$-chunks
and $q$-grams between two strings. Two efficient query
processing algorithms (IndexGram and IndexChunk) are
developed on top of this scheme. We also propose novel
candidate pruning methods to further improve the
efficiency. We then generalize the basic scheme by
incorporating novel ideas of floating $q$-chunks,
optimal selection of $q$-chunks, and reducing the
number of signatures using global ordering. As a
result, the Super and Turbo families of schemes are
developed together with their corresponding query
processing algorithms. We have conducted a
comprehensive experimental study using the six
asymmetric algorithms and nine previous
state-of-the-art algorithms. The experiment results
clearly showcase the efficiency of our methods and
demonstrate space and time characteristics of our
proposed algorithms.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Levandoski:2013:FEP,
author = "Justin J. Levandoski and Ahmed Eldawy and Mohamed F.
Mokbel and Mohamed E. Khalefa",
title = "Flexible and extensible preference evaluation in
database systems",
journal = j-TODS,
volume = "38",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2493268",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Personalized database systems give users answers
tailored to their personal preferences. While numerous
preference evaluation methods for databases have been
proposed (e.g., skyline, top-k, k-dominance,
k-frequency), the implementation of these methods at
the core of a database system is a double-edged sword.
Core implementation provides efficient query processing
for arbitrary database queries, however, this approach
is not practical since each existing (and future)
preference method requires implementation within the
database engine. To solve this problem, this article
introduces FlexPref, a framework for extensible
preference evaluation in database systems. FlexPref,
implemented in the query processor, aims to support a
wide array of preference evaluation methods in a single
extensible code base. Integration with FlexPref is
simple, involving the registration of only three
functions that capture the essence of the preference
method. Once integrated, the preference method
``lives'' at the core of the database, enabling the
efficient execution of preference queries involving
common database operations. This article also provides
a query optimization framework for FlexPref, as well as
a theoretical framework that defines the properties a
preference method must exhibit to be implemented in
FlexPref. To demonstrate the extensibility of FlexPref,
this article also provides case studies detailing the
implementation of seven state-of-the-art preference
evaluation methods within FlexPref. We also
experimentally study the strengths and weaknesses of an
implementation of FlexPref in PostgreSQL over a range
of single-table and multitable preference queries.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2013:IGP,
author = "Wenfei Fan and Xin Wang and Yinghui Wu",
title = "Incremental graph pattern matching",
journal = j-TODS,
volume = "38",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2489791",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Graph pattern matching is commonly used in a variety
of emerging applications such as social network
analysis. These applications highlight the need for
studying the following two issues. First, graph pattern
matching is traditionally defined in terms of subgraph
isomorphism or graph simulation. These notions,
however, often impose too strong a topological
constraint on graphs to identify meaningful matches.
Second, in practice a graph is typically large, and is
frequently updated with small changes. It is often
prohibitively expensive to recompute matches starting
from scratch via batch algorithms when the graph is
updated. This article studies these two issues. (1) We
propose to define graph pattern matching based on a
notion of bounded simulation, which extends graph
simulation by specifying the connectivity of nodes in a
graph within a predefined number of hops. We show that
bounded simulation is able to find sensible matches
that the traditional matching notions fail to catch. We
also show that matching via bounded simulation is in
cubic time, by giving such an algorithm. (2) We provide
an account of results on incremental graph pattern
matching, for matching defined with graph simulation,
bounded simulation, and subgraph isomorphism. We show
that the incremental matching problem is unbounded,
that is, its cost is not determined alone by the size
of the changes in the input and output, for all these
matching notions. Nonetheless, when matching is defined
in terms of simulation or bounded simulation,
incremental matching is semibounded, that is, its
worst-time complexity is bounded by a polynomial in the
size of the changes in the input, output, and auxiliary
information that is necessarily maintained to reuse
previous computation, and the size of graph patterns.
We also develop incremental matching algorithms for
graph simulation and bounded simulation, by minimizing
unnecessary recomputation. In contrast, matching based
on subgraph isomorphism is neither bounded nor
semibounded. (3) We experimentally verify the
effectiveness and efficiency of these algorithms, and
show that: (a) the revised notion of graph pattern
matching allows us to identify communities commonly
found in real-life networks, and (b) the incremental
algorithms substantially outperform their batch
counterparts in response to small changes. These
suggest a promising framework for real-life graph
pattern matching.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Karvounarakis:2013:CDS,
author = "Grigoris Karvounarakis and Todd J. Green and Zachary
G. Ives and Val Tannen",
title = "Collaborative data sharing via update exchange and
provenance",
journal = j-TODS,
volume = "38",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2500127",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 30 16:33:21 MDT 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Recent work [Ives et al. 2005] proposed a new class of
systems for supporting data sharing among scientific
and other collaborations: this new collaborative data
sharing system connects heterogeneous logical peers
using a network of schema mappings. Each peer has a
locally controlled and edited database instance, but
wants to incorporate related data from other peers as
well. To achieve this, every peer's data and updates
propagate along the mappings to the other peers.
However, this operation, termed update exchange, is
filtered by trust conditions -expressing what data and
sources a peer judges to be authoritative-which may
cause a peer to reject another's updates. In order to
support such filtering, updates carry provenance
information. This article develops methods for
realizing such systems: we build upon techniques from
data integration, data exchange, incremental view
maintenance, and view update to propagate updates along
mappings, both to derived and optionally to source
instances. We incorporate a novel model for tracking
data provenance, such that curators may filter updates
based on trust conditions over this provenance. We
implement our techniques in a layer above an
off-the-shelf RDBMS, and we experimentally demonstrate
the viability of these techniques in the Orchestra
prototype system.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ozsoyoglu:2013:FIP,
author = "Z. Meral {\"O}zsoyoglu",
title = "Foreword to invited papers issue",
journal = j-TODS,
volume = "38",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2539032.2539033",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Mozafari:2013:HPC,
author = "Barzan Mozafari and Kai Zeng and Loris D'antoni and
Carlo Zaniolo",
title = "High-performance complex event processing over
hierarchical data",
journal = j-TODS,
volume = "38",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2536779",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "While Complex Event Processing (CEP) constitutes a
considerable portion of the so-called Big Data
analytics, current CEP systems can only process data
having a simple structure, and are otherwise limited in
their ability to efficiently support complex continuous
queries on structured or semistructured information.
However, XML-like streams represent a very popular form
of data exchange, comprising large portions of social
network and RSS feeds, financial feeds, configuration
files, and similar applications requiring advanced CEP
queries. In this article, we present the XSeq language
and system that support CEP on XML streams, via an
extension of XPath that is both powerful and amenable
to an efficient implementation. Specifically, the XSeq
language extends XPath with natural operators to
express sequential and Kleene-* patterns over XML
streams, while remaining highly amenable to efficient
execution. In fact, XSeq is designed to take full
advantage of the recently proposed Visibly Pushdown
Automata (VPA), where higher expressive power can be
achieved without compromising the computationally
attractive properties of finite state automata. Besides
the efficiency and expressivity benefits, the choice of
VPA as the underlying model also enables XSeq to go
beyond XML streams and be easily applicable to any data
with both sequential and hierarchical structures,
including JSON messages, RNA sequences, and software
traces. Therefore, we illustrate the XSeq's power for
CEP applications through examples from different
domains and provide formal results on its
expressiveness and complexity. Finally, we present
several optimization techniques for XSeq queries. Our
extensive experiments indicate that XSeq brings
outstanding performance to CEP applications: two orders
of magnitude improvement is obtained over the same
queries executed in general-purpose XML engines.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sarma:2013:CTL,
author = "Anish Das Sarma and Hongrae Lee and Hector Gonzalez
and Jayant Madhavan and Alon Halevy",
title = "Consistent thinning of large geographical data for map
visualization",
journal = j-TODS,
volume = "38",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2539032.2539034",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Large-scale map visualization systems play an
increasingly important role in presenting geographic
datasets to end-users. Since these datasets can be
extremely large, a map rendering system often needs to
select a small fraction of the data to visualize them
in a limited space. This article addresses the
fundamental challenge of thinning: determining
appropriate samples of data to be shown on specific
geographical regions and zoom levels. Other than the
sheer scale of the data, the thinning problem is
challenging because of a number of other reasons: (1)
data can consist of complex geographical shapes, (2)
rendering of data needs to satisfy certain constraints,
such as data being preserved across zoom levels and
adjacent regions, and (3) after satisfying the
constraints, an optimal solution needs to be chosen
based on objectives such as maximality, fairness, and
importance of data. This article formally defines and
presents a complete solution to the thinning problem.
First, we express the problem as an integer programming
formulation that efficiently solves thinning for
desired objectives. Second, we present more efficient
solutions for maximality, based on DFS traversal of a
spatial tree. Third, we consider the common special
case of point datasets, and present an even more
efficient randomized algorithm. Fourth, we show that
contiguous regions are tractable for a general version
of maximality for which arbitrary regions are
intractable. Fifth, we examine the structure of our
integer programming formulation and show that for point
datasets, our program is integral. Finally, we have
implemented all techniques from this article in Google
Maps [Google 2005] visualizations of fusion tables
[Gonzalez et al. 2010], and we describe a set of
experiments that demonstrate the trade-offs among the
algorithms.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Teubner:2013:XFB,
author = "Jens Teubner and Louis Woods and Chongling Nie",
title = "{XLynx} --- An {FPGA}-based {XML} filter for hybrid
{XQuery} processing",
journal = j-TODS,
volume = "38",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2536800",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "While offering unique performance and energy-saving
advantages, the use of Field-Programmable Gate Arrays
(FPGAs) for database acceleration has demanded major
concessions from system designers. Either the
programmable chips have been used for very basic
application tasks (such as implementing a rigid class
of selection predicates) or their circuit definition
had to be completely recompiled at runtime-a very
CPU-intensive and time-consuming effort. This work
eliminates the need for such concessions. As part of
our XLynx implementation-an FPGA-based XML filter-we
present skeleton automata, which is a design principle
for data-intensive hardware circuits that offers high
expressiveness and quick reconfiguration at the same
time. Skeleton automata provide a generic
implementation for a class of finite-state automata.
They can be parameterized to any particular automaton
instance in a matter of microseconds or less (as
opposed to minutes or hours for complete
recompilation). We showcase skeleton automata based on
XML projection [Marian and Sim{\'e}on 2003], a
filtering technique that illustrates the feasibility of
our strategy for a real-world and challenging task. By
performing XML projection in hardware and filtering
data in the network, we report on performance
improvements of several factors while remaining
nonintrusive to the back-end XML processor (we evaluate
XLynx using the Saxon engine).",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Losemann:2013:CRE,
author = "Katja Losemann and Wim Martens",
title = "The complexity of regular expressions and property
paths in {SPARQL}",
journal = j-TODS,
volume = "38",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2494529",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The World Wide Web Consortium (W3C) recently
introduced property paths in SPARQL 1.1, a query
language for RDF data. Property paths allow SPARQL
queries to evaluate regular expressions over
graph-structured data. However, they differ from
standard regular expressions in several notable
aspects. For example, they have a limited form of
negation, they have numerical occurrence indicators as
syntactic sugar, and their semantics on graphs is
defined in a nonstandard manner. We formalize the W3C
semantics of property paths and investigate various
query evaluation problems on graphs. More specifically,
let $x$ and $y$ be two nodes in an edge-labeled graph
and $r$ be an expression. We study the complexities of:
(1) deciding whether there exists a path from $x$ to
$y$ that matches $r$ and (2) counting how many paths
from $x$ to $y$ match $r$. Our main results show that,
compared to an alternative semantics of regular
expressions on graphs, the complexity of (1) and (2)
under W3C semantics is significantly higher. Whereas
the alternative semantics remains in polynomial time
for large fragments of expressions, the W3C semantics
makes problems (1) and (2) intractable almost
immediately. As a side-result, we prove that the
membership problem for regular expressions with
numerical occurrence indicators and negation is in
polynomial time.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Letelier:2013:SAO,
author = "Andr{\'e}s Letelier and Jorge P{\'e}rez and Reinhard
Pichler and Sebastian Skritek",
title = "Static analysis and optimization of {Semantic Web}
queries",
journal = j-TODS,
volume = "38",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2500130",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Static analysis is a fundamental task in query
optimization. In this article we study static analysis
and optimization techniques for SPARQL, which is the
standard language for querying Semantic Web data. Of
particular interest for us is the optionality feature
in SPARQL. It is crucial in Semantic Web data
management, where data sources are inherently
incomplete and the user is usually interested in
partial answers to queries. This feature is one of the
most complicated constructors in SPARQL and also the
one that makes this language depart from classical
query languages such as relational conjunctive queries.
We focus on the class of well-designed SPARQL queries,
which has been proposed in the literature as a fragment
of the language with good properties regarding query
evaluation. We first propose a tree representation for
SPARQL queries, called pattern trees, which captures
the class of well-designed SPARQL graph patterns. Among
other results, we propose several rules that can be
used to transform pattern trees into a simple normal
form, and study equivalence and containment. We also
study the evaluation and enumeration problems for this
class of queries.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Agarwal:2013:MS,
author = "Pankaj K. Agarwal and Graham Cormode and Zengfeng
Huang and Jeff M. Phillips and Zhewei Wei and Ke Yi",
title = "Mergeable summaries",
journal = j-TODS,
volume = "38",
number = "4",
pages = "26:1--26:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2500128",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the mergeability of data summaries.
Informally speaking, mergeability requires that, given
two summaries on two datasets, there is a way to merge
the two summaries into a single summary on the two
datasets combined together, while preserving the error
and size guarantees. This property means that the
summaries can be merged in a way akin to other
algebraic operators such as sum and max, which is
especially useful for computing summaries on massive
distributed data. Several data summaries are trivially
mergeable by construction, most notably all the
sketches that are linear functions of the datasets. But
some other fundamental ones, like those for heavy
hitters and quantiles, are not (known to be) mergeable.
In this article, we demonstrate that these summaries
are indeed mergeable or can be made mergeable after
appropriate modifications. Specifically, we show that
for $ \epsilon $-approximate heavy hitters, there is a
deterministic mergeable summary of size $ O (1 /
\epsilon) $; for $ \epsilon $-approximate quantiles,
there is a deterministic summary of size $ O((1 /
\epsilon) \log (\epsilon n)) $ that has a restricted
form of mergeability, and a randomized one of size $
O((1 / \epsilon) \log^{3 / 2} (1 / \epsilon)) $ with
full mergeability. We also extend our results to
geometric summaries such as \epsilon -approximations
which permit approximate multidimensional range
counting queries. While most of the results in this
article are theoretical in nature, some of the
algorithms are actually very simple and even perform
better than the previously best known algorithms, which
we demonstrate through experiments in a simulated
sensor network. We also achieve two results of
independent interest: (1) we provide the best known
randomized streaming bound for $ \epsilon $-approximate
quantiles that depends only on $ \epsilon $, of size $
O((1 / \epsilon) \log^{3 / 2} (1 / \epsilon)) $, and
(2) we demonstrate that the MG and the SpaceSaving
summaries for heavy hitters are isomorphic.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Konrad:2013:VXD,
author = "Christian Konrad and Fr{\'e}d{\'e}ric Magniez",
title = "Validating {XML} documents in the streaming model with
external memory",
journal = j-TODS,
volume = "38",
number = "4",
pages = "27:1--27:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2504590",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problem of validating XML documents of
size N against general DTDs in the context of streaming
algorithms. The starting point of this work is a
well-known space lower bound. There are XML documents
and DTDs for which p -pass streaming algorithms require
$ \Omega (N / p) $ space. We show that when allowing
access to external memory, there is a deterministic
streaming algorithm that solves this problem with
memory space $ O(\log^2 N) $, a constant number of
auxiliary read/write streams, and $ O(\log N) $ total
number of passes on the XML document and auxiliary
streams. An important intermediate step of this
algorithm is the computation of the
First-Child-Next-Sibling (FCNS) encoding of the initial
XML document in a streaming fashion. We study this
problem independently, and we also provide
memory-efficient streaming algorithms for decoding an
XML document given in its FCNS encoding. Furthermore,
validating XML documents encoding binary trees against
any DTD in the usual streaming model without external
memory can be done with sublinear memory. There is a
one-pass algorithm using $ O(\sqrt N \log N) $ space,
and a bidirectional two-pass algorithm using $ O(\log^2
N) $ space which perform this task.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cate:2013:LSM,
author = "Balder {Ten Cate} and V{\'\i}ctor Dalmau and Phokion
G. Kolaitis",
title = "Learning schema mappings",
journal = j-TODS,
volume = "38",
number = "4",
pages = "28:1--28:??",
month = nov,
year = "2013",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2539032.2539035",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Dec 9 11:35:10 MST 2013",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A schema mapping is a high-level specification of the
relationship between a source schema and a target
schema. Recently, a line of research has emerged that
aims at deriving schema mappings automatically or
semi-automatically with the help of data examples, that
is, pairs consisting of a source instance and a target
instance that depict, in some precise sense, the
intended behavior of the schema mapping. Several
different uses of data examples for deriving, refining,
or illustrating a schema mapping have already been
proposed and studied. In this article, we use the lens
of computational learning theory to systematically
investigate the problem of obtaining algorithmically a
schema mapping from data examples. Our aim is to
leverage the rich body of work on learning theory in
order to develop a framework for exploring the power
and the limitations of the various algorithmic methods
for obtaining schema mappings from data examples. We
focus on GAV schema mappings, that is, schema mappings
specified by GAV (Global-As-View) constraints. GAV
constraints are the most basic and the most widely
supported language for specifying schema mappings. We
present an efficient algorithm for learning GAV schema
mappings using Angluin's model of exact learning with
membership and equivalence queries. This is optimal,
since we show that neither membership queries nor
equivalence queries suffice, unless the source schema
consists of unary relations only. We also obtain
results concerning the learnability of schema mappings
in the context of Valiant's well-known PAC
(Probably-Approximately-Correct) learning model, and
concerning the learnability of restricted classes of
GAV schema mappings. Finally, as a byproduct of our
work, we show that there is no efficient algorithm for
approximating the shortest GAV schema mapping fitting a
given set of examples, unless the source schema
consists of unary relations only.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kostylev:2014:CAS,
author = "Egor V. Kostylev and Juan L. Reutter and Andr{\'a}s Z.
Salamon",
title = "Classification of annotation semirings over
containment of conjunctive queries",
journal = j-TODS,
volume = "39",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2556524",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problem of query containment of
conjunctive queries over annotated databases.
Annotations are typically attached to tuples and
represent metadata, such as probability, multiplicity,
comments, or provenance. It is usually assumed that
annotations are drawn from a commutative semiring. Such
databases pose new challenges in query optimization,
since many related fundamental tasks, such as query
containment, have to be reconsidered in the presence of
propagation of annotations. We axiomatize several
classes of semirings for each of which containment of
conjunctive queries is equivalent to existence of a
particular type of homomorphism. For each of these
types, we also specify all semirings for which
existence of a corresponding homomorphism is a
sufficient (or necessary) condition for the
containment. We develop new decision procedures for
containment for some semirings which are not in any of
these classes. This generalizes and systematizes
previous approaches.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yi:2014:ISQ,
author = "Ke Yi and Lu Wang and Zhewei Wei",
title = "Indexing for summary queries: Theory and practice",
journal = j-TODS,
volume = "39",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2508702",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Database queries can be broadly classified into two
categories: reporting queries and aggregation queries.
The former retrieves a collection of records from the
database that match the query's conditions, while the
latter returns an aggregate, such as count, sum,
average, or max (min), of a particular attribute of
these records. Aggregation queries are especially
useful in business intelligence and data analysis
applications where users are interested not in the
actual records, but some statistics of them. They can
also be executed much more efficiently than reporting
queries, by embedding properly precomputed aggregates
into an index. However, reporting and aggregation
queries provide only two extremes for exploring the
data. Data analysts often need more insight into the
data distribution than what those simple aggregates
provide, and yet certainly do not want the sheer volume
of data returned by reporting queries. In this article,
we design indexing techniques that allow for extracting
a statistical summary of all the records in the query.
The summaries we support include frequent items,
quantiles, and various sketches, all of which are of
central importance in massive data analysis. Our
indexes require linear space and extract a summary with
the optimal or near-optimal query cost. We illustrate
the efficiency and usefulness of our designs through
extensive experiments and a system demonstration.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kifer:2014:PFM,
author = "Daniel Kifer and Ashwin Machanavajjhala",
title = "{Pufferfish}: a framework for mathematical privacy
definitions",
journal = j-TODS,
volume = "39",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2514689",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/cryptography2010.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we introduce a new and general
privacy framework called Pufferfish. The Pufferfish
framework can be used to create new privacy definitions
that are customized to the needs of a given
application. The goal of Pufferfish is to allow experts
in an application domain, who frequently do not have
expertise in privacy, to develop rigorous privacy
definitions for their data sharing needs. In addition
to this, the Pufferfish framework can also be used to
study existing privacy definitions. We illustrate the
benefits with several applications of this privacy
framework: we use it to analyze differential privacy
and formalize a connection to attackers who believe
that the data records are independent; we use it to
create a privacy definition called hedging privacy,
which can be used to rule out attackers whose prior
beliefs are inconsistent with the data; we use the
framework to define and study the notion of composition
in a broader context than before; we show how to apply
the framework to protect unbounded continuous
attributes and aggregate information; and we show how
to use the framework to rigorously account for prior
data releases.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ma:2014:SSC,
author = "Shuai Ma and Yang Cao and Wenfei Fan and Jinpeng Huai
and Tianyu Wo",
title = "Strong simulation: Capturing topology in graph pattern
matching",
journal = j-TODS,
volume = "39",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2528937",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Graph pattern matching is finding all matches in a
data graph for a given pattern graph and is often
defined in terms of subgraph isomorphism, an
NP-complete problem. To lower its complexity, various
extensions of graph simulation have been considered
instead. These extensions allow graph pattern matching
to be conducted in cubic time. However, they fall short
of capturing the topology of data graphs, that is,
graphs may have a structure drastically different from
pattern graphs they match, and the matches found are
often too large to understand and analyze. To rectify
these problems, this article proposes a notion of
strong simulation, a revision of graph simulation for
graph pattern matching. (1) We identify a set of
criteria for preserving the topology of graphs matched.
We show that strong simulation preserves the topology
of data graphs and finds a bounded number of matches.
(2) We show that strong simulation retains the same
complexity as earlier extensions of graph simulation by
providing a cubic-time algorithm for computing strong
simulation. (3) We present the locality property of
strong simulation which allows us to develop an
effective distributed algorithm to conduct graph
pattern matching on distributed graphs. (4) We
experimentally verify the effectiveness and efficiency
of these algorithms using both real-life and synthetic
data.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gatterbauer:2014:OBP,
author = "Wolfgang Gatterbauer and Dan Suciu",
title = "Oblivious bounds on the probability of {Boolean}
functions",
journal = j-TODS,
volume = "39",
number = "1",
pages = "5:1--5:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2532641",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article develops upper and lower bounds for the
probability of Boolean functions by treating multiple
occurrences of variables as independent and assigning
them new individual probabilities. We call this
approach dissociation and give an exact
characterization of optimal oblivious bounds, that is,
when the new probabilities are chosen independently of
the probabilities of all other variables. Our
motivation comes from the weighted model counting
problem (or, equivalently, the problem of computing the
probability of a Boolean function), which is \#P-hard
in general. By performing several dissociations, one
can transform a Boolean formula whose probability is
difficult to compute into one whose probability is easy
to compute, and which is guaranteed to provide an upper
or lower bound on the probability of the original
formula by choosing appropriate probabilities for the
dissociated variables. Our new bounds shed light on the
connection between previous relaxation-based and
model-based approximations and unify them as concrete
choices in a larger design space. We also show how our
theory allows a standard relational database management
system (DBMS) to both upper and lower bound hard
probabilistic queries in guaranteed polynomial time.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fang:2014:MOP,
author = "Qiong Fang and Wilfred Ng and Jianlin Feng and Yuliang
Li",
title = "Mining order-preserving submatrices from probabilistic
matrices",
journal = j-TODS,
volume = "39",
number = "1",
pages = "6:1--6:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2533712",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Order-preserving submatrices (OPSMs) capture consensus
trends over columns shared by rows in a data matrix.
Mining OPSM patterns discovers important and
interesting local correlations in many real
applications, such as those involving biological data
or sensor data. The prevalence of uncertain data in
various applications, however, poses new challenges for
OPSM mining, since data uncertainty must be
incorporated into OPSM modeling and the algorithmic
aspects. In this article, we define new probabilistic
matrix representations to model uncertain data with
continuous distributions. A novel probabilistic
order-preserving submatrix (POPSM) model is formalized
in order to capture similar local correlations in
probabilistic matrices. The POPSM model adopts a new
probabilistic support measure that evaluates the extent
to which a row belongs to a POPSM pattern. Due to the
intrinsic high computational complexity of the POPSM
mining problem, we utilize the anti-monotonic property
of the probabilistic support measure and propose an
efficient Apriori-based mining framework called
ProbApri to mine POPSM patterns. The framework consists
of two mining methods, UniApri and NormApri, which are
developed for mining POPSM patterns, respectively, from
two representative types of probabilistic matrices, the
UniDist matrix (assuming uniform data distributions)
and the NormDist matrix (assuming normal data
distributions). We show that the NormApri method is
practical enough for mining POPSM patterns from
probabilistic matrices that model more general data
distributions. We demonstrate the superiority of our
approach by two applications. First, we use two
biological datasets to illustrate that the POPSM model
better captures the characteristics of the expression
levels of biologically correlated genes and greatly
promotes the discovery of patterns with high biological
significance. Our result is significantly better than
the counterpart OPSMRM (OPSM with repeated measurement)
model which adopts a set-valued matrix representation
to capture data uncertainty. Second, we run the
experiments on an RFID trace dataset and show that our
POPSM model is effective and efficient in capturing the
common visiting subroutes among users.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wang:2014:ESS,
author = "Jiannan Wang and Guoliang Li and Jianhua Feng",
title = "Extending string similarity join to tolerant fuzzy
token matching",
journal = j-TODS,
volume = "39",
number = "1",
pages = "7:1--7:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2535628",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "String similarity join that finds similar string pairs
between two string sets is an essential operation in
many applications and has attracted significant
attention recently in the database community. A
significant challenge in similarity join is to
implement an effective fuzzy match operation to find
all similar string pairs which may not match exactly.
In this article, we propose a new similarity function,
called fuzzy-token-matching-based similarity which
extends token-based similarity functions (e.g., jaccard
similarity and cosine similarity) by allowing fuzzy
match between two tokens. We study the problem of
similarity join using this new similarity function and
present a signature-based method to address this
problem. We propose new signature schemes and develop
effective pruning techniques to improve the
performance. We also extend our techniques to support
weighted tokens. Experimental results show that our
method achieves high efficiency and result quality and
significantly outperforms state-of-the-art
approaches.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Sen:2014:DRM,
author = "Siddhartha Sen and Robert E. Tarjan",
title = "Deletion without rebalancing in multiway search
trees",
journal = j-TODS,
volume = "39",
number = "1",
pages = "8:1--8:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2540068",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Some database systems that use a form of B-tree for
the underlying data structure do not do rebalancing on
deletion. This means that a bad sequence of deletions
can create a very unbalanced tree. Yet such databases
perform well in practice. Avoidance of rebalancing on
deletion has been justified empirically and by
average-case analysis, but to our knowledge, no
worst-case analysis has been done. We do such an
analysis. We show that the tree height remains
logarithmic in the number of insertions, independent of
the number of deletions. Furthermore, the amortized
time for an insertion or deletion, excluding the search
time, is $ O(1) $, and nodes are modified by insertions
and deletions with a frequency that is exponentially
small in their height. The latter results do not hold
for standard B-trees. By adding periodic rebuilding of
the tree, we obtain a data structure that is
theoretically superior to standard B-trees in many
ways. Our results suggest that rebalancing on deletion
not only is unnecessary but may be harmful.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nekrich:2014:ERS,
author = "Yakov Nekrich",
title = "Efficient range searching for categorical and plain
data",
journal = j-TODS,
volume = "39",
number = "1",
pages = "9:1--9:??",
month = jan,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2543924",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Feb 5 11:31:16 MST 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In the orthogonal range-searching problem, we store a
set of input points $S$ in a data structure; the answer
to a query $Q$ is a piece of information about points
in $ Q \cap S $, for example, the list of all points in
$ Q \cap S $ or the number of points in $Q$. In the
colored (or categorical) range-searching problem, the
set of input points is partitioned into categories; the
answer to a query is a piece of information about
categories of points in a query range. In this article,
we describe several new results for one- and
two-dimensional range-searching problems. We obtain an
optimal adaptive data structure for counting the number
of objects in a three-sided range and for counting
categories of objects in a one-dimensional range. We
also obtain new results on color range reporting in two
dimensions, approximate color counting in one
dimension, and some other related problems.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Xu:2014:OCP,
author = "Pan Xu and Srikanta Tirthapura",
title = "Optimality of Clustering Properties of Space-Filling
Curves",
journal = j-TODS,
volume = "39",
number = "2",
pages = "10:1--10:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2556686",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Space-filling curves have been used in the design of
data structures for multidimensional data for many
decades. A fundamental quality metric of a
space-filling curve is its ``clustering number'' with
respect to a class of queries, which is the average
number of contiguous segments on the space-filling
curve that a query region can be partitioned into. We
present a characterization of the clustering number of
a general class of space-filling curves, as well as the
first nontrivial lower bounds on the clustering number
for any space-filling curve. Our results answer
questions that have been open for more than 15 years.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Thomson:2014:FDT,
author = "Alexander Thomson and Thaddeus Diamond and Shu-Chun
Weng and Kun Ren and Philip Shao and Daniel J. Abadi",
title = "Fast Distributed Transactions and Strongly Consistent
Replication for {OLTP} Database Systems",
journal = j-TODS,
volume = "39",
number = "2",
pages = "11:1--11:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2556685",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "As more data management software is designed for
deployment in public and private clouds, or on a
cluster of commodity servers, new distributed storage
systems increasingly achieve high data access
throughput via partitioning and replication. In order
to achieve high scalability, however, today's systems
generally reduce transactional support, disallowing
single transactions from spanning multiple partitions.
This article describes Calvin, a practical transaction
scheduling and data replication layer that uses a
deterministic ordering guarantee to significantly
reduce the normally prohibitive contention costs
associated with distributed transactions. This allows
near-linear scalability on a cluster of commodity
machines, without eliminating traditional transactional
guarantees, introducing a single point of failure, or
requiring application developers to reason about data
partitioning. By replicating transaction inputs instead
of transactional actions, Calvin is able to support
multiple consistency levels-including Paxos-based
strong consistency across geographically distant
replicas-at no cost to transactional throughput.
Furthermore, Calvin introduces a set of tools that will
allow application developers to gain the full
performance benefit of Calvin's server-side transaction
scheduling mechanisms without introducing the
additional code complexity and inconvenience normally
associated with using DBMS stored procedures in place
of ad hoc client-side transactions.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nykiel:2014:SAM,
author = "Tomasz Nykiel and Michalis Potamias and Chaitanya
Mishra and George Kollios and Nick Koudas",
title = "Sharing across Multiple {MapReduce} Jobs",
journal = j-TODS,
volume = "39",
number = "2",
pages = "12:1--12:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2560796",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Large-scale data analysis lies in the core of modern
enterprises and scientific research. With the emergence
of cloud computing, the use of an analytical query
processing infrastructure can be directly associated
with monetary cost. MapReduce has been a popular
framework in the context of cloud computing, designed
to serve long-running queries (jobs) which can be
processed in batch mode. Taking into account that
different jobs often perform similar work, there are
many opportunities for sharing. In principle, sharing
similar work reduces the overall amount of work, which
can lead to reducing monetary charges for utilizing the
processing infrastructure. In this article we present a
sharing framework tailored to MapReduce, namely, {\tt
MRShare}. Our framework, {\tt MRShare}, transforms a
batch of queries into a new batch that will be executed
more efficiently, by merging jobs into groups and
evaluating each group as a single query. Based on our
cost model for MapReduce, we define an optimization
problem and we provide a solution that derives the
optimal grouping of queries. Given the query grouping,
we merge jobs appropriately and submit them to
MapReduce for processing. A key property of {\tt
MRShare} is that it is independent of the MapReduce
implementation. Experiments with our prototype, built
on top of Hadoop, demonstrate the overall effectiveness
of our approach. {\tt MRShare} is primarily designed
for handling I/O-intensive queries. However, with the
development of high-level languages operating on top of
MapReduce, user queries executed in this model become
more complex and CPU intensive. Commonly, executed
queries can be modeled as evaluating pipelines of
CPU-expensive filters over the input stream. Examples
of such filters include, but are not limited to, index
probes, or certain types of joins. In this article we
adapt some of the standard techniques for filter
ordering used in relational and stream databases,
propose their extensions, and implement them through
{\tt MRAdaptiveFilter}, an extension of {\tt MRShare}
for expensive filter ordering tailored to MapReduce,
which allows one to handle both single- and batch-query
execution modes. We present an experimental evaluation
that demonstrates additional benefits of {\tt
MRAdaptiveFilter}, when executing CPU-intensive queries
in {\tt MRShare}.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lu:2014:EAC,
author = "Ying Lu and Jiaheng Lu and Gao Cong and Wei Wu and
Cyrus Shahabi",
title = "Efficient Algorithms and Cost Models for Reverse
Spatial-Keyword $k$-Nearest Neighbor Search",
journal = j-TODS,
volume = "39",
number = "2",
pages = "13:1--13:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2576232",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Geographic objects associated with descriptive texts
are becoming prevalent, justifying the need for
spatial-keyword queries that consider both locations
and textual descriptions of the objects. Specifically,
the relevance of an object to a query is measured by
spatial-textual similarity that is based on both
spatial proximity and textual similarity. In this
article, we introduce the Reverse Spatial-Keyword
$k$-Nearest Neighbor (RSK $k$ NN) query, which finds
those objects that have the query as one of their $k$
nearest spatial-textual objects. The RSK $k$ NN queries
have numerous applications in online maps and GIS
decision support systems. To answer RSK $k$ NN queries
efficiently, we propose a hybrid index tree, called
IUR-tree (Intersection-Union R-tree) that effectively
combines location proximity with textual similarity.
Subsequently, we design a branch-and-bound search
algorithm based on the IUR-tree. To accelerate the
query processing, we improve IUR-tree by leveraging the
distribution of textual description, leading to some
variants of the IUR-tree called Clustered IUR-tree
(CIUR-tree) and combined clustered IUR-tree (C$^2$
IUR-tree), for each of which we develop optimized
algorithms. We also provide a theoretical cost model to
analyze the efficiency of our algorithms. Our empirical
studies show that the proposed algorithms are efficient
and scalable.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bartolini:2014:DPW,
author = "Ilaria Bartolini and Paolo Ciaccia and Marco Patella",
title = "Domination in the Probabilistic World: Computing
Skylines for Arbitrary Correlations and Ranking
Semantics",
journal = j-TODS,
volume = "39",
number = "2",
pages = "14:1--14:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2602135",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In a probabilistic database, deciding if a tuple $u$
is better than another tuple $v$ has not a univocal
solution, rather it depends on the specific
Probabilistic Ranking Semantics (PRS) one wants to
adopt so as to combine together tuples' scores and
probabilities. In deterministic databases it is known
that skyline queries are a remarkable alternative to
(top-$k$) ranking queries, because they remove from the
user the burden of specifying a scoring function that
combines values of different attributes into a single
score. The skyline of a deterministic relation $R$ is
the set of undominated tuples in $R$ --- tuple $u$
dominates tuple $v$ iff on all the attributes of
interest $u$ is better than or equal to $v$ and
strictly better on at least one attribute. Domination
is equivalent to having $ s(u) >= s(v)$ for all
monotone scoring functions $ s()$. The skyline of a
probabilistic relation $ R^p$ can be similarly defined
as the set of $P$-undominated tuples in $ R^p$, where
now $u$ $P$-dominates $v$ iff, whatever monotone
scoring function one would use to combine the skyline
attributes, $u$ is reputed better than $v$ by the PRS
at hand. This definition, which is applicable to
arbitrary ranking semantics and probabilistic
correlation models, is parametric in the adopted PRS,
thus it ensures that ranking and skyline queries will
always return consistent results. In this article we
provide an overall view of the problem of computing the
skyline of a probabilistic relation. We show how, under
mild conditions that indeed hold for all known PRSs,
checking $P$-domination can be cast into an
optimization problem, whose complexity we characterize
for a variety of combinations of ranking semantics and
correlation models. For each analyzed case we also
provide specific $P$-domination rules, which are
exploited by the algorithm we detail for the case where
the probabilistic model is known to the query
processor. We also consider the case in which the
probability of tuple events can only be obtained
through an oracle, and describe another skyline
algorithm for this loosely integrated scenario. Our
experimental evaluation of $P$-domination rules and
skyline algorithms confirms the theoretical analysis.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Deng:2014:CQR,
author = "Ting Deng and Wenfei Fan",
title = "On the Complexity of Query Result Diversification",
journal = j-TODS,
volume = "39",
number = "2",
pages = "15:1--15:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2602136",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Query result diversification is a bi-criteria
optimization problem for ranking query results. Given a
database $D$, a query $Q$, and a positive integer k, it
is to find a set of $k$ tuples from $ Q(D)$ such that
the tuples are as relevant as possible to the query,
and at the same time, as diverse as possible to each
other. Subsets of $ Q(D)$ are ranked by an objective
function defined in terms of relevance and diversity.
Query result diversification has found a variety of
applications in databases, information retrieval, and
operations research. This article investigates the
complexity of result diversification for relational
queries. (1) We identify three problems in connection
with query result diversification, to determine whether
there exists a set of $k$ tuples that is ranked above a
bound with respect to relevance and diversity, to
assess the rank of a given $k$-element set, and to
count how many $k$-element sets are ranked above a
given bound based on an objective function. (2) We
study these problems for a variety of query languages
and for the three objective functions proposed in
Gollapudi and Sharma [2009]. We establish the upper and
lower bounds of these problems, all matching, for both
combined complexity and data complexity. (3) We also
investigate several special settings of these problems,
identifying tractable cases. Moreover, (4) we
reinvestigate these problems in the presence of
compatibility constraints commonly found in practice,
and provide their complexity in all these settings.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Giatrakos:2014:DGQ,
author = "Nikos Giatrakos and Antonios Deligiannakis and Minos
Garofalakis and Izchak Sharfman and Assaf Schuster",
title = "Distributed Geometric Query Monitoring Using
Prediction Models",
journal = j-TODS,
volume = "39",
number = "2",
pages = "16:1--16:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2602137",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many modern streaming applications, such as online
analysis of financial, network, sensor, and other forms
of data, are inherently distributed in nature. An
important query type that is the focal point in such
application scenarios regards actuation queries, where
proper action is dictated based on a trigger condition
placed upon the current value that a monitored function
receives. Recent work [Sharfman et al. 2006, 2007b,
2008] studies the problem of (nonlinear) sophisticated
function tracking in a distributive manner. The main
concept behind the geometric monitoring approach
proposed there is for each distributed site to perform
the function monitoring over an appropriate subset of
the input domain. In the current work, we examine
whether the distributed monitoring mechanism can become
more efficient, in terms of the number of communicated
messages, by extending the geometric monitoring
framework to utilize prediction models. We initially
describe a number of local estimators (predictors) that
are useful for the applications that we consider and
which have already been shown particularly useful in
past work. We then demonstrate the feasibility of
incorporating predictors in the geometric monitoring
framework and show that prediction-based geometric
monitoring in fact generalizes the original geometric
monitoring framework. We propose a large variety of
different prediction-based monitoring models for the
distributed threshold monitoring of complex functions.
Our extensive experimentation with a variety of real
datasets, functions, and parameter settings indicates
that our approaches can provide significant
communication savings ranging between two times and up
to three orders of magnitude, compared to the
transmission cost of the original monitoring
framework.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lei:2014:RDQ,
author = "Chuan Lei and Elke A. Rundensteiner",
title = "Robust Distributed Query Processing for Streaming
Data",
journal = j-TODS,
volume = "39",
number = "2",
pages = "17:1--17:??",
month = may,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2602138",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed May 21 18:53:24 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Distributed stream processing systems must function
efficiently for data streams that fluctuate in their
arrival rates and data distributions. Yet repeated and
prohibitively expensive load reallocation across
machines may make these systems ineffective,
potentially resulting in data loss or even system
failure. To overcome this problem, we propose a
comprehensive solution, called the Robust Load
Distribution (RLD) strategy, that is resilient under
data fluctuations. RLD provides $ \epsilon $-optimal
query performance under an expected range of load
fluctuations without suffering from the performance
penalty caused by load migration. RLD is based on three
key strategies. First, we model robust distributed
stream processing as a parametric query optimization
problem in a parameter space that captures the stream
fluctuations. The notions of both robust logical and
robust physical plans that work together to proactively
handle all ranges of expected fluctuations in
parameters are abstracted as overlays of this parameter
space. Second, our Early-terminated Robust Partitioning
(ERP) finds a combination of robust logical plans
that together cover the parameter space, while
minimizing the number of prohibitively expensive
optimizer calls with a probabilistic bound on the space
coverage. Third, we design a family of algorithms for
physical plan generation. Our GreedyPhy exploits a
probabilistic model to efficiently find a robust
physical plan that sustains most frequently used robust
logical plans at runtime. Our CorPhy algorithm exploits
operator correlations for the robust physical plan
optimization. The resulting physical plan smooths the
workload on each node under all expected fluctuations.
Our OptPrune algorithm, using CorPhy as baseline, is
guaranteed to find the optimal physical plan that
maximizes the parameter space coverage with a practical
increase in optimization time. Lastly, we further
expand the capabilities of our proposed RLD framework
to also appropriately react under so-called ``space
drifts'', that is, a space drift is a change of the
parameter space where the observed runtime statistics
deviate from the expected optimization-time statistics.
Our RLD solution is capable of adjusting itself to the
unexpected yet significant data fluctuations beyond
those planned for via covering the parameter space. Our
experimental study using stock market and sensor
network streams demonstrates that our RLD methodology
consistently outperforms state-of-the-art solutions in
terms of efficiency and effectiveness in highly
fluctuating data stream environments.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2014:E,
author = "Christian S. Jensen",
title = "Editorial",
journal = j-TODS,
volume = "39",
number = "3",
pages = "18:1--18:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2662448",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhang:2014:TPI,
author = "Rui Zhang and Jianzhong Qi and Martin Stradling and
Jin Huang",
title = "Towards a Painless Index for Spatial Objects",
journal = j-TODS,
volume = "39",
number = "3",
pages = "19:1--19:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2629333",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Conventional spatial indexes, represented by the
R-tree, employ multidimensional tree structures that
are complicated and require enormous efforts to
implement in a full-fledged database management system
(DBMS). An alternative approach for supporting spatial
queries is mapping-based indexing, which maps both data
and queries into a one-dimensional space such that data
can be indexed and queries can be processed through a
one-dimensional indexing structure such as the B$^+$.
Mapping-based indexing requires implementing only a few
mapping functions, incurring much less effort in
implementation compared to conventional spatial index
structures. Yet, a major concern about using
mapping-based indexes is their lower efficiency than
conventional tree structures. In this article, we
propose a mapping-based spatial indexing scheme called
Size Separation Indexing (SSI). SSI is equipped with a
suite of techniques including size separation, data
distribution transformation, and more efficient mapping
algorithms. These techniques overcome the drawbacks of
existing mapping-based indexes and significantly
improve the efficiency of query processing. We show
through extensive experiments that, for window queries
on spatial objects with nonzero extents, SSI has two
orders of magnitude better performance than existing
mapping-based indexes and competitive performance to
the R-tree as a standalone implementation. We have also
implemented SSI on top of two off-the-shelf DBMSs,
PostgreSQL and a commercial platform, both having
R-tree implementation. In this case, SSI is up to two
orders of magnitude faster than their provided spatial
indexes. Therefore, we achieve a spatial index more
efficient than the R-tree in a DBMS implementation that
is at the same time easy to implement. This result may
upset a common perception that has existed for a long
time in this area that the R-tree is the best choice
for indexing spatial objects.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tatti:2014:FRI,
author = "Nikolaj Tatti and Fabian Moerchen and Toon Calders",
title = "Finding Robust Itemsets under Subsampling",
journal = j-TODS,
volume = "39",
number = "3",
pages = "20:1--20:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2656261",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Mining frequent patterns is plagued by the problem of
pattern explosion, making pattern reduction techniques
a key challenge in pattern mining. In this article we
propose a novel theoretical framework for pattern
reduction by measuring the robustness of a property of
an itemset such as closedness or nonderivability. The
robustness of a property is the probability that this
property holds on random subsets of the original data.
We study four properties, namely an itemset being
closed, free, non-derivable, or totally shattered, and
demonstrate how to compute the robustness analytically
without actually sampling the data. Our concept of
robustness has many advantages: Unlike statistical
approaches for reducing patterns, we do not assume a
null hypothesis or any noise model and, in contrast to
noise-tolerant or approximate patterns, the robust
patterns for a given property are always a subset of
the patterns with this property. If the underlying
property is monotonic then the measure is also
monotonic, allowing us to efficiently mine robust
itemsets. We further derive a parameter-free technique
for ranking itemsets that can be used for top- k
approaches. Our experiments demonstrate that we can
successfully use the robustness measure to reduce the
number of patterns and that ranking yields interesting
itemsets.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Choi:2014:MRS,
author = "Dong-Wan Choi and Chin-Wan Chung and Yufei Tao",
title = "Maximizing Range Sum in External Memory",
journal = j-TODS,
volume = "39",
number = "3",
pages = "21:1--21:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2629477",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article studies the MaxRS problem in spatial
databases. Given a set O of weighted points and a
rectangle r of a given size, the goal of the MaxRS
problem is to find a location of r such that the sum of
the weights of all the points covered by r is
maximized. This problem is useful in many
location-based services such as finding the best place
for a new franchise store with a limited delivery range
and finding the hotspot with the largest number of
nearby attractions for a tourist with a limited
reachable range. However, the problem has been studied
mainly in the theoretical perspective, particularly in
computational geometry. The existing algorithms from
the computational geometry community are in-memory
algorithms that do not guarantee the scalability. In
this article, we propose a scalable external-memory
algorithm ( ExactMaxRS ) for the MaxRS problem that is
optimal in terms of the I/O complexity. In addition, we
propose an approximation algorithm ( ApproxMaxCRS ) for
the MaxCRS problem that is a circle version of the
MaxRS problem. We prove the correctness and optimality
of the ExactMaxRS algorithm along with the
approximation bound of the ApproxMaxCRS algorithm.
Furthermore, motivated by the fact that all the
existing solutions simply assume that there is no tied
area for the best location, we extend the MaxRS problem
to a more fundamental problem, namely AllMaxRS, so that
all the locations with the same best score can be
retrieved. We first prove that the AllMaxRS problem
cannot be trivially solved by applying the techniques
for the MaxRS problem. Then we propose an
output-sensitive external-memory algorithm (
TwoPhaseMaxRS ) that gives the exact solution for the
AllMaxRS problem through two phases. Also, we prove
both the soundness and completeness of the result
returned from TwoPhaseMaxRS. From extensive
experimental results, we show that ExactMaxRS and
ApproxMaxCRS are several orders of magnitude faster
than methods adapted from existing algorithms, the
approximation bound in practice is much better than the
theoretical bound of ApproxMaxCRS, and TwoPhaseMaxRS is
not only much faster but also more robust than the
straightforward extension of ExactMaxRS.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Karwa:2014:PAG,
author = "Vishesh Karwa and Sofya Raskhodnikova and Adam Smith
and Grigory Yaroslavtsev",
title = "Private Analysis of Graph Structure",
journal = j-TODS,
volume = "39",
number = "3",
pages = "22:1--22:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2611523",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We present efficient algorithms for releasing useful
statistics about graph data while providing rigorous
privacy guarantees. Our algorithms work on datasets
that consist of relationships between individuals, such
as social ties or email communication. The algorithms
satisfy edge differential privacy, which essentially
requires that the presence or absence of any particular
relationship be hidden. Our algorithms output
approximate answers to subgraph counting queries. Given
a query graph H, for example, a triangle, $k$-star, or
$k$ triangle, the goal is to return the number of
edge-induced isomorphic copies of $H$ in the input
graph. The special case of triangles was considered by
Nissim et al. [2007] and a more general investigation
of arbitrary query graphs was initiated by Rastogi et
al. [2009]. We extend the approach of Nissim et al. to
a new class of statistics, namely $k$-star queries. We
also give algorithms for $k$-triangle queries using a
different approach based on the higher-order local
sensitivity. For the specific graph statistics we
consider (i.e., $k$-stars and $k$-triangles), we
significantly improve on the work of Rastogi et al.:
our algorithms satisfy a stronger notion of privacy
that does not rely on the adversary having a particular
prior distribution on the data, and add less noise to
the answers before releasing them. We evaluate the
accuracy of our algorithms both theoretically and
empirically, using a variety of real and synthetic
datasets. We give explicit, simple conditions under
which these algorithms add a small amount of noise. We
also provide the average-case analysis in the
Erd{\H{o}}s--R{\'e}nyi-Gilbert $ G(n, p)$ random graph
model. Finally, we give hardness results indicating
that the approach Nissim et al. used for triangles
cannot easily be extended to $k$-triangles (hence
justifying our development of a new algorithmic
approach).",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pang:2014:PPA,
author = "Hweehwa Pang and Xuhua Ding",
title = "Privacy-Preserving Ad-Hoc Equi-Join on Outsourced
Data",
journal = j-TODS,
volume = "39",
number = "3",
pages = "23:1--23:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2629501",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In IT outsourcing, a user may delegate the data
storage and query processing functions to a third-party
server that is not completely trusted. This gives rise
to the need to safeguard the privacy of the database as
well as the user queries over it. In this article, we
address the problem of running ad hoc equi-join queries
directly on encrypted data in such a setting. Our
contribution is the first solution that achieves
constant complexity per pair of records that are
evaluated for the join. After formalizing the privacy
requirements pertaining to the database and user
queries, we introduce a cryptographic construct for
securely joining records across relations. The
construct protects the database with a strong
encryption scheme. Moreover, information disclosure
after executing an equi-join is kept to the
minimum-that two input records combine to form an
output record if and only if they share common join
attribute values. There is no disclosure on records
that are not part of the join result. Building on this
construct, we then present join algorithms that
optimize the join execution by eliminating the need to
match every record pair from the input relations. We
provide a detailed analysis of the cost of the
algorithms and confirm the analysis through extensive
experiments with both synthetic and benchmark
workloads. Through this evaluation, we tease out useful
insights on how to configure the join algorithms to
deliver acceptable execution time in practice.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Malvestuto:2014:JLO,
author = "Francesco M. Malvestuto",
title = "A Join-Like Operator to Combine Data Cubes and Answer
Queries from Multiple Data Cubes",
journal = j-TODS,
volume = "39",
number = "3",
pages = "24:1--24:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2638545",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In order to answer a ``joint'' query from multiple
data cubes, Pourabass and Shoshani [2007] distinguish
the data cube on the measure of interest (called the
``primary'' data cube) from the other data cubes
(called ``proxy'' data cubes) that are used to involve
the dimensions (in the query) not in the primary data
cube. They demonstrate in study cases that, if the
measures of the primary and proxy data cubes are
correlated, then the answer to a joint query is an
accurate estimate of its true value. Needless to say,
for two or more proxy data cubes, the result depends
upon the way the primary and proxy data cubes are
combined together; however, for certain combination
schemes Pourabass and Shoshani provide a sufficient
condition, that they call proxy noncommonality, for the
invariance of the result. In this article, we
introduce: (1) a merge operator combining the contents
of a primary data cube with the contents of a proxy
data cube, (2) merge expressions for general
combination schemes, and (3) an equivalence relation
between merge expressions having the same pattern.
Then, we prove that proxy noncommonality characterizes
patterns for which every two merge expressions are
equivalent. Moreover, we provide an efficient procedure
for answering joint queries in the special case of
perfect merge expressions. Finally, we show that our
results apply to data cubes in which measures are
obtained from unaggregated data using the aggregate
functions SUM, COUNT, MAX, and MIN, and a lot more.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gottlob:2014:QRO,
author = "Georg Gottlob and Giorgio Orsi and Andreas Pieris",
title = "Query Rewriting and Optimization for Ontological
Databases",
journal = j-TODS,
volume = "39",
number = "3",
pages = "25:1--25:??",
month = sep,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2638546",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 7 18:54:33 MDT 2014",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Ontological queries are evaluated against a knowledge
base consisting of an extensional database and an
ontology (i.e., a set of logical assertions and
constraints that derive new intensional knowledge from
the extensional database), rather than directly on the
extensional database. The evaluation and optimization
of such queries is an intriguing new problem for
database research. In this article, we discuss two
important aspects of this problem: query rewriting and
query optimization. Query rewriting consists of the
compilation of an ontological query into an equivalent
first-order query against the underlying extensional
database. We present a novel query rewriting algorithm
for rather general types of ontological constraints
that is well suited for practical implementations. In
particular, we show how a conjunctive query against a
knowledge base, expressed using linear and sticky
existential rules, that is, members of the recently
introduced Datalog\pm{} family of ontology languages,
can be compiled into a union of conjunctive queries
(UCQ) against the underlying database. Ontological
query optimization, in this context, attempts to
improve this rewriting process soas to produce possibly
small and cost-effective UCQ rewritings for an input
query.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2014:FIA,
author = "Christian S. Jensen",
title = "Foreword to Invited Articles Issue",
journal = j-TODS,
volume = "39",
number = "4",
pages = "26:1--26:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2697050",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hu:2014:EAT,
author = "Xiaocheng Hu and Yufei Tao and Chin-Wan Chung",
title = "{I/O}-Efficient Algorithms on Triangle Listing and
Counting",
journal = j-TODS,
volume = "39",
number = "4",
pages = "27:1--27:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2691190.2691193",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article studies I/O-efficient algorithms for the
triangle listing problem and the triangle counting
problem, whose solutions are basic operators in dealing
with many other graph problems. In the former problem,
given an undirected graph G, the objective is to find
all the cliques involving 3 vertices in G. In the
latter problem, the objective is to report just the
number of such cliques without having to enumerate
them. Both problems have been well studied in internal
memory, but still remain as difficult challenges when G
does not fit in memory, thus making it crucial to
minimize the number of disk I/Os performed. Although
previous research has attempted to tackle these
challenges, the state-of-the-art solutions rely on a
set of crippling assumptions to guarantee good
performance. Motivated by this, we develop a new
algorithm that is provably I/O and CPU efficient at the
same time, without making any assumption on the input G
at all. The algorithm uses ideas drastically different
from all the previous approaches, and outperforms the
existing competitors by a factor of over an order of
magnitude in our extensive experimentation.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2014:DXK,
author = "Marcelo Arenas and Jonny Daenen and Frank Neven and
Martin Ugarte and Jan {Van Den Bussche} and Stijn
Vansummeren",
title = "Discovering {XSD} Keys from {XML} Data",
journal = j-TODS,
volume = "39",
number = "4",
pages = "28:1--28:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2638547",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A great deal of research into the learning of schemas
from XML data has been conducted in recent years to
enable the automatic discovery of XML schemas from XML
documents when no schema or only a low-quality one is
available. Unfortunately, and in strong contrast to,
for instance, the relational model, the automatic
discovery of even the simplest of XML constraints,
namely XML keys, has been left largely unexplored in
this context. A major obstacle here is the
unavailability of a theory on reasoning about XML keys
in the presence of XML schemas, which is needed to
validate the quality of candidate keys. The present
article embarks on a fundamental study of such a theory
and classifies the complexity of several crucial
properties concerning XML keys in the presence of an
XSD, like, for instance, testing for consistency,
boundedness, satisfiability, universality, and
equivalence. Of independent interest, novel results are
obtained related to cardinality estimation of XPath
result sets. A mining algorithm is then developed
within the framework of levelwise search. The algorithm
leverages known discovery algorithms for functional
dependencies in the relational model, but incorporates
the properties mentioned before to assess and refine
the quality of derived keys. An experimental study on
an extensive body of real-world XML data evaluating the
effectiveness of the proposed algorithm is provided.",
acknowledgement = ack-nhfb,
articleno = "28",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jung:2014:SLM,
author = "Hyungsoo Jung and Hyuck Han and Alan Fekete and Gernot
Heiser and Heon Y. Yeom",
title = "A Scalable Lock Manager for Multicores",
journal = j-TODS,
volume = "39",
number = "4",
pages = "29:1--29:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2691190.2691192",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Modern implementations of DBMS software are intended
to take advantage of high core counts that are becoming
common in high-end servers. However, we have observed
that several database platforms, including MySQL,
Shore-MT, and a commercial system, exhibit throughput
collapse as load increases into oversaturation (where
there are more request threads than cores), even for a
workload with little or no logical contention for
locks, such as a read-only workload. Our analysis of
MySQL identifies latch contention within the lock
manager as the bottleneck responsible for this
collapse. We design a lock manager with reduced
latching, implement it in MySQL, and show that it
avoids the collapse and generally improves performance.
Our efficient implementation of a lock manager is
enabled by a staged allocation and deallocation of
locks. Locks are preallocated in bulk, so that the lock
manager only has to perform simple list manipulation
operations during the acquire and release phases of a
transaction. Deallocation of the lock data structures
is also performed in bulk, which enables the use of
fast implementations of lock acquisition and release as
well as concurrent deadlock checking.",
acknowledgement = ack-nhfb,
articleno = "29",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papadopoulos:2014:LQA,
author = "Stavros Papadopoulos and Graham Cormode and Antonios
Deligiannakis and Minos Garofalakis",
title = "Lightweight Query Authentication on Streams",
journal = j-TODS,
volume = "39",
number = "4",
pages = "30:1--30:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2656336",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider a stream outsourcing setting, where a data
owner delegates the management of a set of disjoint
data streams to an untrusted server. The owner
authenticates his streams via signatures. The server
processes continuous queries on the union of the
streams for clients trusted by the owner. Along with
the results, the server sends proofs of result
correctness derived from the owner's signatures, which
are verifiable by the clients. We design novel
constructions for a collection of fundamental problems
over streams represented as linear algebraic queries.
In particular, our basic schemes authenticate dynamic
vector sums, matrix products, and dot products. These
techniques can be adapted for authenticating a wide
range of important operations in streaming
environments, including group-by queries, joins,
in-network aggregation, similarity matching, and event
processing. We also present extensions to address the
case of sliding window queries, and when multiple
clients are interested in different subsets of the
data. These methods take advantage of a novel nonce
chaining technique that we introduce, which is used to
reduce the verification cost without affecting any
other costs. All our schemes are lightweight and offer
strong cryptographic guarantees derived from formal
definitions and proofs. We experimentally confirm the
practicality of our schemes in the
performance-sensitive streaming setting.",
acknowledgement = ack-nhfb,
articleno = "30",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gheerbrant:2014:NEQ,
author = "Am{\'e}lie Gheerbrant and Leonid Libkin and Cristina
Sirangelo",
title = "Na{\"\i}ve Evaluation of Queries over Incomplete
Databases",
journal = j-TODS,
volume = "39",
number = "4",
pages = "31:1--31:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2691190.2691194",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The term na{\"\i}ve evaluation refers to evaluating
queries over incomplete databases as if nulls were
usual data values, that is, to using the standard
database query evaluation engine. Since the semantics
of query answering over incomplete databases is that of
certain answers, we would like to know when na{\"\i}ve
evaluation computes them, that is, when certain answers
can be found without inventing new specialized
algorithms. For relational databases it is well known
that unions of conjunctive queries possess this
desirable property, and results on preservation of
formulae under homomorphisms tell us that, within
relational calculus, this class cannot be extended
under the open-world assumption. Our goal here is
twofold. First, we develop a general framework that
allows us to determine, for a given semantics of
incompleteness, classes of queries for which na{\"\i}ve
evaluation computes certain answers. Second, we apply
this approach to a variety of semantics, showing that
for many classes of queries beyond unions of
conjunctive queries, na{\"\i}ve evaluation makes
perfect sense under assumptions different from open
world. Our key observations are: (1) na{\"\i}ve
evaluation is equivalent to monotonicity of queries
with respect to a semantics-induced ordering, and (2)
for most reasonable semantics of incompleteness, such
monotonicity is captured by preservation under various
types of homomorphisms. Using these results we find
classes of queries for which na{\"\i}ve evaluation
works, for example, positive first-order formulae for
the closed-world semantics. Even more, we introduce a
general relation-based framework for defining semantics
of incompleteness, show how it can be used to capture
many known semantics and to introduce new ones, and
describe classes of first-order queries for which
na{\"\i}ve evaluation works under such semantics.",
acknowledgement = ack-nhfb,
articleno = "31",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kimelfeld:2014:CMM,
author = "Benny Kimelfeld and Phokion G. Kolaitis",
title = "The Complexity of Mining Maximal Frequent Subgraphs",
journal = j-TODS,
volume = "39",
number = "4",
pages = "32:1--32:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2629550",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A frequent subgraph of a given collection of graphs is
a graph that is isomorphic to a subgraph of at least as
many graphs in the collection as a given threshold.
Frequent subgraphs generalize frequent itemsets and
arise in various contexts, from bioinformatics to the
Web. Since the space of frequent subgraphs is typically
extremely large, research in graph mining has focused
on special types of frequent subgraphs that can be
orders of magnitude smaller in number, yet encapsulate
the space of all frequent subgraphs. Maximal frequent
subgraphs (i.e., the ones not properly contained in any
frequent subgraph) constitute the most useful such
type. In this article, we embark on a comprehensive
investigation of the computational complexity of mining
maximal frequent subgraphs. Our study is carried out by
considering the effect of three different parameters:
possible restrictions on the class of graphs; a fixed
bound on the threshold; and a fixed bound on the number
of desired answers. We focus on specific classes of
connected graphs: general graphs, planar graphs, graphs
of bounded degree, and graphs of bounded treewidth
(trees being a special case). Moreover, each class has
two variants: that in which the nodes are unlabeled,
and that in which they are uniquely labeled. We
delineate the complexity of the enumeration problem for
each of these variants by determining when it is
solvable in (total or incremental) polynomial time and
when it is NP-hard. Specifically, for the labeled
classes, we show that bounding the threshold yields
tractability but, in most cases, bounding the number of
answers does not, unless P=NP; an exception is the case
of labeled trees, where bounding either of these two
parameters yields tractability. The state of affairs
turns out to be quite different for the unlabeled
classes. The main (and most challenging to prove)
result concerns unlabeled trees: we show NP-hardness,
even if the input consists of two trees and both the
threshold and the number of desired answers are equal
to just two. In other words, we establish that the
following problem is NP-complete: given two unlabeled
trees, do they have more than one maximal subtree in
common?",
acknowledgement = ack-nhfb,
articleno = "32",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bienvenu:2014:OBD,
author = "Meghyn Bienvenu and Balder {Ten Cate} and Carsten Lutz
and Frank Wolter",
title = "Ontology-Based Data Access: a Study through
Disjunctive {Datalog}, {CSP}, and {MMSNP}",
journal = j-TODS,
volume = "39",
number = "4",
pages = "33:1--33:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2661643",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Ontology-based data access is concerned with querying
incomplete data sources in the presence of
domain-specific knowledge provided by an ontology. A
central notion in this setting is that of an
ontology-mediated query, which is a database query
coupled with an ontology. In this article, we study
several classes of ontology-mediated queries, where the
database queries are given as some form of conjunctive
query and the ontologies are formulated in description
logics or other relevant fragments of first-order
logic, such as the guarded fragment and the unary
negation fragment. The contributions of the article are
threefold. First, we show that popular
ontology-mediated query languages have the same
expressive power as natural fragments of disjunctive
datalog, and we study the relative succinctness of
ontology-mediated queries and disjunctive datalog
queries. Second, we establish intimate connections
between ontology-mediated queries and constraint
satisfaction problems (CSPs) and their logical
generalization, MMSNP formulas. Third, we exploit these
connections to obtain new results regarding: (i)
first-order rewritability and datalog rewritability of
ontology-mediated queries; (ii) P/NP dichotomies for
ontology-mediated queries; and (iii) the query
containment problem for ontology-mediated queries.",
acknowledgement = ack-nhfb,
articleno = "33",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2014:TPP,
author = "Chao Li and Daniel Yang Li and Gerome Miklau and Dan
Suciu",
title = "A Theory of Pricing Private Data",
journal = j-TODS,
volume = "39",
number = "4",
pages = "34:1--34:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2691190.2691191",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Personal data has value to both its owner and to
institutions who would like to analyze it. Privacy
mechanisms protect the owner's data while releasing to
analysts noisy versions of aggregate query results. But
such strict protections of the individual's data have
not yet found wide use in practice. Instead, Internet
companies, for example, commonly provide free services
in return for valuable sensitive information from
users, which they exploit and sometimes sell to third
parties. As awareness of the value of personal data
increases, so has the drive to compensate the end-user
for her private information. The idea of monetizing
private data can improve over the narrower view of
hiding private data, since it empowers individuals to
control their data through financial means. In this
article we propose a theoretical framework for
assigning prices to noisy query answers as a function
of their accuracy, and for dividing the price amongst
data owners who deserve compensation for their loss of
privacy. Our framework adopts and extends key
principles from both differential privacy and query
pricing in data markets. We identify essential
properties of the pricing function and micropayments,
and characterize valid solutions.",
acknowledgement = ack-nhfb,
articleno = "34",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Davidson:2014:TCN,
author = "Susan Davidson and Sanjeev Khanna and Tova Milo and
Sudeepa Roy",
title = "Top-$k$ and Clustering with Noisy Comparisons",
journal = j-TODS,
volume = "39",
number = "4",
pages = "35:1--35:??",
month = dec,
year = "2014",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2684066",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Jan 7 15:35:46 MST 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problems of max/top-$k$ and clustering
when the comparison operations may be performed by
oracles whose answer may be erroneous. Comparisons may
either be of type or of value: given two data elements,
the answer to a type comparison is ``yes'' if the
elements have the same type and therefore belong to the
same group (cluster); the answer to a value comparison
orders the two data elements. We give efficient
algorithms that are guaranteed to achieve correct
results with high probability, analyze the cost of
these algorithms in terms of the total number of
comparisons (i.e., using a fixed-cost model), and show
that they are essentially the best possible. We also
show that fewer comparisons are needed when values and
types are correlated, or when the error model is one in
which the error decreases as the distance between the
two elements in the sorted order increases. Finally, we
examine another important class of cost functions,
concave functions, which balances the number of rounds
of interaction with the oracle with the number of
questions asked of the oracle. Results of this article
form an important first step in providing a formal
basis for max/top-$k$ and clustering queries in
crowdsourcing applications, that is, when the oracle is
implemented using the crowd. We explain what
simplifying assumptions are made in the analysis, what
results carry to a generalized crowdsourcing setting,
and what extensions are required to support a
full-fledged model.",
acknowledgement = ack-nhfb,
articleno = "35",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2015:EUE,
author = "Christian S. Jensen",
title = "Editorial: Updates to the Editorial Board",
journal = j-TODS,
volume = "40",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2747020",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "1e",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pripuzic:2015:TSE,
author = "Kresimir Pripuzi{\'c} and Ivana Podnar Zarko and Karl
Aberer",
title = "Time- and Space-Efficient Sliding Window Top-$k$ Query
Processing",
journal = j-TODS,
volume = "40",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2736701",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A sliding window top-k ( top-k/w ) query monitors
incoming data stream objects within a sliding window of
size w to identify the k highest-ranked objects with
respect to a given scoring function over time.
Processing of such queries is challenging because, even
when an object is not a top-k/w object at the time when
it enters the processing system, it might become one in
the future. Thus a set of potential top-k/w objects has
to be stored in memory while its size should be
minimized to efficiently cope with high data streaming
rates. Existing approaches typically store top-k/w and
candidate sliding window objects in a k-skyband over a
two-dimensional score-time space. However, due to
continuous changes of the k-skyband, its maintenance is
quite costly. Probabilistic k-skyband is a novel data
structure storing data stream objects from a sliding
window with significant probability to become top-k/w
objects in future. Continuous probabilistic k-skyband
maintenance offers considerably improved runtime
performance compared to k-skyband maintenance,
especially for large values of k, at the expense of a
small and controllable error rate. We propose two
possible probabilistic k-skyband usages: ( i ) When it
is used to process all sliding window objects, the
resulting top-k/w algorithm is approximate and adequate
for processing random-order data streams. ( ii ) When
probabilistic k-skyband is used to process only a
subset of most recent sliding window objects, it can
improve the runtime performance of continuous k-skyband
maintenance, resulting in a novel exact top-k/w
algorithm. Our experimental evaluation systematically
compares different top-k/w processing algorithms and
shows that while competing algorithms offer either time
efficiency at the expanse of space efficiency or
vice-versa, our algorithms based on the probabilistic
k-skyband are both time and space efficient.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Olteanu:2015:SBF,
author = "Dan Olteanu and Jakub Z{\'a}vodn{\'y}",
title = "Size Bounds for Factorised Representations of Query
Results",
journal = j-TODS,
volume = "40",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2656335",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study two succinct representation systems for
relational data based on relational algebra expressions
with unions, Cartesian products, and singleton
relations: f-representations, which employ algebraic
factorisation using distributivity of product over
union, and d-representations, which are
f-representations where further succinctness is brought
by explicit sharing of repeated subexpressions. In
particular we study such representations for results of
conjunctive queries. We derive tight asymptotic bounds
for representation sizes and present algorithms to
compute representations within these bounds. We compare
the succinctness of f-representations and
d-representations for results of equi-join queries, and
relate them to fractional edge covers and fractional
hypertree decompositions of the query hypergraph.
Recent work showed that f-representations can
significantly boost the performance of query evaluation
in centralised and distributed settings and of machine
learning tasks.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pawlik:2015:ECT,
author = "Mateusz Pawlik and Nikolaus Augsten",
title = "Efficient Computation of the Tree Edit Distance",
journal = j-TODS,
volume = "40",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699485",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider the classical tree edit distance between
ordered labelled trees, which is defined as the
minimum-cost sequence of node edit operations that
transform one tree into another. The state-of-the-art
solutions for the tree edit distance are not
satisfactory. The main competitors in the field either
have optimal worst-case complexity but the worst case
happens frequently, or they are very efficient for some
tree shapes but degenerate for others. This leads to
unpredictable and often infeasible runtimes. There is
no obvious way to choose between the algorithms. In
this article we present RTED, a robust tree edit
distance algorithm. The asymptotic complexity of our
algorithm is smaller than or equal to the complexity of
the best competitors for any input instance, that is,
our algorithm is both efficient and worst-case optimal.
This is achieved by computing a dynamic decomposition
strategy that depends on the input trees. RTED is shown
optimal among all algorithms that use LRH (
left-right-heavy ) strategies, which include RTED and
the fastest tree edit distance algorithms presented in
literature. In our experiments on synthetic and
real-world data we empirically evaluate our solution
and compare it to the state-of-the-art.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Drosou:2015:MRD,
author = "Marina Drosou and Evaggelia Pitoura",
title = "Multiple Radii {DisC} Diversity: Result
Diversification Based on Dissimilarity and Coverage",
journal = j-TODS,
volume = "40",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699499",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Recently, result diversification has attracted a lot
of attention as a means to improve the quality of
results retrieved by user queries. In this article, we
introduce a novel definition of diversity called DisC
diversity. Given a tuning parameter $r$, which we call
radius, we consider two items to be similar if their
distance is smaller than or equal to $r$. A DisC
diverse subset of a result contains items such that
each item in the result is represented by a similar
item in the diverse subset and the items in the diverse
subset are dissimilar to each other. We show that
locating a minimum DisC diverse subset is an NP-hard
problem and provide algorithms for its approximation.
We extend our definition to the multiple radii case,
where each item is associated with a different radius
based on its importance, relevance, or other factors.
We also propose adapting DisC diverse subsets to a
different degree of diversification by adjusting $r$,
that is, increasing the radius (or zooming-out) and
decreasing the radius (or zooming-in). We present
efficient implementations of our algorithms based on
the $M$-tree, a spatial index structure, and
experimentally evaluate their performance.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Benedikt:2015:ASA,
author = "Michael Benedikt and Pierre Bourhis and Clemens Ley",
title = "Analysis of Schemas with Access Restrictions",
journal = j-TODS,
volume = "40",
number = "1",
pages = "5:1--5:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699500",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study verification of systems whose transitions
consist of accesses to a Web-based data source. An
access is a lookup on a relation within a relational
database, fixing values for a set of positions in the
relation. For example, a transition can represent
access to a Web form, where the user is restricted to
filling in values for a particular set of fields. We
look at verifying properties of a schema describing the
possible accesses of such a system. We present a
language where one can describe the properties of an
access path and also specify additional restrictions on
accesses that are enforced by the schema. Our main
property language, AccessLTL, is based on a first-order
extension of linear-time temporal logic, interpreting
access paths as sequences of relational structures. We
also present a lower-level automaton model, A-automata,
into which AccessLTL specifications can compile. We
show that AccessLTL and A-automata can express static
analysis problems related to ``querying with limited
access patterns'' that have been studied in the
database literature in the past, such as whether an
access is relevant to answering a query and whether two
queries are equivalent in the accessible data they can
return. We prove decidability and complexity results
for several restrictions and variants of AccessLTL and
explain which properties of paths can be expressed in
each restriction.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Athanassoulis:2015:OUD,
author = "Manos Athanassoulis and Shimin Chen and Anastasia
Ailamaki and Philip B. Gibbons and Radu Stoica",
title = "Online Updates on Data Warehouses via Judicious Use of
Solid-State Storage",
journal = j-TODS,
volume = "40",
number = "1",
pages = "6:1--6:??",
month = mar,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699484",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 26 05:54:21 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data warehouses have been traditionally optimized for
read-only query performance, allowing only offline
updates at night, essentially trading off data
freshness for performance. The need for $ 24 \times 7 $
operations in global markets and the rise of online and
other quickly reacting businesses make concurrent
online updates increasingly desirable. Unfortunately,
state-of-the-art approaches fall short of supporting
fast analysis queries over fresh data. The conventional
approach of performing updates in place can
dramatically slow down query performance, while prior
proposals using differential updates either require
large in-memory buffers or may incur significant update
migration cost. This article presents a novel approach
for supporting online updates in data warehouses that
overcomes the limitations of prior approaches by making
judicious use of available SSDs to cache incoming
updates. We model the problem of query processing with
differential updates as a type of outer join between
the data residing on disks and the updates residing on
SSDs. We present MaSM algorithms for performing such
joins and periodic migrations, with small memory
footprints, low query overhead, low SSD writes,
efficient in-place migration of updates, and correct
ACID support. We present detailed modeling of the
proposed approach, and provide proofs regarding the
fundamental properties of the MaSM algorithms. Our
experimentation shows that MaSM incurs only up to 7\%
overhead both on synthetic range scans (varying range
size from 4KB to 100GB) and in a TPC-H query replay
study, while also increasing the update throughput by
orders of magnitude.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2015:EBT,
author = "Christian S. Jensen",
title = "Editorial: The Best of Two Worlds --- Present Your
{TODS} Paper at {SIGMOD}",
journal = j-TODS,
volume = "40",
number = "2",
pages = "7:1--7:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2770931",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Beedkar:2015:CGS,
author = "Kaustubh Beedkar and Klaus Berberich and Rainer
Gemulla and Iris Miliaraki",
title = "Closing the Gap: Sequence Mining at Scale",
journal = j-TODS,
volume = "40",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2757217",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Frequent sequence mining is one of the fundamental
building blocks in data mining. While the problem has
been extensively studied, few of the available
techniques are sufficiently scalable to handle datasets
with billions of sequences; such large-scale datasets
arise, for instance, in text mining and session
analysis. In this article, we propose MG-FSM, a
scalable algorithm for frequent sequence mining on
MapReduce. MG-FSM can handle so-called ``gap
constraints'', which can be used to limit the output to
a controlled set of frequent sequences. Both positional
and temporal gap constraints, as well as appropriate
maximality and closedness constraints, are supported.
At its heart, MG-FSM partitions the input database in a
way that allows us to mine each partition independently
using any existing frequent sequence mining algorithm.
We introduce the notion of $ \omega $-equivalency,
which is a generalization of the notion of a
``projected database'' used by many frequent pattern
mining algorithms. We also present a number of
optimization techniques that minimize partition size,
and therefore computational and communication costs,
while still maintaining correctness. Our experimental
study in the contexts of text mining and session
analysis suggests that MG-FSM is significantly more
efficient and scalable than alternative approaches.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ameloot:2015:DDF,
author = "Tom J. Ameloot",
title = "Deciding Determinism with Fairness for Simple
Transducer Networks",
journal = j-TODS,
volume = "40",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2757215",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A distributed database system often operates in an
asynchronous communication model where messages can be
arbitrarily delayed. This communication model causes
nondeterministic effects like unpredictable arrival
orders of messages. Nonetheless, in general we want the
distributed system to be deterministic; the system
should produce the same output despite the
nondeterministic effects on messages. Previously, two
interpretations of determinism have been proposed. The
first says that all infinite fair computation traces
produce the same output. The second interpretation is a
confluence notion, saying that all finite computation
traces can still be extended to produce the same
output. A decidability result for the confluence notion
was previously obtained for so-called simple transducer
networks, a model from the field of declarative
networking. In the current article, we also present a
decidability result for simple transducer networks, but
this time for the first interpretation of determinism,
with infinite fair computation traces. We also compare
the expressivity of simple transducer networks under
both interpretations.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Nagendra:2015:EPS,
author = "Mithila Nagendra and K. Sel{\c{c}}uk Candan",
title = "Efficient Processing of Skyline-Join Queries over
Multiple Data Sources",
journal = j-TODS,
volume = "40",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699483",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Efficient processing of skyline queries has been an
area of growing interest. Many of the earlier skyline
techniques assumed that the skyline query is applied to
a single data table. Naturally, these algorithms were
not suitable for many applications in which the skyline
query may involve attributes belonging to multiple data
sources. In other words, if the data used in the
skyline query are stored in multiple tables, then join
operations would be required before the skyline can be
searched. The task of computing skylines on multiple
data sources has been coined as the skyline-join
problem and various skyline-join algorithms have been
proposed. However, the current proposals suffer several
drawbacks: they often need to scan the input tables
exhaustively in order to obtain the set of skyline-join
results; moreover, the pruning techniques employed to
eliminate the tuples are largely based on expensive
pairwise tuple-to-tuple comparisons. In this article,
we aim to address these shortcomings by proposing two
novel skyline-join algorithms, namely skyline-sensitive
join (S$^2$ J) and symmetric skyline-sensitive join
(S$^3$ J), to process skyline queries over two data
sources. Our approaches compute the results using a
novel layer/region pruning technique ( LR-pruning )
that prunes the join space in blocks as opposed to
individual data points, thereby avoiding excessive
pairwise point-to-point dominance checks. Furthermore,
the S$^3$ J algorithm utilizes an early stopping
condition in order to successfully compute the skyline
results by accessing only a subset of the input tables.
In addition to S$^2$ J and S$^3$ J, we also propose the
S$^2$ J-M and S$^3$ J-M algorithms. These algorithms
extend S$^2$ J's and S$^3$ J's two-way skyline-join
ability to efficiently process skyline-join queries
over more than two data sources. S$^2$ J-M and S$^3$
J-M leverage the extended concept of LR-pruning, called
M -way LR-pruning, to compute multi-way skyline-joins
in which more than two data sources are integrated
during skyline processing. We report extensive
experimental results that confirm the advantages of the
proposed algorithms over state-of-the-art skyline-join
techniques.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yuan:2015:OBL,
author = "Ganzhao Yuan and Zhenjie Zhang and Marianne Winslett
and Xiaokui Xiao and Yin Yang and Zhifeng Hao",
title = "Optimizing Batch Linear Queries under Exact and
Approximate Differential Privacy",
journal = j-TODS,
volume = "40",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2699501",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Differential privacy is a promising privacy-preserving
paradigm for statistical query processing over
sensitive data. It works by injecting random noise into
each query result such that it is provably hard for the
adversary to infer the presence or absence of any
individual record from the published noisy results. The
main objective in differentially private query
processing is to maximize the accuracy of the query
results while satisfying the privacy guarantees.
Previous work, notably Li et al. [2010], has suggested
that, with an appropriate strategy, processing a batch
of correlated queries as a whole achieves considerably
higher accuracy than answering them individually.
However, to our knowledge there is currently no
practical solution to find such a strategy for an
arbitrary query batch; existing methods either return
strategies of poor quality (often worse than naive
methods) or require prohibitively expensive
computations for even moderately large domains.
Motivated by this, we propose a low-rank mechanism
(LRM), the first practical differentially private
technique for answering batch linear queries with high
accuracy. LRM works for both exact (i.e., $ \epsilon
$-) and approximate (i.e., ($ \epsilon $, $ \delta $)-)
differential privacy definitions. We derive the utility
guarantees of LRM and provide guidance on how to set
the privacy parameters, given the user's utility
expectation. Extensive experiments using real data
demonstrate that our proposed method consistently
outperforms state-of-the-art query processing solutions
under differential privacy, by large margins.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Termehchy:2015:CEC,
author = "Arash Termehchy and Ali Vakilian and Yodsawalai
Chodpathumwan and Marianne Winslett",
title = "Cost-Effective Conceptual Design for Information
Extraction",
journal = j-TODS,
volume = "40",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2716321",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "It is well established that extracting and annotating
occurrences of entities in a collection of unstructured
text documents with their concepts improves the
effectiveness of answering queries over the collection.
However, it is very resource intensive to create and
maintain large annotated collections. Since the
available resources of an enterprise are limited and/or
its users may have urgent information needs, it may
have to select only a subset of relevant concepts for
extraction and annotation. We call this subset a
conceptual design for the annotated collection. In this
article, we introduce and formally define the problem
of cost-effective conceptual design where, given a
collection, a set of relevant concepts, and a fixed
budget, one likes to find a conceptual design that most
improves the effectiveness of answering queries over
the collection. We provide efficient algorithms for
special cases of the problem and prove it is generally
NP-hard in the number of relevant concepts. We propose
three efficient approximations to solve the problem: a
greedy algorithm, an approximate popularity
maximization (APM for short), and approximate
annotation-benefit maximization (AAM for short). We
show that, if there are no constraints regrading the
overlap of concepts, APM is a fully polynomial time
approximation scheme. We also prove that if the
relevant concepts are mutually exclusive, the greedy
algorithm delivers a constant approximation ratio if
the concepts are equally costly, APM has a constant
approximation ratio, and AAM is a fully polynomial-time
approximation scheme. Our empirical results using a
Wikipedia collection and a search engine query log
validate the proposed formalization of the problem and
show that APM and AAM efficiently compute conceptual
designs. They also indicate that, in general, APM
delivers the optimal conceptual designs if the relevant
concepts are not mutually exclusive. Also, if the
relevant concepts are mutually exclusive, the
conceptual designs delivered by AAM improve the
effectiveness of answering queries over the collection
more than the solutions provided by APM.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cao:2015:EPS,
author = "Xin Cao and Gao Cong and Tao Guo and Christian S.
Jensen and Beng Chin Ooi",
title = "Efficient Processing of Spatial Group Keyword
Queries",
journal = j-TODS,
volume = "40",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2772600",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "With the proliferation of geo-positioning and
geo-tagging techniques, spatio-textual objects that
possess both a geographical location and a textual
description are gaining in prevalence, and spatial
keyword queries that exploit both location and textual
description are gaining in prominence. However, the
queries studied so far generally focus on finding
individual objects that each satisfy a query rather
than finding groups of objects where the objects in a
group together satisfy a query. We define the problem
of retrieving a group of spatio-textual objects such
that the group's keywords cover the query's keywords
and such that the objects are nearest to the query
location and have the smallest inter-object distances.
Specifically, we study three instantiations of this
problem, all of which are NP-hard. We devise exact
solutions as well as approximate solutions with
provable approximation bounds to the problems. In
addition, we solve the problems of retrieving top- k
groups of three instantiations, and study a weighted
version of the problem that incorporates object
weights. We present empirical studies that offer
insight into the efficiency of the solutions, as well
as the accuracy of the approximate solutions.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Vincent:2015:TCD,
author = "Millist Vincent and Jixue Liu and Hong-Cheu Liu and
Sebastian Link",
title = "Technical Correspondence: {``Differential
Dependencies: Reasoning and Discovery''} Revisited",
journal = j-TODS,
volume = "40",
number = "2",
pages = "14:1--14:??",
month = jun,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2757214",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 7 09:22:19 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Song:2011:DDR} and response
\cite{Song:2017:RDD}.",
abstract = "To address the frequently occurring situation where
data is inexact or imprecise, a number of extensions to
the classical notion of a functional dependency (FD)
integrity constraint have been proposed in recent
years. One of these extensions is the notion of a
differential dependency (DD), introduced in the recent
article ``Differential Dependencies: Reasoning and
Discovery'' by Song and Chen in the March 2011 edition
of this journal. A DD generalises the notion of an FD
by requiring only that the values of the attribute from
the RHS of the DD satisfy a distance constraint
whenever the values of attributes from the LHS of the
DD satisfy a distance constraint. In contrast, an FD
requires that the values from the attributes in the RHS
of an FD be equal whenever the values of the attributes
from the LHS of the FD are equal. The article
``Differential Dependencies: Reasoning and Discovery''
investigated a number of aspects of DDs, the most
important of which, since they form the basis for the
other topics investigated, were the consistency problem
(determining whether there exists a relation instance
that satisfies a set of DDs) and the implication
problem (determining whether a set of DDs logically
implies another DD). Concerning these problems, a
number of results were claimed in ``Differential
Dependencies: Reasoning and Discovery''. In this
article we conduct a detailed analysis of the
correctness of these results. The outcomes of our
analysis are that, for almost every claimed result, we
show there are either fundamental errors in the proof
or the result is false. For some of the claimed results
we are able to provide corrected proofs, but for other
results their correctness remains open.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lu:2015:BQA,
author = "Jiaheng Lu and Chunbin Lin and Wei Wang and Chen Li
and Xiaokui Xiao",
title = "Boosting the Quality of Approximate String Matching by
Synonyms",
journal = j-TODS,
volume = "40",
number = "3",
pages = "15:1--15:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818177",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A string-similarity measure quantifies the similarity
between two text strings for approximate string
matching or comparison. For example, the strings
``Sam'' and ``Samuel'' can be considered to be similar.
Most existing work that computes the similarity of two
strings only considers syntactic similarities, for
example, number of common words or $q$-grams. While
this is indeed an indicator of similarity, there are
many important cases where syntactically-different
strings can represent the same real-world object. For
example, ``Bill'' is a short form of ``William,'' and
``Database Management Systems'' can be abbreviated as
``DBMS.'' Given a collection of predefined synonyms,
the purpose of this article is to explore such existing
knowledge to effectively evaluate the similarity
between two strings and efficiently perform similarity
searches and joins, thereby boosting the quality of
approximate string matching. In particular, we first
present an expansion-based framework to measure string
similarities efficiently while considering synonyms. We
then study efficient algorithms for similarity searches
and joins by proposing two novel indexes, called
SI-trees and QP-trees, which combine
signature-filtering and length-filtering strategies. In
order to improve the efficiency of our algorithms, we
develop an estimator to estimate the size of candidates
to enable an online selection of signature filters.
This estimator provides strong low-error,
high-confidence guarantees while requiring only
logarithmic space and time costs, thus making our
method attractive both in theory and in practice.
Finally, the experimental results from a comprehensive
study of the algorithms with three real datasets verify
the effectiveness and efficiency of our approaches.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Rusu:2015:WDA,
author = "Florin Rusu and Zixuan Zhuang and Mingxi Wu and Chris
Jermaine",
title = "Workload-Driven Antijoin Cardinality Estimation",
journal = j-TODS,
volume = "40",
number = "3",
pages = "16:1--16:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818178",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Antijoin cardinality estimation is among a handful of
problems that has eluded accurate efficient solutions
amenable to implementation in relational query
optimizers. Given the widespread use of antijoin and
subset-based queries in analytical workloads and the
extensive research targeted at join cardinality
estimation---a seemingly related problem---the lack of
adequate solutions for antijoin cardinality estimation
is intriguing. In this article, we introduce a novel
sampling-based estimator for antijoin cardinality that
(unlike existent estimators) provides sufficient
accuracy and efficiency to be implemented in a query
optimizer. The proposed estimator incorporates three
novel ideas. First, we use prior workload information
when learning a mixture superpopulation model of the
data offline. Second, we design a Bayesian statistics
framework that updates the superpopulation model
according to the live queries, thus allowing the
estimator to adapt dynamically to the online workload.
Third, we develop an efficient algorithm for sampling
from a hypergeometric distribution in order to generate
Monte Carlo trials, without explicitly instantiating
either the population or the sample. When put together,
these ideas form the basis of an efficient antijoin
cardinality estimator satisfying the strict
requirements of a query optimizer, as shown by the
extensive experimental results over
synthetically-generated as well as massive TPC-H
data.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chen:2015:OLQ,
author = "Zitong Chen and Yubao Liu and Raymond Chi-Wing Wong
and Jiamin Xiong and Ganglin Mai and Cheng Long",
title = "Optimal Location Queries in Road Networks",
journal = j-TODS,
volume = "40",
number = "3",
pages = "17:1--17:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818179",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we study an optimal location query
based on a road network. Specifically, given a road
network containing clients and servers, an optimal
location query finds a location on the road network
such that when a new server is set up at this location,
a certain cost function computed based on the clients
and servers (including the new server) is optimized.
Two types of cost functions, namely, MinMax and MaxSum,
have been used for this query. The optimal location
query problem with MinMax as the cost function is
called the MinMax query, which finds a location for
setting up a new server such that the maximum cost of a
client being served by his/her closest server is
minimized. The optimal location query problem with
MaxSum as the cost function is called the MaxSum query,
which finds a location for setting up a new server such
that the sum of the weights of clients attracted by the
new server is maximized. The MinMax query and the
MaxSum query correspond to two types of optimal
location query with the objectives defined from the
clients' perspective and from the new server's
perspective, respectively. Unfortunately, the existing
solutions for the optimal query problem are not
efficient. In this article, we propose an efficient
algorithm, namely, MinMax-Alg ( MaxSum-Alg ), for the
MinMax (MaxSum) query, which is based on a novel idea
of nearest location component. We also discuss two
extensions of the optimal location query, namely, the
optimal multiple-location query and the optimal
location query on a 3D road network. Extensive
experiments were conducted, showing that our algorithms
are faster than the state of the art by at least an
order of magnitude on large real benchmark datasets.
For example, in our largest real datasets, the state of
the art ran for more than 10 (12) hours while our
algorithm ran within 3 (2) minutes only for the MinMax
(MaxSum) query, that is, our algorithm ran at least 200
(600) times faster than the state of the art.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Rietveld:2015:RLD,
author = "Kristian F. D. Rietveld and Harry A. G. Wijshoff",
title = "Reducing Layered Database Applications to their
Essence through Vertical Integration",
journal = j-TODS,
volume = "40",
number = "3",
pages = "18:1--18:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818180",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In the last decade, improvements on single-core
performance of CPUs has stagnated. Consequently,
methods for the development and optimization of
software for these platforms have to be reconsidered.
Software must be optimized such that the available
single-core performance is exploited more effectively.
This can be achieved by reducing the number of
instructions that need to be executed. In this article,
we show that layered database applications execute many
redundant, nonessential, instructions that can be
eliminated without affecting the course of execution
and the output of the application. This elimination is
performed using a vertical integration process which
breaks down the different layers of layered database
applications. By doing so, applications are being
reduced to their essence, and as a consequence,
transformations can be carried out that affect both the
application code and the data access code which were
not possible before. We show that this vertical
integration process can be fully automated and, as
such, be integrated in an operational workflow.
Experimental evaluation of this approach shows that up
to 95\% of the instructions can be eliminated. The
reduction of instructions leads to a more efficient use
of the available hardware resources. This results in
greatly improved performance of the application and a
significant reduction in energy consumption.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cheng:2015:SDM,
author = "Yu Cheng and Florin Rusu",
title = "{SCANRAW}: a Database Meta-Operator for Parallel
In-Situ Processing and Loading",
journal = j-TODS,
volume = "40",
number = "3",
pages = "19:1--19:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818181",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Traditional databases incur a significant
data-to-query delay due to the requirement to load data
inside the system before querying. Since this is not
acceptable in many domains generating massive amounts
of raw data (e.g., genomics), databases are entirely
discarded. External tables, on the other hand, provide
instant SQL querying over raw files. Their performance
across a query workload is limited though by the speed
of repeated full scans, tokenizing, and parsing of the
entire file. In this article, we propose SCANRAW, a
novel database meta-operator for in-situ processing
over raw files that integrates data loading and
external tables seamlessly, while preserving their
advantages: optimal performance across a query workload
and zero time-to-query. We decompose loading and
external table processing into atomic stages in order
to identify common functionality. We analyze
alternative implementations and discuss possible
optimizations for each stage. Our major contribution is
a parallel superscalar pipeline implementation that
allows SCANRAW to take advantage of the current many-
and multicore processors by overlapping the execution
of independent stages. Moreover, SCANRAW overlaps query
processing with loading by speculatively using the
additional I/O bandwidth arising during the conversion
process for storing data into the database, such that
subsequent queries execute faster. As a result, SCANRAW
makes intelligent use of the available system
resources---CPU cycles and I/O bandwidth---by switching
dynamically between tasks to ensure that optimal
performance is achieved. We implement SCANRAW in a
state-of-the-art database system and evaluate its
performance across a variety of synthetic and
real-world datasets. Our results show that SCANRAW with
speculative loading achieves the best-possible
performance for a query sequence at any point in the
processing. Moreover, SCANRAW maximizes resource
utilization for the entire workload execution while
speculatively loading data and without interfering with
normal query processing.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Parchas:2015:UGP,
author = "Panos Parchas and Francesco Gullo and Dimitris
Papadias and Francesco Bonchi",
title = "Uncertain Graph Processing through Representative
Instances",
journal = j-TODS,
volume = "40",
number = "3",
pages = "20:1--20:??",
month = oct,
year = "2015",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818182",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Oct 24 11:43:27 MDT 2015",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Data in several applications can be represented as an
uncertain graph whose edges are labeled with a
probability of existence. Exact query processing on
uncertain graphs is prohibitive for most applications,
as it involves evaluation over an exponential number of
instantiations. Thus, typical approaches employ
Monte-Carlo sampling, which (i) draws a number of
possible graphs (samples), (ii) evaluates the query on
each of them, and (iii) aggregates the individual
answers to generate the final result. However, this
approach can also be extremely time consuming for large
uncertain graphs commonly found in practice. To
facilitate efficiency, we study the problem of
extracting a single representative instance from an
uncertain graph. Conventional processing techniques can
then be applied on this representative to closely
approximate the result on the original graph. In order
to maintain data utility, the representative instance
should preserve structural characteristics of the
uncertain graph. We start with representatives that
capture the expected vertex degrees, as this is a
fundamental property of the graph topology. We then
generalize the notion of vertex degree to the concept
of n -clique cardinality, that is, the number of
cliques of size n that contain a vertex. For the first
problem, we propose two methods: Average Degree
Rewiring (ADR), which is based on random edge rewiring,
and Approximate B-Matching (ABM), which applies graph
matching techniques. For the second problem, we develop
a greedy approach and a game-theoretic framework. We
experimentally demonstrate, with real uncertain graphs,
that indeed the representative instances can be used to
answer, efficiently and accurately, queries based on
several metrics such as shortest path distance,
clustering coefficient, and betweenness centrality.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Ameloot:2016:WFM,
author = "Tom J. Ameloot and Bas Ketsman and Frank Neven and
Daniel Zinn",
title = "Weaker Forms of Monotonicity for Declarative
Networking: a More Fine-Grained Answer to the
{CALM}-Conjecture",
journal = j-TODS,
volume = "40",
number = "4",
pages = "21:1--21:??",
month = jan,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2809784",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jan 21 12:35:53 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The CALM-conjecture, first stated by Hellerstein
[2010] and proved in its revised form by Ameloot et al.
[2013] within the framework of relational transducer
networks, asserts that a query has a coordination-free
execution strategy if and only if the query is
monotone. Zinn et al. [2012] extended the framework of
relational transducer networks to allow for specific
data distribution strategies and showed that the
nonmonotone win-move query is coordination-free for
domain-guided data distributions. In this article, we
extend the story by equating increasingly larger
classes of coordination-free computations with
increasingly weaker forms of monotonicity and present
explicit Datalog variants that capture each of these
classes. One such fragment is based on stratified
Datalog where rules are required to be connected with
the exception of the last stratum. In addition, we
characterize coordination-freeness as those
computations that do not require knowledge about all
other nodes in the network, and therefore, can not
globally coordinate. The results in this article can be
interpreted as a more fine-grained answer to the
CALM-conjecture.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bonifati:2016:LJQ,
author = "Angela Bonifati and Radu Ciucanu and S{\l}awek
Staworko",
title = "Learning Join Queries from User Examples",
journal = j-TODS,
volume = "40",
number = "4",
pages = "24:1--24:??",
month = jan,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2818637",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jan 21 12:35:53 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We investigate the problem of learning join queries
from user examples. The user is presented with a set of
candidate tuples and is asked to label them as positive
or negative examples, depending on whether or not she
would like the tuples as part of the join result. The
goal is to quickly infer an arbitrary n -ary join
predicate across an arbitrary number m of relations
while keeping the number of user interactions as
minimal as possible. We assume no prior knowledge of
the integrity constraints across the involved
relations. Inferring the join predicate across multiple
relations when the referential constraints are unknown
may occur in several applications, such as data
integration, reverse engineering of database queries,
and schema inference. In such scenarios, the number of
tuples involved in the join is typically large. We
introduce a set of strategies that let us inspect the
search space and aggressively prune what we call
uninformative tuples, and we directly present to the
user the informative ones---that is, those that allow
the user to quickly find the goal query she has in
mind. In this article, we focus on the inference of
joins with equality predicates and also allow
disjunctive join predicates and projection in the
queries. We precisely characterize the frontier between
tractability and intractability for the following
problems of interest in these settings: consistency
checking, learnability, and deciding the
informativeness of a tuple. Next, we propose several
strategies for presenting tuples to the user in a given
order that allows minimization of the number of
interactions. We show the efficiency of our approach
through an experimental study on both benchmark and
synthetic datasets.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yang:2016:NFI,
author = "Xiaochun Yang and Tao Qiu and Bin Wang and Baihua
Zheng and Yaoshu Wang and Chen Li",
title = "Negative Factor: Improving Regular-Expression Matching
in Strings",
journal = j-TODS,
volume = "40",
number = "4",
pages = "25:1--25:46",
month = jan,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2847525",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Jan 21 12:35:53 MST 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The problem of finding matches of a regular expression
(RE) on a string exists in many applications, such as
text editing, biosequence search, and shell commands.
Existing techniques first identify candidates using
substrings in the RE, then verify each of them using an
automaton. These techniques become inefficient when
there are many candidate occurrences that need to be
verified. In this article, we propose a novel technique
that prunes false negatives by utilizing negative
factors, which are substrings that cannot appear in an
answer. A main advantage of the technique is that it
can be integrated with many existing algorithms to
improve their efficiency significantly. We present a
detailed description of this technique. We develop an
efficient algorithm that utilizes negative factors to
prune candidates, then improve it by using bit
operations to process negative factors in parallel. We
show that negative factors, when used with necessary
factors (substrings that must appear in each answer),
can achieve much better pruning power. We analyze the
large number of negative factors, and develop an
algorithm for finding a small number of high-quality
negative factors. We conducted a thorough experimental
study of this technique on real datasets, including DNA
sequences, proteins, and text documents, and show
significant performance improvement of the
state-of-the-art tools by an order of magnitude.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhou:2016:FRW,
author = "Zhuojie Zhou and Nan Zhang and Zhiguo Gong and Gautam
Das",
title = "Faster Random Walks by Rewiring Online Social Networks
On-the-Fly",
journal = j-TODS,
volume = "40",
number = "4",
pages = "26:1--26:??",
month = feb,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2847526",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many online social networks feature restrictive web
interfaces that only allow the query of a user's local
neighborhood. To enable analytics over such an online
social network through its web interface, many recent
efforts use Markov Chain Monte Carlo (MCMC) methods
such as random walks to sample users in the social
network and thereby support analytics based on the
samples. The problem with such an approach, however, is
the large amount of queries often required for a random
walk to converge to a desired (stationary) sampling
distribution. In this article, we consider a novel
problem of enabling a faster random walk over online
social networks by ``rewiring'' the social network
on-the-fly. Specifically, we develop a Modified
TOpology Sampling (MTO-Sampling) scheme that, by using
only information exposed by the restrictive web
interface, constructs a ``virtual''
random-walk-friendly overlay topology of the social
network while performing a random walk and ensures that
the random walk follows the modified overlay topology
rather than the original one. We describe in this
article instantiations of MTO-Sampling for various
types of random walks, such as Simple Random Walk
(MTO-SRW), Metropolis--Hastings Random Walk (MTO-MHRW),
and General Random Walk (MTO-GRW). We not only rigidly
prove that MTO-Sampling improves the efficiency of
sampling, but we also demonstrate the significance of
such improvement through experiments on real-world
online social networks such as Google Plus, Epinion,
Facebook, etc.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2016:EUE,
author = "Christian S. Jensen",
title = "Editorial: Updates to the Editorial Board",
journal = j-TODS,
volume = "41",
number = "1",
pages = "1:1--1:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2893581",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "1e",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Libkin:2016:STV,
author = "Leonid Libkin",
title = "{SQL}'s Three-Valued Logic and Certain Answers",
journal = j-TODS,
volume = "41",
number = "1",
pages = "1:1--1:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877206",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The goal of the article is to bridge the difference
between theoretical and practical approaches to
answering queries over databases with nulls.
Theoretical research has long ago identified the notion
of correctness of query answering over incomplete data:
one needs to find certain answers, which are true
regardless of how incomplete information is
interpreted. This serves as the notion of correctness
of query answering, but carries a huge complexity tag.
In practice, on the other hand, query answering must be
very efficient, and to achieve this, SQL uses
three-valued logic for evaluating queries on databases
with nulls. Due to the complexity mismatch, the two
approaches cannot coincide, but perhaps they are
related in some way. For instance, does SQL always
produce answers we can be certain about? This is not
so: SQL's and certain answers semantics could be
totally unrelated. We show, however, that a slight
modification of the three-valued semantics for
relational calculus queries can provide the required
certainty guarantees. The key point of the new scheme
is to fully utilize the three-valued semantics, and
classify answers not into certain or noncertain, as was
done before, but rather into certainly true, certainly
false, or unknown. This yields relatively small changes
to the evaluation procedure, which we consider at the
level of both declarative (relational calculus) and
procedural (relational algebra) queries. These new
evaluation procedures give us certainty guarantees even
for queries returning tuples with null values.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhang:2016:MOF,
author = "Ce Zhang and Arun Kumar and Christopher R{\'e}",
title = "Materialization Optimizations for Feature Selection
Workloads",
journal = j-TODS,
volume = "41",
number = "1",
pages = "2:1--2:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877204",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "There is an arms race in the data management industry
to support statistical analytics. Feature selection,
the process of selecting a feature set that will be
used to build a statistical model, is widely regarded
as the most critical step of statistical analytics.
Thus, we argue that managing the feature selection
process is a pressing data management challenge. We
study this challenge by describing a feature selection
language and a supporting prototype system that builds
on top of current industrial R-integration layers. From
our interactions with analysts, we learned that feature
selection is an interactive human-in-the-loop process,
which means that feature selection workloads are rife
with reuse opportunities. Thus, we study how to
materialize portions of this computation using not only
classical database materialization optimizations but
also methods that have not previously been used in
database optimization, including structural
decomposition methods (like QR factorization) and
warmstart. These new methods have no analogue in
traditional SQL systems, but they may be interesting
for array and scientific database applications. On a
diverse set of datasets and programs, we find that
traditional database-style approaches that ignore these
new opportunities are more than two orders of magnitude
slower than an optimal plan in this new trade-off space
across multiple R backends. Furthermore, we show that
it is possible to build a simple cost-based optimizer
to automatically select a near-optimal execution plan
for feature selection.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Olteanu:2016:EFP,
author = "Dan Olteanu and Sebastiaan J. {Van Schaik}",
title = "{ENFrame}: a Framework for Processing Probabilistic
Data",
journal = j-TODS,
volume = "41",
number = "1",
pages = "3:1--3:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877205",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article introduces ENFrame, a framework for
processing probabilistic data. Using ENFrame, users can
write programs in a fragment of Python with constructs
such as loops, list comprehension, aggregate operations
on lists, and calls to external database engines.
Programs are then interpreted probabilistically by
ENFrame. We exemplify ENFrame on three clustering
algorithms ( k -means, k -medoids, and Markov
clustering) and one classification algorithm ( k
-nearest-neighbour). A key component of ENFrame is an
event language to succinctly encode correlations, trace
the computation of user programs, and allow for
computation of discrete probability distributions for
program variables. We propose a family of sequential
and concurrent, exact, and approximate algorithms for
computing the probability of interconnected events.
Experiments with k -medoids clustering and k
-nearest-neighbour show orders-of-magnitude
improvements of exact processing using ENFrame over
na{\"\i}ve processing in each possible world, of
approximate over exact, and of concurrent over
sequential processing.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fink:2016:DQN,
author = "Robert Fink and Dan Olteanu",
title = "Dichotomies for Queries with Negation in Probabilistic
Databases",
journal = j-TODS,
volume = "41",
number = "1",
pages = "4:1--4:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877203",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article charts the tractability frontier of two
classes of relational algebra queries in
tuple-independent probabilistic databases. The first
class consists of queries with join, projection,
selection, and negation but without repeating relation
symbols and union. The second class consists of
quantified queries that express the following binary
relationships among sets of entities: set division, set
inclusion, set equivalence, and set incomparability.
Quantified queries are expressible in relational
algebra using join, projection, nested negation, and
repeating relation symbols. Each query in the two
classes has either polynomial-time or \#P-hard data
complexity and the tractable queries can be recognised
efficiently. Our result for the first query class
extends a known dichotomy for conjunctive queries
without self-joins to such queries with negation. For
quantified queries, their tractability is sensitive to
their outermost projection operator: They are tractable
if no attribute representing set identifiers is
projected away and \#P-hard otherwise.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhou:2016:BEQ,
author = "Xiaoling Zhou and Jianbin Qin and Chuan Xiao and Wei
Wang and Xuemin Lin and Yoshiharu Ishikawa",
title = "{BEVA}: an Efficient Query Processing Algorithm for
Error-Tolerant Autocompletion",
journal = j-TODS,
volume = "41",
number = "1",
pages = "5:1--5:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877201",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Query autocompletion has become a standard feature in
many search applications, especially for search
engines. A recent trend is to support the
error-tolerant autocompletion, which increases the
usability significantly by matching prefixes of
database strings and allowing a small number of errors.
In this article, we systematically study the query
processing problem for error-tolerant autocompletion
with a given edit distance threshold. We propose a
general framework that encompasses existing methods and
characterizes different classes of algorithms and the
minimum amount of information they need to maintain
under different constraints. We then propose a novel
evaluation strategy that achieves the minimum active
node size by eliminating ancestor-descendant
relationships among active nodes entirely. In addition,
we characterize the essence of edit distance
computation by a novel data structure named edit vector
automaton (EVA). It enables us to compute new active
nodes and their associated states efficiently by table
lookups. In order to support large distance thresholds,
we devise a partitioning scheme to reduce the size and
construction cost of the automaton, which results in
the universal partitioned EVA (UPEVA) to handle
arbitrarily large thresholds. Our extensive evaluation
demonstrates that our proposed method outperforms
existing approaches in both space and time
efficiencies.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fagin:2016:DCI,
author = "Ronald Fagin and Benny Kimelfeld and Frederick Reiss
and Stijn Vansummeren",
title = "Declarative Cleaning of Inconsistencies in Information
Extraction",
journal = j-TODS,
volume = "41",
number = "1",
pages = "6:1--6:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877202",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The population of a predefined relational schema from
textual content, commonly known as Information
Extraction (IE), is a pervasive task in contemporary
computational challenges associated with Big Data.
Since the textual content varies widely in nature and
structure (from machine logs to informal natural
language), it is notoriously difficult to write IE
programs that unambiguously extract the sought
information. For example, during extraction, an IE
program could annotate a substring as both an address
and a person name. When this happens, the extracted
information is said to be inconsistent, and some way of
removing inconsistencies is crucial to compute the
final output. Industrial-strength IE systems like GATE
and IBM SystemT therefore provide a built-in collection
of cleaning operations to remove inconsistencies from
extracted relations. These operations, however, are
collected in an ad hoc fashion through use cases.
Ideally, we would like to allow IE developers to
declare their own policies. But existing cleaning
operations are defined in an algorithmic way, and hence
it is not clear how to extend the built-in operations
without requiring low-level coding of internal or
external functions. We embark on the establishment of a
framework for declarative cleaning of inconsistencies
in IE through principles of database theory.
Specifically, building upon the formalism of document
spanners for IE, we adopt the concept of prioritized
repairs, which has been recently proposed as an
extension of the traditional database repairs to
incorporate priorities among conflicting facts. We show
that our framework captures the popular cleaning
policies, as well as the POSIX semantics for extraction
through regular expressions. We explore the problem of
determining whether a cleaning declaration is
unambiguous (i.e., always results in a single repair)
and whether it increases the expressive power of the
extraction language. We give both positive and negative
results, some of which are general and some of which
apply to policies used in practice.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Pham:2016:ISS,
author = "Huy Pham and Cyrus Shahabi and Yan Liu",
title = "Inferring Social Strength from Spatiotemporal Data",
journal = j-TODS,
volume = "41",
number = "1",
pages = "7:1--7:??",
month = apr,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2877200",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 20 11:19:20 MDT 2016",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The advent of geolocation technologies has generated
unprecedented rich datasets of people's location
information at a very high fidelity. These location
datasets can be used to study human behavior; for
example, social studies have shown that people who are
seen together frequently at the same place and same
time are most probably socially related. In this
article, we are interested in inferring these social
connections by analyzing people's location information;
this is useful in a variety of application domains,
from sales and marketing to intelligence analysis. In
particular, we propose an entropy-based model (EBM)
that not only infers social connections but also
estimates the strength of social connections by
analyzing people's co-occurrences in space and time. We
examine two independent methods: diversity and weighted
frequency, through which co-occurrences contribute to
the strength of a social connection. In addition, we
take the characteristics of each location into
consideration in order to compensate for cases where
only limited location information is available. We also
study the role of location semantics in improving our
computation of social strength. We develop a parallel
implementation of our algorithm using MapReduce to
create a scalable and efficient solution for online
applications. We conducted extensive sets of
experiments with real-world datasets including both
people's location data and their social connections,
where we used the latter as the ground truth to verify
the results of applying our approach to the former. We
show that our approach is valid across different
networks and outperforms the competitors.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cheung:2016:SBL,
author = "Alvin Cheung and Samuel Madden and Armando
Solar-Lezama",
title = "{Sloth}: Being Lazy Is a Virtue (When Issuing Database
Queries)",
journal = j-TODS,
volume = "41",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2894749",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many web applications store persistent data in
databases. During execution, such applications spend a
significant amount of time communicating with the
database for retrieval and storing of persistent data
over the network. These network round-trips represent a
significant fraction of the overall execution time for
many applications (especially those that issue a lot of
database queries) and, as a result, increase their
latency. While there has been prior work that aims to
eliminate round-trips by batching queries, they are
limited by (1) a requirement that developers manually
identify batching opportunities, or (2) the fact that
they employ static program analysis techniques that
cannot exploit many opportunities for batching, as many
of these opportunities require knowing precise
information about the state of the running program. In
this article, we present S loth, a new system that
extends traditional lazy evaluation to expose query
batching opportunities during application execution,
even across loops, branches, and method boundaries.
Many such opportunities often require expensive and
sophisticated static analysis to recognize from the
application source code. Rather than doing so, Sloth
instead makes use of dynamic analysis to capture
information about the program state and, based on that
information, decides how to batch queries and when to
issue them to the database. We formalize extended lazy
evaluation and prove that it preserves program
semantics when executed under standard semantics.
Furthermore, we describe our implementation of Sloth
and our experience in evaluating Sloth using over 100
benchmarks from two large-scale open-source
applications, in which Sloth achieved up to a $ 3
\times $ reduction in page load time by delaying
computation using extended lazy evaluation.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2016:EDC,
author = "Christian S. Jensen",
title = "Editorial: The Dark Citations of {TODS} Papers and
What to Do about It --- or: Cite the Journal Paper",
journal = j-TODS,
volume = "41",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2946798",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "8e",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Caruccio:2016:SQV,
author = "Loredana Caruccio and Giuseppe Polese and Genoveffa
Tortora",
title = "Synchronization of Queries and Views Upon Schema
Evolutions: a Survey",
journal = j-TODS,
volume = "41",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2903726",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "One of the problems arising upon the evolution of a
database schema is that some queries and views defined
on the previous schema version might no longer work
properly. Thus, evolving a database schema entails the
redefinition of queries and views to adapt them to the
new schema. Although this problem has been mainly
raised in the context of traditional information
systems, solutions to it are also advocated in other
database-related areas, such as Data Integration, Web
Data Integration, and Data Warehouses. The problem is a
critical one, since industrial organizations often need
to adapt their databases and data warehouses to
frequent changes in the real world. In this article, we
provide a survey of existing approaches and tools to
the problem of adapting queries and views upon a
database schema evolution; we also propose a
classification framework to enable a uniform comparison
method among many heterogeneous approaches and tools.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Deng:2016:CMT,
author = "Ting Deng and Wenfei Fan and Floris Geerts",
title = "Capturing Missing Tuples and Missing Values",
journal = j-TODS,
volume = "41",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2901737",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Databases in real life are often neither entirely
closed-world nor entirely open-world. Databases in an
enterprise are typically partially closed, in which a
part of the data is constrained by master data that
contains complete information about the enterprise in
certain aspects. It has been shown that, despite
missing tuples, such a database may turn out to have
complete information for answering a query. This
article studies partially closed databases from which
both tuples and attribute values may be missing. We
specify such a database in terms of conditional tables
constrained by master data, referred to as c
-instances. We first propose three models to
characterize whether a c -instance T is complete for a
query Q relative to master data. That is, depending on
how missing values in T are instantiated, the answer to
Q in T remains unchanged when new tuples are added. We
then investigate three problems, to determine (a)
whether a given c -instance is complete for a query Q,
(b) whether there exists a c -instance that is complete
for Q relative to master data available, and (c)
whether a c -instance is a minimal-size database that
is complete for Q. We establish matching lower and
upper bounds on these problems for queries expressed in
a variety of languages in each of the three models for
specifying relative completeness.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dutt:2016:PBF,
author = "Anshuman Dutt and Jayant R. Haritsa",
title = "Plan Bouquets: a Fragrant Approach to Robust Query
Processing",
journal = j-TODS,
volume = "41",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2901738",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Identifying efficient execution plans for declarative
OLAP queries typically entails estimation of several
predicate selectivities. In practice, these estimates
often differ significantly from the values actually
encountered during query execution, leading to poor
plan choices and grossly inflated response times. We
propose here a conceptually new approach to address
this classical problem, wherein the compile-time
estimation process is completely eschewed for
error-prone selectivities. Instead, from the set of
optimal plans in the query's selectivity error space, a
limited subset, called the ``plan bouquet,'' is
selected such that at least one of the bouquet plans is
2-optimal at each location in the space. Then, at run
time, a sequence of cost-budgeted executions from the
plan bouquet is carried out, eventually finding a plan
that executes to completion within its assigned budget.
The duration and switching of these executions is
controlled by a graded progression of isosurfaces
projected onto the optimal performance profile. We
prove that this construction results, for the first
time, in guarantees on worst-case performance
sub-optimality. Moreover, it ensures repeatable
execution strategies across different invocations of a
query. We then present a suite of enhancements to the
basic plan bouquet algorithm, including randomized
variants, that result in significantly stronger
performance guarantees. An efficient isosurface
identification algorithm is also introduced to curtail
the bouquet construction overheads. The plan bouquet
approach has been empirically evaluated on both
PostgreSQL and a commercial DBMS, over the TPC-H and
TPC-DS benchmark environments. Our experimental results
indicate that it delivers substantial improvements in
the worst-case behavior, without impairing the
average-case performance, as compared to the native
optimizers of these systems. Moreover, it can be
implemented using existing optimizer infrastructure,
making it relatively easy to incorporate in current
database engines. Overall, the plan bouquet approach
provides novel performance guarantees that open up new
possibilities for robust query processing.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jung:2016:RWR,
author = "Jinhong Jung and Kijung Shin and Lee Sael and U.
Kang",
title = "Random Walk with Restart on Large Graphs Using Block
Elimination",
journal = j-TODS,
volume = "41",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2901736",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Given a large graph, how can we calculate the
relevance between nodes fast and accurately? Random
walk with restart (RWR) provides a good measure for
this purpose and has been applied to diverse data
mining applications including ranking, community
detection, link prediction, and anomaly detection.
Since calculating RWR from scratch takes a long time,
various preprocessing methods, most of which are
related to inverting adjacency matrices, have been
proposed to speed up the calculation. However, these
methods do not scale to large graphs because they
usually produce large dense matrices that do not fit
into memory. In addition, the existing methods are
inappropriate when graphs dynamically change because
the expensive preprocessing task needs to be computed
repeatedly. In this article, we propose B ear, a fast,
scalable, and accurate method for computing RWR on
large graphs. Bear has two versions: a preprocessing
method BearS for static graphs and an incremental
update method BearD for dynamic graphs. BearS consists
of the preprocessing step and the query step. In the
preprocessing step, BearS reorders the adjacency matrix
of a given graph so that it contains a large and
easy-to-invert submatrix, and precomputes several
matrices including the Schur complement of the
submatrix. In the query step, BearS quickly computes
the RWR scores for a given query node using a block
elimination approach with the matrices computed in the
preprocessing step. For dynamic graphs, BearD
efficiently updates the changed parts in the
preprocessed matrices of BearS based on the observation
that only small parts of the preprocessed matrices
change when few edges are inserted or deleted. Through
extensive experiments, we show that BearS significantly
outperforms other state-of-the-art methods in terms of
preprocessing and query speed, space efficiency, and
accuracy. We also show that BearD quickly updates the
preprocessed matrices and immediately computes queries
when the graph changes.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2016:ECF,
author = "Marcelo Arenas and Gonzalo I. Diaz",
title = "The Exact Complexity of the First-Order Logic
Definability Problem",
journal = j-TODS,
volume = "41",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2886095",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the definability problem for first-order
logic, denoted by FO-D ef. The input of FO-Def is a
relational database instance I and a relation R; the
question to answer is whether there exists a
first-order query Q (or, equivalently, a relational
algebra expression Q ) such that Q evaluated on I gives
R as an answer. Although the study of FO-D ef dates
back to 1978, when the decidability of this problem was
shown, the exact complexity of FO-Def remains as a
fundamental open problem. In this article, we provide a
polynomial-time algorithm for solving FO-Def that uses
calls to a graph-isomorphism subroutine (or oracle). As
a consequence, the first-order definability problem is
found to be complete for the class GI of all problems
that are polynomial-time Turing reducible to the graph
isomorphism problem, thus closing the open question
about the exact complexity of this problem. The
technique used is also applied to a generalized version
of the problem that accepts a finite set of relation
pairs, and whose exact complexity was also open; this
version is also found to be GI -complete.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cohen:2016:CLT,
author = "Sara Cohen and Yaacov Y. Weiss",
title = "The Complexity of Learning Tree Patterns from Example
Graphs",
journal = j-TODS,
volume = "41",
number = "2",
pages = "14:1--14:??",
month = jun,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2890492",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:57 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article investigates the problem of learning tree
patterns that return nodes with a given set of labels,
from example graphs provided by the user. Example
graphs are annotated by the user as being either
positive or negative. The goal is then to determine
whether there exists a tree pattern returning tuples of
nodes with the given labels in each of the positive
examples, but in none of the negative examples, and
furthermore, to find one such pattern if it exists.
These are called the satisfiability and learning
problems, respectively. This article thoroughly
investigates the satisfiability and learning problems
in a variety of settings. In particular, we consider
example sets that (1) may contain only positive
examples, or both positive and negative examples, (2)
may contain directed or undirected graphs, and (3) may
have multiple occurrences of labels or be uniquely
labeled (to some degree). In addition, we consider tree
patterns of different types that can allow, or
prohibit, wildcard labeled nodes and descendant edges.
We also consider two different semantics for mapping
tree patterns to graphs. The complexity of
satisfiability is determined for the different
combinations of settings. For cases in which
satisfiability is polynomial, it is also shown that
learning is polynomial. (This is nontrivial as
satisfying patterns may be exponential in size.)
Finally, the minimal learning problem, that is, that of
finding a minimal-sized satisfying pattern, is studied
for cases in which satisfiability is polynomial.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bailis:2016:SAV,
author = "Peter Bailis and Alan Fekete and Ali Ghodsi and Joseph
M. Hellerstein and Ion Stoica",
title = "Scalable Atomic Visibility with {RAMP} Transactions",
journal = j-TODS,
volume = "41",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2909870",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Databases can provide scalability by partitioning data
across several servers. However, multipartition,
multioperation transactional access is often expensive,
employing coordination-intensive locking, validation,
or scheduling mechanisms. Accordingly, many real-world
systems avoid mechanisms that provide useful semantics
for multipartition operations. This leads to incorrect
behavior for a large class of applications including
secondary indexing, foreign key enforcement, and
materialized view maintenance. In this work, we
identify a new isolation model-Read Atomic (RA)
isolation-that matches the requirements of these use
cases by ensuring atomic visibility: either all or none
of each transaction's updates are observed by other
transactions. We present algorithms for Read Atomic
Multipartition (RAMP) transactions that enforce atomic
visibility while offering excellent scalability,
guaranteed commit despite partial failures (via
coordination-free execution ), and minimized
communication between servers (via partition
independence ). These RAMP transactions correctly
mediate atomic visibility of updates and provide
readers with snapshot access to database state by using
limited multiversioning and by allowing clients to
independently resolve nonatomic reads. We demonstrate
that, in contrast with existing algorithms, RAMP
transactions incur limited overhead-even under high
contention-and scale linearly to 100 servers.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{To:2016:PSE,
author = "Quoc-Cuong To and Benjamin Nguyen and Philippe
Pucheral",
title = "Private and Scalable Execution of {SQL} Aggregates on
a Secure Decentralized Architecture",
journal = j-TODS,
volume = "41",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2894750",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Current applications, from complex sensor systems
(e.g., quantified self) to online e-markets, acquire
vast quantities of personal information that usually
end up on central servers where they are exposed to
prying eyes. Conversely, decentralized architectures
that help individuals keep full control of their data
complexify global treatments and queries, impeding the
development of innovative services. This article aims
precisely at reconciling individual's privacy on one
side and global benefits for the community and business
perspectives on the other. It promotes the idea of
pushing the security to secure hardware devices
controlling the data at the place of their acquisition.
Thanks to these tangible physical elements of trust,
secure distributed querying protocols can reestablish
the capacity to perform global computations, such as
Structured Query Language (SQL) aggregates, without
revealing any sensitive information to central servers.
This article studies how to secure the execution of
such queries in the presence of honest-but-curious and
malicious attackers. It also discusses how the
resulting querying protocols can be integrated in a
concrete decentralized architecture. Cost models and
experiments on SQL/Asymmetric Architecture (AA), our
distributed prototype running on real tamper-resistant
hardware, demonstrate that this approach can scale to
nationwide applications.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Burdick:2016:DFL,
author = "Douglas Burdick and Ronald Fagin and Phokion G.
Kolaitis and Lucian Popa and Wang-Chiew Tan",
title = "A Declarative Framework for Linking Entities",
journal = j-TODS,
volume = "41",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2894748",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We introduce and develop a declarative framework for
entity linking and, in particular, for entity
resolution. As in some earlier approaches, our
framework is based on a systematic use of constraints.
However, the constraints we adopt are link-to-source
constraints, unlike in earlier approaches where
source-to-link constraints were used to dictate how to
generate links. Our approach makes it possible to focus
entirely on the intended properties of the outcome of
entity linking, thus separating the constraints from
any procedure of how to achieve that outcome. The core
language consists of link-to-source constraints that
specify the desired properties of a link relation in
terms of source relations and built-in predicates such
as similarity measures. A key feature of the
link-to-source constraints is that they employ
disjunction, which enables the declarative listing of
all the reasons two entities should be linked. We also
consider extensions of the core language that capture
collective entity resolution by allowing
interdependencies among the link relations. We identify
a class of ``good'' solutions for entity-linking
specifications, which we call maximum-value solutions
and which capture the strength of a link by counting
the reasons that justify it. We study natural
algorithmic problems associated with these solutions,
including the problem of enumerating the ``good''
solutions and the problem of finding the certain links,
which are the links that appear in every ``good''
solution. We show that these problems are tractable for
the core language but may become intractable once we
allow interdependencies among the link relations. We
also make some surprising connections between our
declarative framework, which is deterministic, and
probabilistic approaches such as ones based on Markov
Logic Networks.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bourhis:2016:BRR,
author = "Pierre Bourhis and Gabriele Puppis and Cristian
Riveros and Slawek Staworko",
title = "Bounded Repairability for Regular Tree Languages",
journal = j-TODS,
volume = "41",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2898995",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study the problem of bounded repairability of a
given restriction tree language R into a target tree
language T. More precisely, we say that R is bounded
repairable with respect to T if there exists a bound on
the number of standard tree editing operations
necessary to apply to any tree in R to obtain a tree in
T. We consider a number of possible specifications for
tree languages: bottom-up tree automata (on curry
encoding of unranked trees) that capture the class of
XML schemas and document type definitions (DTDs). We
also consider a special case when the restriction
language R is universal (i.e., contains all trees over
a given alphabet). We give an effective
characterization of bounded repairability between pairs
of tree languages represented with automata. This
characterization introduces two tools-synopsis trees
and a coverage relation between them-allowing one to
reason about tree languages that undergo a bounded
number of editing operations. We then employ this
characterization to provide upper bounds to the
complexity of deciding bounded repairability and show
that these bounds are tight. In particular, when the
input tree languages are specified with arbitrary
bottom-up automata, the problem is coNExp-complete. The
problem remains coNExp-complete even if we use
deterministic nonrecursive DTDs to specify the input
languages. The complexity of the problem can be reduced
if we assume that the alphabet, the set of node labels,
is fixed: the problem becomes PS pace-complete for
nonrecursive DTDs and coNP-complete for deterministic
nonrecursive DTDs. Finally, when the restriction tree
language R is universal, we show that the bounded
repairability problem becomes Exp-complete if the
target language is specified by an arbitrary bottom-up
tree automaton and becomes tractable (P-complete, in
fact) when a deterministic bottom-up automaton is
used.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bender:2016:BTC,
author = "Michael A. Bender and Roozbeh Ebrahimi and Haodong Hu
and Bradley C. Kuszmaul",
title = "{B}-Trees and Cache-Oblivious {B}-Trees with
Different-Sized Atomic Keys",
journal = j-TODS,
volume = "41",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2907945",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Most B-tree articles assume that all $N$ keys have the
same size $K$, that $ f = B / K$ keys fit in a disk
block, and therefore that the search cost is $
O(\log_{f + 1} N)$ block transfers. When keys have
variable size, B-tree operations have no nontrivial
performance guarantees, however. This article provides
B-tree-like performance guarantees on dictionaries that
contain keys of different sizes in a model in which
keys must be stored and compared as opaque objects. The
resulting atomic-key dictionaries exhibit performance
bounds in terms of the average key size and match the
bounds when all keys are the same size. Atomic-key
dictionaries can be built with minimal modification to
the B-tree structure, simply by choosing the pivot keys
properly. This article describes both static and
dynamic atomic-key dictionaries. In the static case, if
there are N keys with average size K, the search cost
is $ O(\lceil K / B \rceil \log_{1 + \lceil B / K
\rceil } N)$ expected transfers. It is not possible to
transform these expected bounds into worst-case bounds.
The cost to build the tree is $ O(N K)$ operations and
$ O(N K / B)$ transfers if all keys are presented in
sorted order. If not, the cost is the sorting cost. For
the dynamic dictionaries, the amortized cost to insert
a key $ \kappa $ of arbitrary length at an arbitrary
rank is dominated by the cost to search for $ \kappa $.
Specifically, the amortized cost to insert a key $
\kappa $ of arbitrary length and random rank is $
O(\lceil K / B \rceil \log_{1 + \lceil B / K \rceil } N
+ | \kappa | / B)$ transfers. A dynamic-programming
algorithm is shown for constructing a search tree with
minimal expected cost. This article also gives a
cache-oblivious static atomic-key B-tree, which
achieves the same asymptotic performance as the static
B-tree dictionary, mentioned previously. A
cache-oblivious data structure or algorithm is not
parameterized by the block size $B$ or memory size $M$
in the memory hierarchy; rather, it is universal,
working simultaneously for all possible values of $B$
or $M$. On a machine with block size $B$, if there are
$N$ keys with average size $K$, search operations costs
$ O(\lceil K / B \rceil \log_{1 + \lceil B / K \rceil
}N)$ block transfers in expectation. This
cache-oblivious layout can be built in $ O(N \log (N
K))$ processor operations.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Mazowiecki:2016:MDR,
author = "Filip Mazowiecki and Filip Murlak and Adam Witkowski",
title = "Monadic {Datalog} and Regular Tree Pattern Queries",
journal = j-TODS,
volume = "41",
number = "3",
pages = "20:1--20:??",
month = aug,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2925986",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Containment of monadic datalog programs over trees is
decidable. The situation is more complex when tree
nodes carry labels from an infinite alphabet that can
be tested for equality. It then matters whether the
descendant relation is allowed or not: the descendant
relation can be eliminated easily from monadic programs
only when label equalities are not used. With
descendant, even containment of linear monadic programs
in unions of conjunctive queries is undecidable, and
positive results are known only for bounded-depth
trees. We show that without descendant, containment of
connected monadic programs is decidable over ranked
trees, but over unranked trees it is so only for linear
programs. With descendant, it becomes decidable over
unranked trees under restriction to downward programs:
each rule only moves down from the node in the head.
This restriction is motivated by regular tree pattern
queries, a recent formalism in the area of ActiveXML,
which we show to be equivalent to linear downward
programs.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tian:2016:BHW,
author = "Yuanyuan Tian and Fatma {\"O}zcan and Tao Zou and
Romulo Goncalves and Hamid Pirahesh",
title = "Building a Hybrid Warehouse: Efficient Joins between
Data Stored in {HDFS} and Enterprise Warehouse",
journal = j-TODS,
volume = "41",
number = "4",
pages = "21:1--21:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2972950",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The Hadoop Distributed File System (HDFS) has become
an important data repository in the enterprise as the
center for all business analytics, from SQL queries and
machine learning to reporting. At the same time,
enterprise data warehouses (EDWs) continue to support
critical business analytics. This has created the need
for a new generation of a special federation between
Hadoop-like big data platforms and EDWs, which we call
the hybrid warehouse. There are many applications that
require correlating data stored in HDFS with EDW data,
such as the analysis that associates click logs stored
in HDFS with the sales data stored in the database. All
existing solutions reach out to HDFS and read the data
into the EDW to perform the joins, assuming that the
Hadoop side does not have efficient SQL support. In
this article, we show that it is actually better to do
most data processing on the HDFS side, provided that we
can leverage a sophisticated execution engine for joins
on the Hadoop side. We identify the best hybrid
warehouse architecture by studying various algorithms
to join database and HDFS tables. We utilize Bloom
filters to minimize the data movement and exploit the
massive parallelism in both systems to the fullest
extent possible. We describe a new zigzag join
algorithm and show that it is a robust join algorithm
for hybrid warehouses that performs well in almost all
cases. We further develop a sophisticated cost model
for the various join algorithms and show that it can
facilitate query optimization in the hybrid warehouse
to correctly choose the right algorithm under different
predicate and join selectivities.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Khamis:2016:JGR,
author = "Mahmoud Abo Khamis and Hung Q. Ngo and Christopher
R{\'e} and Atri Rudra",
title = "Joins via Geometric Resolutions: Worst Case and
Beyond",
journal = j-TODS,
volume = "41",
number = "4",
pages = "22:1--22:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2967101",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We present a simple geometric framework for the
relational join. Using this framework, we design an
algorithm that achieves the fractional hypertree-width
bound, which generalizes classical and recent
worst-case algorithmic results on computing joins. In
addition, we use our framework and the same algorithm
to show a series of what are colloquially known as
beyond worst-case results. The framework allows us to
prove results for data stored in BTrees,
multidimensional data structures, and even multiple
indices per table. A key idea in our framework is
formalizing the inference one does with an index as a
type of geometric resolution, transforming the
algorithmic problem of computing joins to a geometric
problem. Our notion of geometric resolution can be
viewed as a geometric analog of logical resolution. In
addition to the geometry and logic connections, our
algorithm can also be thought of as backtracking search
with memoization.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Papadimitriou:2016:GBA,
author = "Dimitra Papadimitriou and Georgia Koutrika and John
Mylopoulos and Yannis Velegrakis",
title = "The Goal Behind the Action: Toward Goal-Aware Systems
and Applications",
journal = j-TODS,
volume = "41",
number = "4",
pages = "23:1--23:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2934666",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Human activity is almost always intentional, be it in
a physical context or as part of an interaction with a
computer system. By understanding why user-generated
events are happening and what purposes they serve, a
system can offer a significantly improved and more
engaging experience. However, goals cannot be easily
captured. Analyzing user actions such as clicks and
purchases can reveal patterns and behaviors, but
understanding the goals behind these actions is a
different and challenging issue. Our work presents a
unified, multidisciplinary viewpoint for goal
management that covers many different cases where goals
can be used and techniques with which they can be
exploited. Our purpose is to provide a common reference
point to the concepts and challenging tasks that need
to be formally defined when someone wants to approach a
data analysis problem from a goal-oriented point of
view. This work also serves as a springboard to discuss
several open challenges and opportunities for
goal-oriented approaches in data management, analysis,
and sharing systems and applications.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fazzinga:2016:EIC,
author = "Bettina Fazzinga and Sergio Flesca and Filippo Furfaro
and Francesco Parisi",
title = "Exploiting Integrity Constraints for Cleaning
Trajectories of {RFID}-Monitored Objects",
journal = j-TODS,
volume = "41",
number = "4",
pages = "24:1--24:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2939368",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A probabilistic framework for cleaning the data
collected by Radio-Frequency IDentification (RFID)
tracking systems is introduced. What has to be cleaned
is the set of trajectories that are the possible
interpretations of the readings: a trajectory in this
set is a sequence whose generic element is a location
covered by the reader(s) that made the detection at the
corresponding time point. The cleaning is guided by
integrity constraints and consists of discarding the
inconsistent trajectories and assigning to the others a
suitable probability of being the actual one. The
probabilities are evaluated by adopting probabilistic
conditioning that logically consists of the following
steps. First, the trajectories are assigned a priori
probabilities that rely on the independence assumption
between the time points. Then, these probabilities are
revised according to the spatio-temporal correlations
encoded by the constraints. This is done by
conditioning the a priori probability of each
trajectory to the event that the constraints are
satisfied: this means taking the ratio of this a priori
probability to the sum of the a priori probabilities of
all the consistent trajectories. Instead of performing
these steps by materializing all the trajectories and
their a priori probabilities (which is infeasible,
owing to the typically huge number of trajectories),
our approach exploits a data structure called
conditioned trajectory graph (ct-graph) that compactly
represents the trajectories and their conditioned
probabilities, and an algorithm for efficiently
constructing the ct-graph, which progressively builds
it while avoiding the construction of components
encoding inconsistent trajectories.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Maabout:2016:SMU,
author = "Sofian Maabout and Carlos Ordonez and Patrick Kamnang
Wanko and Nicolas Hanusse",
title = "Skycube Materialization Using the Topmost Skyline or
Functional Dependencies",
journal = j-TODS,
volume = "41",
number = "4",
pages = "25:1--25:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2955092",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Given a table $ T(I d, D_1, \ldots {}, D_d) $, the
skycube of $T$ is the set of skylines with respect to
to all nonempty subsets (subspaces) of the set of all
dimensions $ \{ D_1, \ldots {}, D_d \} $. To optimize
the evaluation of any skyline query, the solutions
proposed so far in the literature either (i) precompute
all of the skylines or (ii) use compression techniques
so that the derivation of any skyline can be done with
little effort. Even though solutions (i) are appealing
because skyline queries have optimal execution time,
they suffer from time and space scalability because the
number of skylines to be materialized is exponential
with respect to d. On the other hand, solutions (ii)
are attractive in terms of memory consumption, but as
we show, they also have a high time complexity. In this
article, we make contributions to both kinds of
solutions. We first observe that skyline patterns are
monotonic. This property leads to a simple yet
efficient solution for full and partial skycube
materialization when the skyline with respect to all
dimensions, the topmost skyline, is small. On the other
hand, when the topmost skyline is large relative to the
size of the input table, it turns out that functional
dependencies, a fundamental concept in databases,
uncover a monotonic property between skylines. Equipped
with this information, we show that closed attributes
sets are fundamental for partial and full skycube
materialization. Extensive experiments with real and
synthetic datasets show that our solutions generally
outperform state-of-the-art algorithms.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dignos:2016:EKR,
author = "Anton Dign{\"o}s and Michael H. B{\"o}hlen and Johann
Gamper and Christian S. Jensen",
title = "Extending the Kernel of a Relational {DBMS} with
Comprehensive Support for Sequenced Temporal Queries",
journal = j-TODS,
volume = "41",
number = "4",
pages = "26:1--26:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2967608",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many databases contain temporal, or time-referenced,
data and use intervals to capture the temporal aspect.
While SQL-based database management systems (DBMSs) are
capable of supporting the management of interval data,
the support they offer can be improved considerably. A
range of proposed temporal data models and query
languages offer ample evidence to this effect. Natural
queries that are very difficult to formulate in SQL are
easy to formulate in these temporal query languages.
The increased focus on analytics over historical data
where queries are generally more complex exacerbates
the difficulties and thus the potential benefits of a
temporal query language. Commercial DBMSs have recently
started to offer limited temporal functionality in a
step-by-step manner, focusing on the representation of
intervals and neglecting the implementation of the
query evaluation engine. This article demonstrates how
it is possible to extend the relational database engine
to achieve a full-fledged, industrial-strength
implementation of sequenced temporal queries, which
intuitively are queries that are evaluated at each time
point. Our approach reduces temporal queries to
nontemporal queries over data with adjusted intervals,
and it leaves the processing of nontemporal queries
unaffected. Specifically, the approach hinges on three
concepts: interval adjustment, timestamp propagation,
and attribute scaling. Interval adjustment is enabled
by introducing two new relational operators, a temporal
normalizer and a temporal aligner, and the latter two
concepts are enabled by the replication of timestamp
attributes and the use of so-called scaling functions.
By providing a set of reduction rules, we can transform
any temporal query, expressed in terms of temporal
relational operators, to a query expressed in terms of
relational operators and the two new operators. We
prove that the size of a transformed query is linear in
the number of temporal operators in the original query.
An integration of the new operators and the
transformation rules, along with query optimization
rules, into the kernel of PostgreSQL is reported.
Empirical studies with the resulting temporal DBMS are
covered that offer insights into pertinent design
properties of the article's proposal. The new system is
available as open-source software.",
acknowledgement = ack-nhfb,
articleno = "26",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bourhis:2016:GBD,
author = "Pierre Bourhis and Marco Manna and Michael Morak and
Andreas Pieris",
title = "Guarded-Based Disjunctive Tuple-Generating
Dependencies",
journal = j-TODS,
volume = "41",
number = "4",
pages = "27:1--27:??",
month = dec,
year = "2016",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2976736",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:58 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We perform an in-depth complexity analysis of query
answering under guarded-based classes of disjunctive
tuple-generating dependencies (DTGDs), focusing on
(unions of) conjunctive queries ((U)CQs). We show that
the problem under investigation is very hard, namely
2ExpTime-complete, even for fixed sets of dependencies
of a very restricted form. This is a surprising lower
bound that demonstrates the enormous impact of
disjunction on query answering under guarded-based
tuple-generating dependencies, and also reveals the
source of complexity for expressive logics such as the
guarded fragment of first-order logic. We then proceed
to investigate whether prominent subclasses of (U)CQs
(i.e., queries of bounded treewidth and
hypertree-width, and acyclic queries) have a positive
impact on the complexity of the problem under
consideration. We show that queries of bounded
treewidth and bounded hypertree-width do not reduce the
complexity of our problem, even if we focus on
predicates of bounded arity or on fixed sets of DTGDs.
Regarding acyclic queries, although the problem remains
2ExpTime-complete in general, in some relevant settings
the complexity reduces to ExpTime-complete. Finally,
with the aim of identifying tractable cases, we focus
our attention on atomic queries. We show that atomic
queries do not make the query answering problem easier
under classes of guarded-based DTGDs that allow more
than one atom to occur in the body of the dependencies.
However, the complexity significantly decreases in the
case of dependencies that can have only one atom in the
body. In particular, we obtain a Ptime-completeness if
we focus on predicates of bounded arity, and
AC$_0$-membership when the set of dependencies and the
query are fixed. Interestingly, our results can be used
as a generic tool for establishing complexity results
for query answering under various description logics.",
acknowledgement = ack-nhfb,
articleno = "27",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Beame:2017:EMC,
author = "Paul Beame and Jerry Li and Sudeepa Roy and Dan
Suciu",
title = "Exact Model Counting of Query Expressions: Limitations
of Propositional Methods",
journal = j-TODS,
volume = "42",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2984632",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We prove exponential lower bounds on the running time
of the state-of-the-art exact model counting
algorithms-algorithms for exactly computing the number
of satisfying assignments, or the satisfying
probability, of Boolean formulas. These algorithms can
be seen, either directly or indirectly, as building
Decision-Decomposable Negation Normal Form
(decision-DNNF) representations of the input Boolean
formulas. Decision-DNNFs are a special case of d -DNNFs
where d stands for deterministic. We show that any
knowledge compilation representations from a class
(called DLDDs in this article) that contain
decision-DNNFs can be converted into equivalent Free
Binary Decision Diagrams (FBDDs), also known as
Read-Once Branching Programs, with only a
quasi-polynomial increase in representation size.
Leveraging known exponential lower bounds for FBDDs, we
then obtain similar exponential lower bounds for
decision-DNNFs, which imply exponential lower bounds
for model-counting algorithms. We also separate the
power of decision-DNNFs from d -DNNFs and a
generalization of decision-DNNFs known as AND-FBDDs. We
then prove new lower bounds for FBDDs that yield
exponential lower bounds on the running time of these
exact model counters when applied to the problem of
query evaluation in tuple-independent probabilistic
databases-computing the probability of an answer to a
query given independent probabilities of the individual
tuples in a database instance. This approach to the
query evaluation problem, in which one first obtains
the lineage for the query and database instance as a
Boolean formula and then performs weighted model
counting on the lineage, is known as grounded
inference. A second approach, known as lifted inference
or extensional query evaluation, exploits the
high-level structure of the query as a first-order
formula. Although it has been widely believed that
lifted inference is strictly more powerful than
grounded inference on the lineage alone, no formal
separation has previously been shown for query
evaluation. In this article, we show such a formal
separation for the first time. In particular, we
exhibit a family of database queries for which
polynomial-time extensional query evaluation techniques
were previously known but for which query evaluation
via grounded inference using the state-of-the-art exact
model counters requires exponential time.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2017:EUE,
author = "Christian S. Jensen",
title = "Editorial: Updates to the Editorial Board",
journal = j-TODS,
volume = "42",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3041040",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "1e",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Liu:2017:SMD,
author = "Xiufeng Liu and Lukasz Golab and Wojciech Golab and
Ihab F. Ilyas and Shichao Jin",
title = "Smart Meter Data Analytics: Systems, Algorithms, and
Benchmarking",
journal = j-TODS,
volume = "42",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3004295",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Smart electricity meters have been replacing
conventional meters worldwide, enabling automated
collection of fine-grained (e.g., every 15 minutes or
hourly) consumption data. A variety of smart meter
analytics algorithms and applications have been
proposed, mainly in the smart grid literature. However,
the focus has been on what can be done with the data
rather than how to do it efficiently. In this article,
we examine smart meter analytics from a software
performance perspective. First, we design a performance
benchmark that includes common smart meter analytics
tasks. These include offline feature extraction and
model building as well as a framework for online
anomaly detection that we propose. Second, since
obtaining real smart meter data is difficult due to
privacy issues, we present an algorithm for generating
large realistic datasets from a small seed of real
data. Third, we implement the proposed benchmark using
five representative platforms: a traditional numeric
computing platform (Matlab), a relational DBMS with a
built-in machine learning toolkit (PostgreSQL/MADlib),
a main-memory column store (``System C''), and two
distributed data processing platforms (Hive and
Spark/Spark Streaming). We compare the five platforms
in terms of application development effort and
performance on a multicore machine as well as a cluster
of 16 commodity servers.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Currim:2017:DMM,
author = "Sabah Currim and Richard T. Snodgrass and Young-Kyoon
Suh and Rui Zhang",
title = "{DBMS} Metrology: Measuring Query Time",
journal = j-TODS,
volume = "42",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2996454",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "It is surprisingly hard to obtain accurate and precise
measurements of the time spent executing a query
because there are many sources of variance. To
understand these sources, we review relevant
per-process and overall measures obtainable from the
Linux kernel and introduce a structural causal model
relating these measures. A thorough correlational
analysis provides strong support for this model. We
attempted to determine why a particular measurement
wasn't repeatable and then to devise ways to eliminate
or reduce that variance. This enabled us to articulate
a timing protocol that applies to proprietary DBMSes,
that ensures the repeatability of a query, and that
obtains a quite accurate query execution time while
dropping very few outliers. This resulting query time
measurement procedure, termed the Tucson Timing
Protocol Version 2 (TTPv2), consists of the following
steps: (i) perform sanity checks to ensure data
validity; (ii) drop some query executions via clearly
motivated predicates; (iii) drop some entire queries at
a cardinality, again via clearly motivated predicates;
(iv) for those that remain, compute a single measured
time by a carefully justified formula over the
underlying measures of the remaining query executions;
and (v) perform post-analysis sanity checks. The result
is a mature, general, robust, self-checking protocol
that provides a more precise and more accurate timing
of the query. The protocol is also applicable to other
operating domains in which measurements of multiple
processes each doing computation and I/O is needed.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wu:2017:CFC,
author = "You Wu and Pankaj K. Agarwal and Chengkai Li and Jun
Yang and Cong Yu",
title = "Computational Fact Checking through Query
Perturbations",
journal = j-TODS,
volume = "42",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2996453",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Our media is saturated with claims of ``facts'' made
from data. Database research has in the past focused on
how to answer queries, but has not devoted much
attention to discerning more subtle qualities of the
resulting claims, for example, is a claim
``cherry-picking''? This article proposes a framework
that models claims based on structured data as
parameterized queries. Intuitively, with its choice of
the parameter setting, a claim presents a particular
(and potentially biased) view of the underlying data. A
key insight is that we can learn a lot about a claim by
``perturbing'' its parameters and seeing how its
conclusion changes. For example, a claim is not robust
if small perturbations to its parameters can change its
conclusions significantly. This framework allows us to
formulate practical fact-checking
tasks-reverse-engineering vague claims, and countering
questionable claims-as computational problems. Along
with the modeling framework, we develop an algorithmic
framework that enables efficient instantiations of
``meta'' algorithms by supplying appropriate
algorithmic building blocks. We present real-world
examples and experiments that demonstrate the power of
our model, efficiency of our algorithms, and usefulness
of their results.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Teflioudi:2017:EAM,
author = "Christina Teflioudi and Rainer Gemulla",
title = "Exact and Approximate Maximum Inner Product Search
with {LEMP}",
journal = j-TODS,
volume = "42",
number = "1",
pages = "5:1--5:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2996452",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We study exact and approximate methods for maximum
inner product search, a fundamental problem in a number
of data mining and information retrieval tasks. We
propose the LEMP framework, which supports both exact
and approximate search with quality guarantees. At its
heart, LEMP transforms a maximum inner product search
problem over a large database of vectors into a number
of smaller cosine similarity search problems. This
transformation allows LEMP to prune large parts of the
search space immediately and to select suitable search
algorithms for each of the remaining problems
individually. LEMP is able to leverage existing methods
for cosine similarity search, but we also provide a
number of novel search algorithms tailored to our
setting. We conducted an extensive experimental study
that provides insight into the performance of many
state-of-the-art techniques-including LEMP-on multiple
real-world datasets. We found that LEMP often was
significantly faster or more accurate than alternative
methods.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Shi:2017:UUA,
author = "Xiaogang Shi and Bin Cui and Gillian Dobbie and Beng
Chin Ooi",
title = "{UniAD}: a Unified Ad Hoc Data Processing System",
journal = j-TODS,
volume = "42",
number = "1",
pages = "6:1--6:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3009957",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Instead of constructing complex declarative queries,
many users prefer to write their programs using
procedural code embedded with simple queries. Since
many users are not expert programmers or the programs
are written in a rush, these programs usually exhibit
poor performance in practice and it is a challenge to
automatically and efficiently optimize these programs.
In this article, we present UniAD, which stands for Uni
fied execution for Ad hoc Data processing, a system
designed to simplify the programming of data processing
tasks and provide efficient execution for user
programs. We provide the background of program
semantics and propose a novel intermediate
representation, called Unified Intermediate
Representation (UniIR), which utilizes a simple and
expressive mechanism HOQ to describe the operations
performed in programs. By combining both procedural and
declarative logics with the proposed intermediate
representation, we can perform various optimizations
across the boundary between procedural and declarative
code. We propose a transformation-based optimizer to
automatically optimize programs and implement the UniAD
system. The extensive experimental results on various
benchmarks demonstrate that our techniques can
significantly improve the performance of a wide range
of data processing programs.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Song:2017:RDD,
author = "Shaoxu Song and Lei Chen",
title = "Response to {``Differential Dependencies
Revisited''}",
journal = j-TODS,
volume = "42",
number = "1",
pages = "7:1--7:??",
month = mar,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/2983602",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Mar 2 18:02:59 MST 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "See \cite{Song:2011:DDR,Vincent:2015:TCD}.",
abstract = "A recent article [Vincent et al. 2015] concerns the
correctness of several results in reasoning about
differential dependencies ( dds), originally reported
in Song and Chen [2011]. The major concern by Vincent
et al. [2015] roots from assuming a type of infeasible
differential functions in the given dds for consistency
and implication analysis, which are not allowed in Song
and Chen [2011]. A differential function is said to be
infeasible if there is no tuple pair with values that
can satisfy the specified distance constraints. For
example, [price($ < 2 $, $ > 4$)] requires the
difference of two price values to be $ < 2$ and $ > 4$
at the same time, which is clearly impossible. Although
dds involving infeasible differential functions may be
syntactically interesting, they are semantically
meaningless and would neither be specified by domain
experts nor discovered from data. For these reasons,
infeasible differential functions are not considered
[Song and Chen 2011] and the results in Song and Chen
[2011] are correct, in contrast to what is claimed in
Vincent et al. [2015].",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Paparrizos:2017:FAT,
author = "John Paparrizos and Luis Gravano",
title = "Fast and Accurate Time-Series Clustering",
journal = j-TODS,
volume = "42",
number = "2",
pages = "8:1--8:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3044711",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The proliferation and ubiquity of temporal data across
many disciplines has generated substantial interest in
the analysis and mining of time series. Clustering is
one of the most popular data-mining methods, not only
due to its exploratory power but also because it is
often a preprocessing step or subroutine for other
techniques. In this article, we present $k$-Shape and
$k$-MultiShapes ($k$-MS), two novel algorithms for
time-series clustering. $k$-Shape and $k$-MS rely on a
scalable iterative refinement procedure. As their
distance measure, $k$-Shape and $k$-MS use shape-based
distance (SBD), a normalized version of the
cross-correlation measure, to consider the shapes of
time series while comparing them. Based on the
properties of SBD, we develop two new methods, namely
ShapeExtraction (SE) and MultiShapesExtraction (MSE),
to compute cluster centroids that are used in every
iteration to update the assignment of time series to
clusters. $k$-Shape relies on SE to compute a single
centroid per cluster based on all time series in each
cluster. In contrast, $k$-MS relies on MSE to compute
multiple centroids per cluster to account for the
proximity and spatial distribution of time series in
each cluster. To demonstrate the robustness of SBD,
$k$-Shape, and $k$-MS, we perform an extensive
experimental evaluation on 85 datasets against
state-of-the-art distance measures and clustering
methods for time series using rigorous statistical
analysis. SBD, our efficient and parameter-free
distance measure, achieves similar accuracy to Dynamic
Time Warping (DTW), a highly accurate but
computationally expensive distance measure that
requires parameter tuning. For clustering, we compare
$k$-Shape and $k$-MS against scalable and non-scalable
partitional, hierarchical, spectral, density-based, and
shapelet-based methods, with combinations of the most
competitive distance measures. $k$-Shape outperforms
all scalable methods in terms of accuracy. Furthermore,
$k$-Shape also outperforms all non-scalable approaches,
with one exception, namely $k$-medoids with DTW, which
achieves similar accuracy. However, unlike $k$-Shape,
this approach requires tuning of its distance measure
and is significantly slower than $k$-Shape. $k$-MS
performs similarly to $k$-Shape in comparison to rival
methods, but $k$-MS is significantly more accurate than
$k$-Shape. Beyond clustering, we demonstrate the
effectiveness of $k$-Shape to reduce the search space
of one-nearest-neighbor classifiers for time series.
Overall, SBD, $k$-Shape, and $k$-MS emerge as
domain-independent, highly accurate, and efficient
methods for time-series comparison and clustering with
broad applications.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Koutris:2017:CQA,
author = "Paraschos Koutris and Jef Wijsen",
title = "Consistent Query Answering for Self-Join-Free
Conjunctive Queries Under Primary Key Constraints",
journal = j-TODS,
volume = "42",
number = "2",
pages = "9:1--9:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3068334",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A relational database is said to be uncertain if
primary key constraints can possibly be violated. A
repair (or possible world) of an uncertain database is
obtained by selecting a maximal number of tuples
without ever selecting two distinct tuples with the
same primary key value. For any Boolean query $q$,
CERTAINTY($q$) is the problem that takes an uncertain
database db as input and asks whether $q$ is true in
every repair of db. The complexity of this problem has
been particularly studied for $q$ ranging over the
class of self-join-free Boolean conjunctive queries. A
research challenge is to determine, given $q$, whether
CERTAINTY($q$) belongs to complexity classes FO, $P$,
or coNP-complete. In this article, we combine existing
techniques for studying this complexity classification
task. We show that, for any self-join-free Boolean
conjunctive query $q$, it can be decided whether or not
CERTAINTY($q$) is in FO. We additionally show how to
construct a single SQL query for solving CERTAINTY($q$)
if it is in FO. Further, for any self-join-free Boolean
conjunctive query $q$, CERTAINTY($q$) is either in $P$
or coNP-complete and the complexity dichotomy is
effective. This settles a research question that has
been open for 10 years.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Yu:2017:ODM,
author = "Yanwei Yu and Lei Cao and Elke A. Rundensteiner and
Qin Wang",
title = "Outlier Detection over Massive-Scale Trajectory
Streams",
journal = j-TODS,
volume = "42",
number = "2",
pages = "10:1--10:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3013527",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The detection of abnormal moving objects over
high-volume trajectory streams is critical for
real-time applications ranging from military
surveillance to transportation management. Yet this
outlier detection problem, especially along both the
spatial and temporal dimensions, remains largely
unexplored. In this work, we propose a rich taxonomy of
novel classes of neighbor-based trajectory outlier
definitions that model the anomalous behavior of moving
objects for a large range of real-time applications.
Our theoretical analysis and empirical study on two
real-world datasets-the Beijing Taxi trajectory data
and the Ground Moving Target Indicator data stream-and
one generated Moving Objects dataset demonstrate the
effectiveness of our taxonomy in effectively capturing
different types of abnormal moving objects.
Furthermore, we propose a general strategy for
efficiently detecting these new outlier classes called
the {\em minimal examination\/} (MEX) framework. The
MEX framework features three core optimization
principles, which leverage spatiotemporal as well as
the predictability properties of the neighbor evidence
to minimize the detection costs. Based on this
foundation, we design algorithms that detect the
outliers based on these classes of new outlier
semantics that successfully leverage our optimization
principles. Our comprehensive experimental study
demonstrates that our proposed MEX strategy drives the
detection costs 100-fold down into the practical realm
for applications that analyze high-volume trajectory
streams in near real time.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Han:2017:CCF,
author = "Yunheng Han and Weiwei Sun and Baihua Zheng",
title = "{COMPRESS}: a Comprehensive Framework of Trajectory
Compression in Road Networks",
journal = j-TODS,
volume = "42",
number = "2",
pages = "11:1--11:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3015457",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/datacompression.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "More and more advanced technologies have become
available to collect and integrate an unprecedented
amount of data from multiple sources, including GPS
trajectories about the traces of moving objects. Given
the fact that GPS trajectories are vast in size while
the information carried by the trajectories could be
redundant, we focus on trajectory compression in this
article. As a systematic solution, we propose a
comprehensive framework, namely, COMPRESS
(Comprehensive Paralleled Road-Network-Based Trajectory
Compression), to compress GPS trajectory data in an
urban road network. In the preprocessing step, COMPRESS
decomposes trajectories into spatial paths and temporal
sequences, with a thorough justification for trajectory
decomposition. In the compression step, COMPRESS
performs spatial compression on spatial paths, and
temporal compression on temporal sequences in parallel.
It introduces two alternative algorithms with different
strengths for lossless spatial compression and designs
lossy but error-bounded algorithms for temporal
compression. It also presents query processing
algorithms to support error-bounded location-based
queries on compressed trajectories without full
decompression. All algorithms under COMPRESS are
efficient and have the time complexity of $ O (| T |)
$, where $ | T | $ is the size of the input trajectory
$T$. We have also conducted a comprehensive
experimental study to demonstrate the effectiveness of
COMPRESS, whose compression ratio is significantly
better than related approaches.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{TenCate:2017:AAS,
author = "Balder {Ten Cate} and Phokion G. Kolaitis and Kun Qian
and Wang-Chiew Tan",
title = "Approximation Algorithms for Schema-Mapping Discovery
from Data Examples",
journal = j-TODS,
volume = "42",
number = "2",
pages = "12:1--12:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3044712",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In recent years, data examples have been at the core
of several different approaches to schema-mapping
design. In particular, Gottlob and Senellart introduced
a framework for schema-mapping discovery from a single
data example, in which the derivation of a schema
mapping is cast as an optimization problem. Our goal is
to refine and study this framework in more depth. Among
other results, we design a polynomial-time
$\log(n)$-approximation algorithm for computing optimal
schema mappings from a given set of data examples
(where $n$ is the combined size of the given data
examples) for a restricted class of schema mappings;
moreover, we show that this approximation ratio cannot
be improved. In addition to the complexity-theoretic
results, we implemented the aforementioned
$\log(n)$-approximation algorithm and carried out an
experimental evaluation in a real-world mapping
scenario.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Maniu:2017:IFQ,
author = "Silviu Maniu and Reynold Cheng and Pierre Senellart",
title = "An Indexing Framework for Queries on Probabilistic
Graphs",
journal = j-TODS,
volume = "42",
number = "2",
pages = "13:1--13:??",
month = jun,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3044713",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Jun 23 16:29:07 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Information in many applications, such as mobile
wireless systems, social networks, and road networks,
is captured by graphs. In many cases, such information
is uncertain. We study the problem of querying a
probabilistic graph, in which vertices are connected to
each other probabilistically. In particular, we examine
``source-to-target'' queries (ST-queries), such as
computing the shortest path between two vertices. The
major difference with the deterministic setting is that
query answers are enriched with probabilistic
annotations. Evaluating ST-queries over probabilistic
graphs is \#P-hard, as it requires examining an
exponential number of ``possible worlds''-database
instances generated from the probabilistic graph.
Existing solutions to the ST-query problem, which
sample possible worlds, have two downsides: (i) a
possible world can be very large and (ii) many samples
are needed for reasonable accuracy. To tackle these
issues, we study the ProbTree, a data structure that
stores a succinct, or indexed, version of the possible
worlds of the graph. Existing ST-query solutions are
executed on top of this structure, with the number of
samples and sizes of the possible worlds reduced. We
examine lossless and lossy methods for generating the
ProbTree, which reflect the tradeoff between the
accuracy and efficiency of query evaluation. We analyze
the correctness and complexity of these approaches. Our
extensive experiments on real datasets show that the
ProbTree is fast to generate and small in size. It also
enhances the accuracy and efficiency of existing
ST-query algorithms significantly.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gan:2017:HAE,
author = "Junhao Gan and Yufei Tao",
title = "On the Hardness and Approximation of {Euclidean}
{DBSCAN}",
journal = j-TODS,
volume = "42",
number = "3",
pages = "14:1--14:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3083897",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "DBSCAN is a method proposed in 1996 for clustering
multi-dimensional points, and has received extensive
applications. Its computational hardness is still
unsolved to this date. The original KDD'96 paper
claimed an algorithm of $ O(n \log n) $ ``average
runtime complexity'' (where n is the number of data
points) without a rigorous proof. In 2013, a genuine $
O(n \log n) $-time algorithm was found in 2D space
under Euclidean distance. The hardness of
dimensionality $ d \geq 3$ has remained open ever
since. This article considers the problem of computing
DBSCAN clusters from scratch (assuming no existing
indexes) under Euclidean distance. We prove that, for $
d \geq 3$, the problem requires $ \omega (n^{4 / 3}) $
time to solve, unless very significant
breakthroughs-ones widely believed to be
impossible-could be made in theoretical computer
science. Motivated by this, we propose a relaxed
version of the problem called $ \rho $- approximate
DBSCAN, which returns the same clusters as DBSCAN,
unless the clusters are ``unstable'' (i.e., they change
once the input parameters are slightly perturbed). The
$ \rho $-approximate problem can be settled in $ O(n) $
expected time regardless of the constant dimensionality
d. The article also enhances the previous result on the
exact DBSCAN problem in 2D space. We show that, if the
n data points have been pre-sorted on each dimension
(i.e., one sorted list per dimension), the problem can
be settled in $ O(n) $ worst-case time. As a corollary,
when all the coordinates are integers, the 2D DBSCAN
problem can be solved in $ O(n \log \log n) $ time
deterministically, improving the existing $ O(n \log n)
$ bound.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Martens:2017:BCS,
author = "Wim Martens and Frank Neven and Matthias Niewerth and
Thomas Schwentick",
title = "{BonXai}: Combining the Simplicity of {DTD} with the
Expressiveness of {XML} Schema",
journal = j-TODS,
volume = "42",
number = "3",
pages = "15:1--15:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3105960",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "While the migration from DTD to XML Schema was driven
by a need for increased expressivity and flexibility,
the latter was also significantly more complex to use
and understand. Whereas DTDs are characterized by their
simplicity, XML Schema Documents are notoriously
difficult. In this article, we introduce the XML
specification language BonXai, which incorporates many
features of XML Schema but is arguably almost as easy
to use as DTDs. In brief, the latter is achieved by
sacrificing the explicit use of types in favor of
simple patterns expressing contexts for elements. The
goal of BonXai is not to replace XML Schema but rather
to provide a simpler alternative for users who want to
go beyond the expressiveness and features of DTD but do
not need the explicit use of types. Furthermore, XML
Schema processing tools can be used as a back-end for
BonXai, since BonXai can be automatically converted
into XML Schema. A particularly strong point of BonXai
is its solid foundation rooted in a decade of
theoretical work around pattern-based schemas. We
present a formal model for a core fragment of BonXai
and the translation algorithms to and from a core
fragment of XML Schema. We prove that BonXai and XML
Schema can be converted back-and-forth on the level of
tree languages and we formally study the size
trade-offs between the two languages.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zheng:2017:ESB,
author = "Weiguo Zheng and Lei Zou and Lei Chen and Dongyan
Zhao",
title = "Efficient {SimRank}-Based Similarity Join",
journal = j-TODS,
volume = "42",
number = "3",
pages = "16:1--16:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3083899",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Graphs have been widely used to model complex data in
many real-world applications. Answering vertex join
queries over large graphs is meaningful and
interesting, which can benefit friend recommendation in
social networks and link prediction, and so on. In this
article, we adopt ``SimRank'' [13] to evaluate the
similarity between two vertices in a large graph
because of its generality. Note that ``SimRank'' is
purely structure dependent, and it does not rely on the
domain knowledge. Specifically, we define a
SimRank-based join (SRJ) query to find all vertex pairs
satisfying the threshold from two sets of vertices $U$
and $V$. To reduce the search space, we propose a
shortest-path-distance-based upper bound for SimRank
scores to prune unpromising vertex pairs. In the
verification, we propose a novel index, called h-go
cover$^+$, to efficiently compute the SimRank score of
any single vertex pair. Given a graph $G$, we only
materialize the SimRank scores of a small proportion of
vertex pairs (i.e., the h-go cover$^+$ vertex pairs),
based on which the SimRank score of any vertex pair can
be computed easily. To find the h-go cover$^+$ vertex
pairs, we propose an efficient method without building
the vertex-pair graph. Hence, large graphs can be dealt
with easily. Extensive experiments over both real and
synthetic datasets confirm the efficiency of our
solution.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kaminski:2017:QNA,
author = "Mark Kaminski and Egor V. Kostylev and Bernardo Cuenca
Grau",
title = "Query Nesting, Assignment, and Aggregation in {SPARQL
1.1}",
journal = j-TODS,
volume = "42",
number = "3",
pages = "17:1--17:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3083898",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Answering aggregate queries is a key requirement of
emerging applications of Semantic Technologies, such as
data warehousing, business intelligence, and sensor
networks. To fulfil the requirements of such
applications, the standardization of SPARQL 1.1 led to
the introduction of a wide range of constructs that
enable value computation, aggregation, and query
nesting. In this article, we provide an in-depth formal
analysis of the semantics and expressive power of these
new constructs as defined in the SPARQL 1.1
specification, and hence lay the necessary foundations
for the development of robust, scalable, and extensible
query engines supporting complex numerical and
analytics tasks.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Tschirschnitz:2017:DID,
author = "Fabian Tschirschnitz and Thorsten Papenbrock and Felix
Naumann",
title = "Detecting Inclusion Dependencies on Very Many Tables",
journal = j-TODS,
volume = "42",
number = "3",
pages = "18:1--18:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3105959",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Detecting inclusion dependencies, the prerequisite of
foreign keys, in relational data is a challenging task.
Detecting them among the hundreds of thousands or even
millions of tables on the web is daunting. Still, such
inclusion dependencies can help connect disparate
pieces of information on the Web and reveal unknown
relationships among tables. With the algorithm M any,
we present a novel inclusion dependency detection
algorithm, specialized for the very many --- but
typically small --- tables found on the Web. We make
use of Bloom filters and indexed bit-vectors to show
the feasibility of our approach. Our evaluation on two
corpora of Web tables shows a superior runtime over
known approaches and its usefulness to reveal hidden
structures on the Web.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schubert:2017:DRR,
author = "Erich Schubert and J{\"o}rg Sander and Martin Ester
and Hans Peter Kriegel and Xiaowei Xu",
title = "{DBSCAN} Revisited, Revisited: Why and How You Should
(Still) Use {DBSCAN}",
journal = j-TODS,
volume = "42",
number = "3",
pages = "19:1--19:??",
month = aug,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3068335",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Aug 24 16:30:15 MDT 2017",
bibsource = "http://www.acm.org/pubs/contents/journals/tods/;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "At SIGMOD 2015, an article was presented with the
title ``DBSCAN Revisited: Mis-Claim, Un-Fixability, and
Approximation'' that won the conference's best paper
award. In this technical correspondence, we want to
point out some inaccuracies in the way DBSCAN was
represented, and why the criticism should have been
directed at the assumption about the performance of
spatial index structures such as R-trees and not at an
algorithm that can use such indexes. We will also
discuss the relationship of DBSCAN performance and the
indexability of the dataset, and discuss some
heuristics for choosing appropriate DBSCAN parameters.
Some indicators of bad parameters will be proposed to
help guide future users of this algorithm in choosing
parameters such as to obtain both meaningful results
and good performance. In new experiments, we show that
the new SIGMOD 2015 methods do not appear to offer
practical benefits if the DBSCAN parameters are well
chosen and thus they are primarily of theoretical
interest. In conclusion, the original DBSCAN algorithm
with effective indexes and reasonably chosen parameter
values performs competitively compared to the method
proposed by Gan and Tao.",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Aberger:2017:ERE,
author = "Christopher R. Aberger and Andrew Lamb and Susan Tu
and Andres N{\"o}tzli and Kunle Olukotun and
Christopher R{\'e}",
title = "{EmptyHeaded}: a Relational Engine for Graph
Processing",
journal = j-TODS,
volume = "42",
number = "4",
pages = "20:1--20:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3129246",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "There are two types of high-performance graph
processing engines: low- and high-level engines.
Low-level engines (Galois, PowerGraph, Snap) provide
optimized data structures and computation models but
require users to write low-level imperative code, hence
ensuring that efficiency is the burden of the user. In
high-level engines, users write in query languages like
datalog (SociaLite) or SQL (Grail). High-level engines
are easier to use but are orders of magnitude slower
than the low-level graph engines. We present
EmptyHeaded, a high-level engine that supports a rich
datalog-like query language and achieves performance
comparable to that of low-level engines. At the core of
EmptyHeaded's design is a new class of join algorithms
that satisfy strong theoretical guarantees, but have
thus far not achieved performance comparable to that of
specialized graph processing engines. To achieve high
performance, EmptyHeaded introduces a new join engine
architecture, including a novel query optimizer and
execution engine that leverage single-instruction
multiple data (SIMD) parallelism. With this
architecture, EmptyHeaded outperforms high-level
approaches by up to three orders of magnitude on graph
pattern queries, PageRank, and Single-Source Shortest
Paths (SSSP) and is an order of magnitude faster than
many low-level baselines. We validate that EmptyHeaded
competes with the best-of-breed low-level engine
(Galois), achieving comparable performance on PageRank
and at most 3$ \times $ worse performance on SSSP.
Finally, we show that the EmptyHeaded design can easily
be extended to accommodate a standard resource
description framework (RDF) workload, the LUBM
benchmark. On the LUBM benchmark, we show that
EmptyHeaded can compete with and sometimes outperform
two high-level, but specialized RDF baselines
(TripleBit and RDF-3X), while outperforming MonetDB by
up to three orders of magnitude and LogicBlox by up to
two orders of magnitude.",
acknowledgement = ack-nhfb,
articleno = "20",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2017:DQL,
author = "Marcelo Arenas and Martin Ugarte",
title = "Designing a Query Language for {RDF}: Marrying Open
and Closed Worlds",
journal = j-TODS,
volume = "42",
number = "4",
pages = "21:1--21:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3129247",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "When querying an Resource Description Framework (RDF)
graph, a prominent feature is the possibility of
extending the answer to a query with optional
information. However, the definition of this feature in
SPARQL-the standard RDF query language-has raised some
important issues. Most notably, the use of this feature
increases the complexity of the evaluation problem, and
its closed-world semantics is in conflict with the
underlying open-world semantics of RDF. Many approaches
for fixing such problems have been proposed, the most
prominent being the introduction of the semantic notion
of weakly monotone SPARQL query. Weakly monotone SPARQL
queries have shaped the class of queries that conform
to the open-world semantics of RDF. Unfortunately,
finding an effective way of restricting SPARQL to the
fragment of weakly monotone queries has proven to be an
elusive problem. In practice, the most widely adopted
fragment for writing SPARQL queries is based on the
syntactic notion of well designedness. This notion has
proven to be a good approach for writing SPARQL
queries, but its expressive power has yet to be fully
understood. The starting point of this article is to
understand the relation between well-designed queries
and the semantic notion of weak monotonicity. It is
known that every well-designed SPARQL query is weakly
monotone; as our first contribution we prove that the
converse does not hold, even if an extension of this
notion based on the use of disjunction is considered.
Given this negative result, we embark on the task of
defining syntactic fragments that are weakly monotone
and have higher expressive power than the fragment of
well-designed queries. To this end, we move to a more
general scenario where infinite RDF graphs are also
allowed, so interpolation techniques studied for
first-order logic can be applied. With the use of these
techniques, we are able to define a new operator for
SPARQL that gives rise to a query language with the
desired properties (over finite and infinite RDF
graphs). It should be noticed that every query in this
fragment is weakly monotone if we restrict the
semantics to finite RDF graphs. Moreover, we use this
result to provide a simple characterization of the
class of monotone CONSTRUCT queries, that is, the class
of SPARQL queries that produce RDF graphs as output.
Finally, we pinpoint the complexity of the evaluation
problem for the query languages identified in the
article.",
acknowledgement = ack-nhfb,
articleno = "21",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Barany:2017:DPP,
author = "Vince B{\'a}r{\'a}ny and Balder {Ten Cate} and Benny
Kimelfeld and Dan Olteanu and Zografoula Vagena",
title = "Declarative Probabilistic Programming with {Datalog}",
journal = j-TODS,
volume = "42",
number = "4",
pages = "22:1--22:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3132700",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Probabilistic programming languages are used for
developing statistical models. They typically consist
of two components: a specification of a stochastic
process (the prior) and a specification of observations
that restrict the probability space to a conditional
subspace (the posterior). Use cases of such formalisms
include the development of algorithms in machine
learning and artificial intelligence. In this article,
we establish a probabilistic-programming extension of
Datalog that, on the one hand, allows for defining a
rich family of statistical models, and on the other
hand retains the fundamental properties of
declarativity. Our proposed extension provides
mechanisms to include common numerical probability
functions; in particular, conclusions of rules may
contain values drawn from such functions. The semantics
of a program is a probability distribution over the
possible outcomes of the input database with respect to
the program. Observations are naturally incorporated by
means of integrity constraints over the extensional and
intensional relations. The resulting semantics is
robust under different chases and invariant to
rewritings that preserve logical equivalence.",
acknowledgement = ack-nhfb,
articleno = "22",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Alvaro:2017:BCA,
author = "Peter Alvaro and Neil Conway and Joseph M. Hellerstein
and David Maier",
title = "{Blazes}: Coordination Analysis and Placement for
Distributed Programs",
journal = j-TODS,
volume = "42",
number = "4",
pages = "23:1--23:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3110214",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Distributed consistency is perhaps the most-discussed
topic in distributed systems today. Coordination
protocols can ensure consistency, but in practice they
cause undesirable performance unless used judiciously.
Scalable distributed architectures avoid coordination
whenever possible, but under-coordinated systems can
exhibit behavioral anomalies under fault, which are
often extremely difficult to debug. This raises
significant challenges for distributed system
architects and developers. In this article, we present
B lazes, a cross-platform program analysis framework
that (a) identifies program locations that require
coordination to ensure consistent executions, and (b)
automatically synthesizes application-specific
coordination code that can significantly outperform
general-purpose techniques. We present two case
studies, one using annotated programs in the Twitter
Storm system and another using the Bloom declarative
language.",
acknowledgement = ack-nhfb,
articleno = "23",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Colazzo:2017:LTM,
author = "Dario Colazzo and Giorgio Ghelli and Carlo Sartiani",
title = "Linear Time Membership in a Class of Regular
Expressions with Counting, Interleaving, and Unordered
Concatenation",
journal = j-TODS,
volume = "42",
number = "4",
pages = "24:1--24:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3132701",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Regular Expressions (REs) are ubiquitous in database
and programming languages. While many applications make
use of REs extended with interleaving (shuffle) and
unordered concatenation operators, this extension badly
affects the complexity of basic operations, and,
especially, makes membership NP-hard, which is
unacceptable in most practical scenarios. In this
article, we study the problem of membership checking
for a restricted class of these extended REs, called
conflict-free REs, which are expressive enough to cover
the vast majority of real-world applications. We
present several polynomial algorithms for membership
checking over conflict-free REs. The algorithms are all
polynomial and differ in terms of adopted optimization
techniques and in the kind of supported operators. As a
particular application, we generalize the approach to
check membership of Extensible Markup Language trees
into a class of EDTDs (Extended Document Type
Definitions) that models the crucial aspects of DTDs
(Document Type Definitions) and XSD (XML Schema
Definitions) schemas. Results about an extensive
experimental analysis validate the efficiency of the
presented membership checking techniques.",
acknowledgement = ack-nhfb,
articleno = "24",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Zhang:2017:PPD,
author = "Jun Zhang and Graham Cormode and Cecilia M. Procopiuc
and Divesh Srivastava and Xiaokui Xiao",
title = "{PrivBayes}: Private Data Release via {Bayesian}
Networks",
journal = j-TODS,
volume = "42",
number = "4",
pages = "25:1--25:??",
month = nov,
year = "2017",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3134428",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Nov 18 10:18:22 MST 2017",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Privacy-preserving data publishing is an important
problem that has been the focus of extensive study. The
state-of-the-art solution for this problem is
differential privacy, which offers a strong degree of
privacy protection without making restrictive
assumptions about the adversary. Existing techniques
using differential privacy, however, cannot effectively
handle the publication of high-dimensional data. In
particular, when the input dataset contains a large
number of attributes, existing methods require
injecting a prohibitive amount of noise compared to the
signal in the data, which renders the published data
next to useless. To address the deficiency of the
existing methods, this paper presents PrivBayes, a
differentially private method for releasing
high-dimensional data. Given a dataset D, PrivBayes
first constructs a Bayesian network N, which (i)
provides a succinct model of the correlations among the
attributes in D and (ii) allows us to approximate the
distribution of data in D using a set P of
low-dimensional marginals of D. After that, PrivBayes
injects noise into each marginal in P to ensure
differential privacy and then uses the noisy marginals
and the Bayesian network to construct an approximation
of the data distribution in D. Finally, PrivBayes
samples tuples from the approximate distribution to
construct a synthetic dataset, and then releases the
synthetic data. Intuitively, PrivBayes circumvents the
curse of dimensionality, as it injects noise into the
low-dimensional marginals in P instead of the
high-dimensional dataset D. Private construction of
Bayesian networks turns out to be significantly
challenging, and we introduce a novel approach that
uses a surrogate function for mutual information to
build the model more accurately. We experimentally
evaluate PrivBayes on real data and demonstrate that it
significantly outperforms existing solutions in terms
of accuracy.",
acknowledgement = ack-nhfb,
articleno = "25",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2018:EUE,
author = "Christian S. Jensen",
title = "Editorial: Updates to the {Editorial Board}",
journal = j-TODS,
volume = "43",
number = "1",
pages = "1:1--1:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3183376",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Demertzis:2018:PPR,
author = "Ioannis Demertzis and Stavros Papadopoulos and
Odysseas Papapetrou and Antonios Deligiannakis and
Minos Garofalakis and Charalampos Papamanthou",
title = "Practical Private Range Search in Depth",
journal = j-TODS,
volume = "43",
number = "1",
pages = "2:1--2:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3167971",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We consider a data owner that outsources its dataset
to an untrusted server. The owner wishes to enable the
server to answer range queries on a single attribute,
without compromising the privacy of the data and the
queries. There are several schemes on ``practical''
private range search (mainly in database venues) that
attempt to strike a trade-off between efficiency and
security. Nevertheless, these methods either lack
provable security guarantees or permit unacceptable
privacy leakages. In this article, we take an
interdisciplinary approach, which combines the rigor of
security formulations and proofs with efficient data
management techniques. We construct a wide set of novel
schemes with realistic security/performance trade-offs,
adopting the notion of Searchable Symmetric Encryption
(SSE), primarily proposed for keyword search. We reduce
range search to multi-keyword search using
range-covering techniques with tree-like indexes, and
formalize the problem as Range Searchable Symmetric
Encryption (RSSE). We demonstrate that, given any
secure SSE scheme, the challenge boils down to (i)
formulating leakages that arise from the index
structure and (ii) minimizing false positives incurred
by some schemes under heavy data skew. We also explain
an important concept in the recent SSE bibliography,
namely locality, and design generic and specialized
ways to attribute locality to our RSSE schemes.
Moreover, we are the first to devise secure schemes for
answering range aggregate queries, such as range sums
and range min/max. We analytically detail the
superiority of our proposals over prior work and
experimentally confirm their practicality.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Chung:2018:EIU,
author = "Yeounoh Chung and Michael Lind Mortensen and Carsten
Binnig and Tim Kraska",
title = "Estimating the Impact of Unknown Unknowns on Aggregate
Query Results",
journal = j-TODS,
volume = "43",
number = "1",
pages = "3:1--3:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3167970",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "It is common practice for data scientists to acquire
and integrate disparate data sources to achieve higher
quality results. But even with a perfectly cleaned and
merged data set, two fundamental questions remain: (1)
Is the integrated data set complete? and (2) What is
the impact of any unknown (i.e., unobserved) data on
query results? In this work, we develop and analyze
techniques to estimate the impact of the unknown data
(a.k.a., unknown unknowns ) on simple aggregate
queries. The key idea is that the overlap between
different data sources enables us to estimate the
number and values of the missing data items. Our main
techniques are parameter-free and do not assume prior
knowledge about the distribution; we also propose a
parametric model that can be used instead when the data
sources are imbalanced. Through a series of
experiments, we show that estimating the impact of
unknown unknowns is invaluable to better assess the
results of aggregate queries over integrated data
sources.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Shaikhha:2018:BEQ,
author = "Amir Shaikhha and Yannis Klonatos and Christoph Koch",
title = "Building Efficient Query Engines in a High-Level
Language",
journal = j-TODS,
volume = "43",
number = "1",
pages = "4:1--4:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3183653",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Abstraction without regret refers to the vision of
using high-level programming languages for systems
development without experiencing a negative impact on
performance. A database system designed according to
this vision offers both increased productivity and high
performance instead of sacrificing the former for the
latter as is the case with existing, monolithic
implementations that are hard to maintain and extend.
In this article, we realize this vision in the domain
of analytical query processing. We present LegoBase, a
query engine written in the high-level programming
language Scala. The key technique to regain efficiency
is to apply generative programming: LegoBase performs
source-to-source compilation and optimizes database
systems code by converting the high-level Scala code to
specialized, low-level C code. We show how generative
programming allows to easily implement a wide spectrum
of optimizations, such as introducing data partitioning
or switching from a row to a column data layout, which
are difficult to achieve with existing low-level query
compilers that handle only queries. We demonstrate that
sufficiently powerful abstractions are essential for
dealing with the complexity of the optimization effort,
shielding developers from compiler internals and
decoupling individual optimizations from each other. We
evaluate our approach with the TPC-H benchmark and show
that (a) with all optimizations enabled, our
architecture significantly outperforms a commercial
in-memory database as well as an existing query
compiler. (b) Programmers need to provide just a few
hundred lines of high-level code for implementing the
optimizations, instead of complicated low-level code
that is required by existing query compilation
approaches. (c) These optimizations may potentially
come at the cost of using more system memory for
improved performance. (d) The compilation overhead is
low compared to the overall execution time, thus making
our approach usable in practice for compiling query
engines.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Libkin:2018:TNA,
author = "Leonid Libkin and Juan L. Reutter and Adri{\'a}n Soto
and Domagoj Vrgoc",
title = "{TriAL}: a Navigational Algebra for {RDF}
Triplestores",
journal = j-TODS,
volume = "43",
number = "1",
pages = "5:1--5:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3154385",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/string-matching.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Navigational queries over RDF data are viewed as one
of the main applications of graph query languages, and
yet the standard model of graph databases ---
essentially labeled graphs --- is different from the
triples-based model of RDF. While encodings of RDF
databases into graph data exist, we show that even the
most natural ones are bound to lose some functionality
when used in conjunction with graph query
languages. The solution is to work directly with
triples, but then many properties taken for granted in
the graph database context (e.g., reachability) lose
their natural meaning. Our goal is to introduce
languages that work directly over triples and are
closed, i.e., they produce sets of triples, rather than
graphs. Our basic language is called TriAL, or Triple
Algebra: it guarantees closure properties by replacing
the product with a family of join operations. We extend
TriAL with recursion and explain why such an extension
is more intricate for triples than for graphs. We
present a declarative language, namely a fragment of
datalog, capturing the recursive algebra. For both
languages, the combined complexity of query evaluation
is given by low-degree polynomials. We compare our
language with previously studied graph query languages
such as adaptations of XPath, regular path queries, and
nested regular expressions; many of these languages are
subsumed by the recursive triple algebra. We also
provide an implementation of recursive TriAL on top of
a relational query engine, and we show its usefulness
by running a wide array of navigational queries over
real-world RDF data, while at the same time testing how
our implementation compares to existing RDF systems.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Cao:2018:BQR,
author = "Yang Cao and Wenfei Fan and Floris Geerts and Ping
Lu",
title = "Bounded Query Rewriting Using Views",
journal = j-TODS,
volume = "43",
number = "1",
pages = "6:1--6:??",
month = apr,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3183673",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Apr 11 18:02:25 MDT 2018",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "A query $Q$ in a language $L$ has a bounded rewriting
using a set of $L$-definable views if there exists a
query $ Q^'$ in $L$ such that given any dataset $D$, $
Q(D)$ can be computed by $ Q_'$ that accesses only
cached views and a small fraction $ D_Q$ of $D$. We
consider datasets $D$ that satisfy a set of access
constraints, which are a combination of simple
cardinality constraints and associated indices, such
that the size $ |D_Q|$ of $ D_Q$ and the time to
identify $ D_Q$ are independent of $ |D|$, no matter
how big $D$ is. In this article, we study the problem
for deciding whether a query has a bounded rewriting
given a set $V$ of views and a set $A$ of access
constraints. We establish the complexity of the problem
for various query languages $L$, from $
\Sigma_3^p$-complete for conjunctive queries (CQ) to
undecidable for relational algebra (FO). We show that
the intractability for CQ is rather robust even for
acyclic CQ with fixed $V$ and $A$, and characterize
when the problem is in PTIME. To make practical use of
bounded rewriting, we provide an effective syntax for
FO queries that have a bounded rewriting. The syntax
characterizes a key subclass of such queries without
sacrificing the expressive power, and can be checked in
PTIME. Finally, we investigate $ L_1$-to-$ L_2$ bounded
rewriting, when Q in $ L_1$ is allowed to be rewritten
into a query $ Q^'$ in another language $ L_2$. We show
that this relaxation does not simplify the analysis of
bounded query rewriting using views.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Berkholz:2018:AFQ,
author = "Christoph Berkholz and Jens Keppeler and Nicole
Schweikardt",
title = "Answering {FO+MOD} Queries under Updates on Bounded
Degree Databases",
journal = j-TODS,
volume = "43",
number = "2",
pages = "7:1--7:??",
month = sep,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3232056",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "We investigate the query evaluation problem for fixed
queries over fully dynamic databases, where tuples can
be inserted or deleted. The task is to design a dynamic
algorithm that immediately reports the new result of a
fixed query after every database update. We consider
queries in first-order logic (FO) and its extension
with modulo-counting quantifiers (FO+MOD) and show that
they can be efficiently evaluated under updates,
provided that the dynamic database does not exceed a
certain degree bound. In particular, we construct a
data structure that allows us to answer a Boolean
FO+MOD query and to compute the size of the result of a
non-Boolean query within constant time after every
database update. Furthermore, after every database
update, we can update the data structure in constant
time such that afterwards we are able to test within
constant time for a given tuple whether or not it
belongs to the query result, to enumerate all tuples in
the new query result, and to enumerate the difference
between the old and the new query result with constant
delay between the output tuples. The preprocessing time
needed to build the data structure is linear in the
size of the database. Our results extend earlier work
on the evaluation of first-order queries on static
databases of bounded degree and rely on an effective
Hanf normal form for FO+MOD recently obtained by
Heimberg, Kuske, and Schweikardt (LICS 2016).",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Barcelo:2018:EES,
author = "Pablo Barcel{\'o} and Markus Kr{\"o}ll and Reinhard
Pichler and Sebastian Skritek",
title = "Efficient Evaluation and Static Analysis for
Well-Designed Pattern Trees with Projection",
journal = j-TODS,
volume = "43",
number = "2",
pages = "8:1--8:??",
month = sep,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3233983",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Conjunctive queries (CQs) fail to provide an answer
when the pattern described by the query does not
exactly match the data. CQs might thus be too
restrictive as a querying mechanism when data is
semistructured or incomplete. The semantic web
therefore provides a formalism-known as (projected)
well-designed pattern trees (pWDPTs)-that tackles this
problem: pWDPTs allow us to formulate queries that
match parts of the query over the data if available,
but do not ignore answers of the remaining query
otherwise. Here we abstract away the specifics of
semantic web applications and study pWDPTs over
arbitrary relational schemas. Since the language of
pWDPTs subsumes CQs, their evaluation problem is
intractable. We identify structural properties of
pWDPTs that lead to (fixed-parameter) tractability of
various variants of the evaluation problem. We also
show that checking if a pWDPT is equivalent to one in
our tractable class is in 2EXPTIME. As a corollary, we
obtain fixed-parameter tractability of evaluation for
pWDPTs with such good behavior. Our techniques also
allow us to develop a theory of approximations for
pWDPTs.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Lazerson:2018:LMD,
author = "Arnon Lazerson and Daniel Keren and Assaf Schuster",
title = "Lightweight Monitoring of Distributed Streams",
journal = j-TODS,
volume = "43",
number = "2",
pages = "9:1--9:??",
month = sep,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3226113",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "As data becomes dynamic, large, and distributed, there
is increasing demand for what have become known as
distributed stream algorithms. Since continuously
collecting the data to a central server and processing
it there is infeasible, a common approach is to define
local conditions at the distributed nodes, such that-as
long as they are maintained-some desirable global
condition holds. Previous methods derived local
conditions focusing on communication efficiency. While
proving very useful for reducing the communication
volume, these local conditions often suffer from heavy
computational burden at the nodes. The computational
complexity of the local conditions affects both the
runtime and the energy consumption. These are
especially critical for resource-limited devices like
smartphones and sensor nodes. Such devices are becoming
more ubiquitous due to the recent trend toward smart
cities and the Internet of Things. To accommodate for
high data rates and limited resources of these devices,
it is crucial that the local conditions be quickly and
efficiently evaluated. Here we propose a novel
approach, designated CB (for Convex/Concave Bounds). CB
defines local conditions using suitably chosen convex
and concave functions. Lightweight and simple, these
local conditions can be rapidly checked on the fly.
CB's superiority over the state-of-the-art is
demonstrated in its reduced runtime and power
consumption, by up to six orders of magnitude in some
cases. As an added bonus, CB also reduced communication
overhead in all the tested application scenarios.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Qi:2018:RQU,
author = "Jianzhong Qi and Fei Zuo and Hanan Samet and Jia Cheng
Yao",
title = "{$K$}-Regret Queries Using Multiplicative Utility
Functions",
journal = j-TODS,
volume = "43",
number = "2",
pages = "10:1--10:??",
month = sep,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3230634",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:12 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The k -regret query aims to return a size- k subset S
of a database D such that, for any query user that
selects a data object from this size- k subset S rather
than from database D, her regret ratio is minimized.
The regret ratio here is modeled by the relative
difference in the optimality between the locally
optimal object in S and the globally optimal object in
D. The optimality of a data object in turn is modeled
by a utility function of the query user. Unlike
traditional top- k queries, the k -regret query does
not minimize the regret ratio for a specific utility
function. Instead, it considers a family of infinite
utility functions F, and aims to find a size- k subset
that minimizes the maximum regret ratio of any utility
function in F. Studies on k -regret queries have
focused on the family of additive utility functions,
which have limitations in modeling individuals'
preferences and decision-making processes, especially
for a common observation called the diminishing
marginal rate of substitution (DMRS). We introduce k
-regret queries with multiplicative utility functions,
which are more expressive in modeling the DMRS, to
overcome those limitations. We propose a query
algorithm with bounded regret ratios. To showcase the
applicability of the algorithm, we apply it to a
special family of multiplicative utility functions, the
Cobb--Douglas family of utility functions, and a
closely related family of utility functions, the
Constant Elasticity of Substitution family of utility
functions, both of which are frequently used utility
functions in microeconomics. After a further study of
the query properties, we propose a heuristic algorithm
that produces even smaller regret ratios in practice.
Extensive experiments on the proposed algorithms
confirm that they consistently achieve small maximum
regret ratios.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kimelfeld:2018:RFC,
author = "Benny Kimelfeld and Christopher R{\'e}",
title = "A Relational Framework for Classifier Engineering",
journal = j-TODS,
volume = "43",
number = "3",
pages = "11:1--11:??",
month = nov,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3268931",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:13 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In the design of analytical procedures and machine
learning solutions, a critical and time-consuming task
is that of feature engineering, for which various
recipes and tooling approaches have been developed. In
this article, we embark on the establishment of
database foundations for feature engineering. We
propose a formal framework for classification in the
context of a relational database. The goal of this
framework is to open the way to research and techniques
to assist developers with the task of feature
engineering by utilizing the database's modeling and
understanding of data and queries and by deploying the
well-studied principles of database management. As a
first step, we demonstrate the usefulness of this
framework by formally defining three key algorithmic
challenges. The first challenge is that of
separability, which is the problem of determining the
existence of feature queries that agree with the
training examples. The second is that of evaluating the
VC dimension of the model class with respect to a given
sequence of feature queries. The third challenge is
identifiability, which is the task of testing for a
property of independence among features that are
represented as database queries. We give preliminary
results on these challenges for the case where features
are defined by means of conjunctive queries, and, in
particular, we study the implication of various
traditional syntactic restrictions on the inherent
computational complexity.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Schwentick:2018:DCU,
author = "Thomas Schwentick and Nils Vortmeier and Thomas
Zeume",
title = "Dynamic Complexity under Definable Changes",
journal = j-TODS,
volume = "43",
number = "3",
pages = "12:1--12:??",
month = nov,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3241040",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:13 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In the setting of dynamic complexity, the goal of a
dynamic program is to maintain the result of a fixed
query for an input database that is subject to changes,
possibly using additional auxiliary relations. In other
words, a dynamic program updates a materialized view
whenever a base relation is changed. The update of
query result and auxiliary relations is specified using
first-order logic or, equivalently, relational algebra.
The original framework by Patnaik and Immerman only
considers changes to the database that insert or delete
single tuples. This article extends the setting to
definable changes, also specified by first-order
queries on the database, and generalizes previous
maintenance results to these more expressive change
operations. More specifically, it is shown that the
undirected reachability query is first-order
maintainable under single-tuple changes and first-order
defined insertions, likewise the directed reachability
query for directed acyclic graphs is first-order
maintainable under insertions defined by
quantifier-free first-order queries. These results rely
on bounded bridge properties, which basically say that,
after an insertion of a defined set of edges, for each
connected pair of nodes there is some path with a
bounded number of new edges. While this bound can be
huge, in general, it is shown to be small for insertion
queries defined by unions of conjunctive queries. To
illustrate that the results for this restricted setting
could be practically relevant, they are complemented by
an experimental study that compares the performance of
dynamic programs with complex changes, dynamic programs
with single changes, and with recomputation from
scratch. The positive results are complemented by
several inexpressibility results. For example, it is
shown that-unlike for single-tuple insertions-dynamic
programs that maintain the reachability query under
definable, quantifier-free changes strictly need update
formulas with quantifiers. Finally, further positive
results unrelated to reachability are presented: it is
shown that for changes definable by parameter-free
first-order formulas, all LOGSPACE-definable (and even
AC$^1$-definable) queries can be maintained by
first-order dynamic programs.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Arenas:2018:ELQ,
author = "Marcelo Arenas and Georg Gottlob and Andreas Pieris",
title = "Expressive Languages for Querying the {Semantic Web}",
journal = j-TODS,
volume = "43",
number = "3",
pages = "13:1--13:??",
month = nov,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3238304",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:13 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "The problem of querying RDF data is a central issue
for the development of the Semantic Web. The query
language SPARQL has become the standard language for
querying RDF since its W3C standardization in 2008.
However, the 2008 version of this language missed some
important functionalities: reasoning capabilities to
deal with RDFS and OWL vocabularies, navigational
capabilities to exploit the graph structure of RDF
data, and a general form of recursion much needed to
express some natural queries. To overcome these
limitations, a new version of SPARQL, called SPARQL
1.1, was released in 2013, which includes entailment
regimes for RDFS and OWL vocabularies, and a mechanism
to express navigation patterns through regular
expressions. Unfortunately, there are a number of
useful navigation patterns that cannot be expressed in
SPARQL 1.1, and the language lacks a general mechanism
to express recursive queries. To the best of our
knowledge, no efficient RDF query language that
combines the above functionalities is known. It is the
aim of this work to fill this gap. To this end, we
focus on a core fragment of the OWL 2 QL profile of OWL
2 and show that every SPARQL query enriched with the
above features can be naturally translated into a query
expressed in a language that is based on an extension
of Datalog, which allows for value invention and
stratified negation. However, the query evaluation
problem for this language is highly intractable, which
is not surprising since it is expressive enough to
encode some inherently hard queries. We identify a
natural fragment of it, and we show it to be tractable
and powerful enough to define SPARQL queries enhanced
with the desired functionalities.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Polychroniou:2018:DJD,
author = "Orestis Polychroniou and Wangda Zhang and Kenneth A.
Ross",
title = "Distributed Joins and Data Placement for Minimal
Network Traffic",
journal = j-TODS,
volume = "43",
number = "3",
pages = "14:1--14:??",
month = nov,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3241039",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:13 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Network communication is the slowest component of many
operators in distributed parallel databases deployed
for large-scale analytics. Whereas considerable work
has focused on speeding up databases on modern
hardware, communication reduction has received less
attention. Existing parallel DBMSs rely on algorithms
designed for disks with minor modifications for
networks. A more complicated algorithm may burden the
CPUs but could avoid redundant transfers of tuples
across the network. We introduce track join, a new
distributed join algorithm that minimizes network
traffic by generating an optimal transfer schedule for
each distinct join key. Track join extends the
trade-off options between CPU and network. Track join
explicitly detects and exploits locality, also allowing
for advanced placement of tuples beyond hash
partitioning on a single attribute. We propose a novel
data placement algorithm based on track join that
minimizes the total network cost of multiple joins
across different dimensions in an analytical workload.
Our evaluation shows that track join outperforms hash
join on the most expensive queries of real workloads
regarding both network traffic and execution time.
Finally, we show that our data placement optimization
approach is both robust and effective in minimizing the
total network cost of joins in analytical workloads.",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Abuzaid:2018:MPA,
author = "Firas Abuzaid and Peter Bailis and Jialin Ding and
Edward Gan and Samuel Madden and Deepak Narayanan and
Kexin Rong and Sahaana Suri",
title = "{MacroBase}: Prioritizing Attention in Fast Data",
journal = j-TODS,
volume = "43",
number = "4",
pages = "15:1--15:??",
month = dec,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3276463",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "As data volumes continue to rise, manual inspection is
becoming increasingly untenable. In response, we
present MacroBase, a data analytics engine that
prioritizes end-user attention in high-volume fast data
streams. MacroBase enables efficient, accurate, and
modular analyses that highlight and aggregate important
and unusual behavior, acting as a search engine for
fast data. MacroBase is able to deliver
order-of-magnitude speedups over alternatives by
optimizing the combination of explanation (i.e.,
feature selection) and classification tasks and by
leveraging a new reservoir sampler and heavy-hitters
sketch specialized for fast data streams. As a result,
MacroBase delivers accurate results at speeds of up to
2M events per second per query on a single core. The
system has delivered meaningful results in production,
including at a telematics company monitoring hundreds
of thousands of vehicles.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dayan:2018:OBF,
author = "Niv Dayan and Manos Athanassoulis and Stratos Idreos",
title = "Optimal {Bloom} Filters and Adaptive Merging for
{LSM}-Trees",
journal = j-TODS,
volume = "43",
number = "4",
pages = "16:1--16:??",
month = dec,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3276980",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "In this article, we show that key-value stores backed
by a log-structured merge-tree (LSM-tree) exhibit an
intrinsic tradeoff between lookup cost, update cost,
and main memory footprint, yet all existing designs
expose a suboptimal and difficult to tune tradeoff
among these metrics. We pinpoint the problem to the
fact that modern key-value stores suboptimally co-tune
the merge policy, the buffer size, and the Bloom
filters' false-positive rates across the LSM-tree's
different levels. We present Monkey, an LSM-tree based
key-value store that strikes the optimal balance
between the costs of updates and lookups with any given
main memory budget. The core insight is that worst-case
lookup cost is proportional to the sum of the
false-positive rates of the Bloom filters across all
levels of the LSM-tree. Contrary to state-of-the-art
key-value stores that assign a fixed number of
bits-per-element to all Bloom filters, Monkey allocates
memory to filters across different levels so as to
minimize the sum of their false-positive rates. We show
analytically that Monkey reduces the asymptotic
complexity of the worst-case lookup I/O cost, and we
verify empirically using an implementation on top of
RocksDB that Monkey reduces lookup latency by an
increasing margin as the data volume grows (50--80\%
for the data sizes we experimented with). Furthermore,
we map the design space onto a closed-form model that
enables adapting the merging frequency and memory
allocation to strike the best tradeoff among lookup
cost, update cost and main memory, depending on the
workload (proportion of lookups and updates), the
dataset (number and size of entries), and the
underlying hardware (main memory available, disk vs.
flash). We show how to use this model to answer what-if
design questions about how changes in environmental
parameters impact performance and how to adapt the
design of the key-value store for optimal
performance.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Meneghetti:2018:LQA,
author = "Niccol{\`o} Meneghetti and Oliver Kennedy and Wolfgang
Gatterbauer",
title = "Learning From Query-Answers: a Scalable Approach to
Belief Updating and Parameter Learning",
journal = j-TODS,
volume = "43",
number = "4",
pages = "17:1--17:??",
month = dec,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3277503",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Tuple-independent and disjoint-independent
probabilistic databases (TI- and DI-PDBs) represent
uncertain data in a factorized form as a product of
independent random variables that represent either
tuples (TI-PDBs) or sets of tuples (DI-PDBs). When the
user submits a query, the database derives the marginal
probabilities of each output-tuple, exploiting the
underlying assumptions of statistical independence.
While query processing in TI- and DI-PDBs has been
studied extensively, limited research has been
dedicated to the problems of updating or deriving the
parameters from observations of query results.
Addressing this problem is the main focus of this
article. We first introduce Beta Probabilistic
Databases (B-PDBs), a generalization of TI-PDBs
designed to support both (i) belief updating and (ii)
parameter learning in a principled and scalable way.
The key idea of B-PDBs is to treat each parameter as a
latent, Beta-distributed random variable. We show how
this simple expedient enables both belief updating and
parameter learning in a principled way, without
imposing any burden on regular query processing.
Building on B-PDBs, we then introduce Dirichlet
Probabilistic Databases (D-PDBs), a generalization of
DI-PDBs with similar properties. We provide the
following key contributions for both B- and D-PDBs: (i)
We study the complexity of performing Bayesian belief
updates and devise efficient algorithms for certain
tractable classes of queries; (ii) we propose a soft-EM
algorithm for computing maximum-likelihood estimates of
the parameters; (iii) we present an algorithm for
efficiently computing conditional probabilities,
allowing us to efficiently implement B- and D-PDBs via
a standard relational engine; and (iv) we support our
conclusions with extensive experimental results.",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2018:PSG,
author = "Wenfei Fan and Wenyuan Yu and Jingbo Xu and Jingren
Zhou and Xiaojian Luo and Qiang Yin and Ping Lu and
Yang Cao and Ruiqi Xu",
title = "Parallelizing Sequential Graph Computations",
journal = j-TODS,
volume = "43",
number = "4",
pages = "18:1--18:??",
month = dec,
year = "2018",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3282488",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This article presents GRAPE, a parallel GRAPhEngine
for graph computations. GRAPE differs from prior
systems in its ability to parallelize existing
sequential graph algorithms as a whole, without the
need for recasting the entire algorithm into a new
model. Underlying GRAPE are a simple programming model
and a principled approach based on fixpoint computation
that starts with partial evaluation and uses an
incremental function as the intermediate consequence
operator. We show that users can devise existing
sequential graph algorithms with minor additions, and
GRAPE parallelizes the computation. Under a monotonic
condition, the GRAPE parallelization guarantees to
converge at correct answers as long as the sequential
algorithms are correct. Moreover, we show that
algorithms in MapReduce, BSP, and PRAM can be optimally
simulated on GRAPE. In addition to the ease of
programming, we experimentally verify that GRAPE
achieves comparable performance to the state-of-the-art
graph systems using real-life and synthetic graphs.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Kipf:2019:SAF,
author = "Andreas Kipf and Varun Pandey and Jan B{\"o}ttcher and
Lucas Braun and Thomas Neumann and Alfons Kemper",
title = "Scalable Analytics on Fast Data",
journal = j-TODS,
volume = "44",
number = "1",
pages = "1:1--1:??",
month = jan,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3283811",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Today's streaming applications demand increasingly
high event throughput rates and are often subject to
strict latency constraints. To allow for more complex
workloads, such as window-based aggregations, streaming
systems need to support stateful event processing. This
introduces new challenges for streaming engines as the
state needs to be maintained in a consistent and
durable manner and simultaneously accessed by complex
queries for real-time analytics. Modern streaming
systems, such as Apache Flink, do not allow for
efficiently exposing the state to analytical queries.
Thus, data engineers are forced to keep the state in
external data stores, which significantly increases the
latencies until events become visible to analytical
queries. Proprietary solutions have been created to
meet data freshness constraints. These solutions are
expensive, error-prone, and difficult to maintain.
Main-memory database systems, such as HyPer, achieve
extremely low query response times while maintaining
high update rates, which makes them well-suited for
analytical streaming workloads. In this article, we
explore extensions to database systems to match the
performance and usability of streaming systems.",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Li:2019:WJX,
author = "Feifei Li and Bin Wu and Ke Yi and Zhuoyue Zhao",
title = "Wander Join and {XDB}: Online Aggregation via Random
Walks",
journal = j-TODS,
volume = "44",
number = "1",
pages = "2:1--2:??",
month = jan,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3284551",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Joins are expensive, and online aggregation over joins
was proposed to mitigate the cost, which offers users a
nice and flexible tradeoff between query efficiency and
accuracy in a continuous, online fashion. However, the
state-of-the-art approach, in both internal and
external memory, is based on ripple join, which is
still very expensive and even needs unrealistic
assumptions (e.g., tuples in a table are stored in
random order). This article proposes a new approach,
the wander join algorithm, to the online aggregation
problem by performing random walks over the underlying
join graph. We also design an optimizer that chooses
the optimal plan for conducting the random walks
without having to collect any statistics a priori.
Compared with ripple join, wander join is particularly
efficient for equality joins involving multiple tables,
but also supports $ \theta $-joins. Selection
predicates and group-by clauses can be handled as well.
To demonstrate the usefulness of wander join, we have
designed and implemented XDB (approXimate DB) by
integrating wander join into various systems including
PostgreSQL, Spark, and a stand-alone plug-in version
using PL/SQL. The design and implementation of XDB has
demonstrated wander join's practicality in a
full-fledged database system. Extensive experiments
using the TPC-H benchmark have demonstrated the
superior performance of wander join over ripple join.",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bai:2019:HMD,
author = "Ran Bai and Wing Kai Hon and Eric Lo and Zhian He and
Kenny Zhu",
title = "Historic Moments Discovery in Sequence Data",
journal = j-TODS,
volume = "44",
number = "1",
pages = "3:1--3:??",
month = jan,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3276975",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Many emerging applications are based on finding
interesting subsequences from sequence data. Finding
``prominent streaks,'' a set of the longest contiguous
subsequences with values all above (or below) a certain
threshold, from sequence data is one of that kind that
receives much attention. Motivated from real
applications, we observe that prominent streaks alone
are not insightful enough but require the discovery of
something we coined as ``historic moments'' as
companions. In this article, we present an algorithm to
efficiently compute historic moments from sequence
data. The algorithm is incremental and space optimal,
meaning that when facing new data arrival, it is able
to efficiently refresh the results by keeping minimal
information. Case studies show that historic moments
can significantly improve the insights offered by
prominent streaks alone. Furthermore, experiments show
that our algorithm can outperform the baseline in both
time and space.",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Alexandrov:2019:ROE,
author = "Alexander Alexandrov and Georgi Krastev and Volker
Markl",
title = "Representations and Optimizations for Embedded
Parallel Dataflow Languages",
journal = j-TODS,
volume = "44",
number = "1",
pages = "4:1--4:??",
month = jan,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3281629",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 29 17:36:16 MST 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "Parallel dataflow engines such as Apache Hadoop,
Apache Spark, and Apache Flink are an established
alternative to relational databases for modern data
analysis applications. A characteristic of these
systems is a scalable programming model based on
distributed collections and parallel transformations
expressed by means of second-order functions such as
map and reduce. Notable examples are Flink's DataSet
and Spark's RDD programming abstractions. These
programming models are realized as EDSLs-domain
specific languages embedded in a general-purpose host
language such as Java, Scala, or Python. This approach
has several advantages over traditional external DSLs
such as SQL or XQuery. First, syntactic constructs from
the host language (e.g., anonymous functions syntax,
value definitions, and fluent syntax via method
chaining) can be reused in the EDSL. This eases the
learning curve for developers already familiar with the
host language. Second, it allows for seamless
integration of library methods written in the host
language via the function parameters passed to the
parallel dataflow operators. This reduces the effort
for developing analytics dataflows that go beyond pure
SQL and require domain-specific logic. At the same
time, however, state-of-the-art parallel dataflow EDSLs
exhibit a number of shortcomings. First, one of the
main advantages of an external DSL such as SQL-the
high-level, declarative Select-From-Where syntax-is
either lost completely or mimicked in a non-standard
way. Second, execution aspects such as caching, join
order, and partial aggregation have to be decided by
the programmer. Optimizing them automatically is very
difficult due to the limited program context available
in the intermediate representation of the DSL. In this
article, we argue that the limitations listed above are
a side effect of the adopted type-based embedding
approach. As a solution, we propose an alternative EDSL
design based on quotations. We present a DSL embedded
in Scala and discuss its compiler pipeline,
intermediate representation, and some of the enabled
optimizations. We promote the algebraic type of bags in
union representation as a model for distributed
collections and its associated structural recursion
scheme and monad as a model for parallel collection
processing. At the source code level, Scala's
comprehension syntax over a bag monad can be used to
encode Select-From-Where expressions in a standard way.
At the intermediate representation level, maintaining
comprehensions as a first-class citizen can be used to
simplify the design and implementation of holistic
dataflow optimizations that accommodate for nesting and
control-flow. The proposed DSL design therefore
reconciles the benefits of embedded parallel dataflow
DSLs with the declarativity and optimization potential
of external DSLs like SQL.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Fan:2019:DG,
author = "Wenfei Fan and Ping Lu",
title = "Dependencies for Graphs",
journal = j-TODS,
volume = "44",
number = "2",
pages = "5:1--5:??",
month = apr,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3287285",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:20 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3287285",
abstract = "This article proposes a class of dependencies for
graphs, referred to as graph entity dependencies
(GEDs). A GED is defined as a combination of a graph
pattern and an attribute dependency. In a uniform
format, GEDs can express graph functional dependencies
with constant literals to catch inconsistencies, and
keys carrying id literals to identify entities
(vertices) in a graph. We revise the chase for GEDs and
prove its Church--Rosser property. We characterize GED
satisfiability and implication, and establish the
complexity of these problems and the validation problem
for GEDs, in the presence and absence of constant
literals and id literals. We also develop a sound,
complete and independent axiom system for finite
implication of GEDs. In addition, we extend GEDs with
built-in predicates or disjunctions, to strike a
balance between the expressive power and complexity. We
settle the complexity of the satisfiability,
implication, and validation problems for these
extensions.",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Hu:2019:OOM,
author = "Xiao Hu and Ke Yi and Yufei Tao",
title = "Output-Optimal Massively Parallel Algorithms for
Similarity Joins",
journal = j-TODS,
volume = "44",
number = "2",
pages = "6:1--6:??",
month = apr,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3311967",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:20 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3311967",
abstract = "Parallel join algorithms have received much attention
in recent years due to the rapid development of
massively parallel systems such as MapReduce and Spark.
In the database theory community, most efforts have
been focused on studying worst-case optimal algorithms.
However, the worst-case optimality of these join
algorithms relies on the hard instances having very
large output sizes. In the case of a two-relation join,
the hard instance is just a Cartesian product, with an
output size that is quadratic in the input size. In
practice, however, the output size is usually much
smaller. One recent parallel join algorithm by Beame et
al. has achieved output-optimality (i.e., its cost is
optimal in terms of both the input size and the output
size), but their algorithm only works for a 2-relation
equi-join and has some imperfections. In this article,
we first improve their algorithm to true optimality.
Then we design output-optimal algorithms for a large
class of similarity joins. Finally, we present a lower
bound, which essentially eliminates the possibility of
having output-optimal algorithms for any join on more
than two relations.",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Dautrich:2019:IIT,
author = "Jonathan L. {Dautrich, Jr.} and Chinya V.
Ravishankar",
title = "Inferring Insertion Times and Optimizing Error
Penalties in Time-decaying {Bloom} Filters",
journal = j-TODS,
volume = "44",
number = "2",
pages = "7:1--7:??",
month = apr,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3284552",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:20 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3284552",
abstract = "Current Bloom Filters tend to ignore Bayesian priors
as well as a great deal of useful information they
hold, compromising the accuracy of their responses.
Incorrect responses cause users to incur penalties that
are both application- and item-specific, but current
Bloom Filters are typically tuned only for static
penalties. Such shortcomings are problematic for all
Bloom Filter variants, but especially so for
Time-decaying Bloom Filters, in which the memory of
older items decays over time, causing both false
positives and false negatives. We address these issues
by introducing inferential filters, which integrate
Bayesian priors and information latent in filters to
make penalty-optimal, query-specific decisions. We also
show how to properly infer insertion times in such
filters. Our methods are general, but here we
illustrate their application to inferential
time-decaying filters to support novel query types and
sliding window queries with dynamic error penalties. We
present inferential versions of the Timing Bloom Filter
and Generalized Bloom Filter. Our experiments on real
and synthetic datasets show that our methods reduce
penalties for incorrect responses to sliding-window
queries in these filters by up to 70\% when penalties
are dynamic.",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Gummidi:2019:SSC,
author = "Srinivasa Raghavendra Bhuvan Gummidi and Xike Xie and
Torben Bach Pedersen",
title = "A Survey of Spatial Crowdsourcing",
journal = j-TODS,
volume = "44",
number = "2",
pages = "8:1--8:??",
month = apr,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3291933",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:20 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3291933",
abstract = "Widespread use of advanced mobile devices has led to
the emergence of a new class of crowdsourcing called
spatial crowdsourcing. Spatial crowdsourcing advances
the potential of a crowd to perform tasks related to
real-world scenarios involving physical locations,
which were not feasible with conventional crowdsourcing
methods. The main feature of spatial crowdsourcing is
the presence of spatial tasks that require workers to
be physically present at a particular location for task
fulfillment. Research related to this new paradigm has
gained momentum in recent years, necessitating a
comprehensive survey to offer a bird's-eye view of the
current state of spatial crowdsourcing literature. In
this article, we discuss the spatial crowdsourcing
infrastructure and identify the fundamental differences
between spatial and conventional crowdsourcing.
Furthermore, we provide a comprehensive view of the
existing literature by introducing a taxonomy,
elucidate the issues/challenges faced by different
components of spatial crowdsourcing, and suggest
potential research directions for the future.",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Damme:2019:CES,
author = "Patrick Damme and Annett Ungeth{\"u}m and Juliana
Hildebrandt and Dirk Habich and Wolfgang Lehner",
title = "From a Comprehensive Experimental Survey to a
Cost-based Selection Strategy for Lightweight Integer
Compression Algorithms",
journal = j-TODS,
volume = "44",
number = "3",
pages = "9:1--9:??",
month = jun,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3323991",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/datacompression.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3323991",
abstract = "Lightweight integer compression algorithms are
frequently applied in in-memory database systems to
tackle the growing gap between processor speed and main
memory bandwidth. In recent years, the vectorization of
basic techniques such as delta coding and null
suppression has considerably enlarged the corpus of
available algorithms. As a result, today there is a
large number of algorithms to choose from, while
different algorithms are tailored to different data
characteristics. However, a comparative evaluation of
these algorithms with different data and hardware
characteristics has never been sufficiently conducted
in the literature. To close this gap, we conducted an
exhaustive experimental survey by evaluating several
state-of-the-art lightweight integer compression
algorithms as well as cascades of basic techniques. We
systematically investigated the influence of data as
well as hardware properties on the performance and the
compression rates. The evaluated algorithms are based
on publicly available implementations as well as our
own vectorized reimplementations. We summarize our
experimental findings leading to several new insights
and to the conclusion that there is no single-best
algorithm. Moreover, in this article, we also introduce
and evaluate a novel cost model for the selection of a
suitable lightweight integer compression algorithm for
a given dataset.",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Bonifati:2019:IMS,
author = "Angela Bonifati and Ugo Comignani and Emmanuel Coquery
and Romuald Thion",
title = "Interactive Mapping Specification with Exemplar
Tuples",
journal = j-TODS,
volume = "44",
number = "3",
pages = "10:1--10:??",
month = jun,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3321485",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3321485",
abstract = "While schema mapping specification is a cumbersome
task for data curation specialists, it becomes
unfeasible for non-expert users, who are unacquainted
with the semantics and languages of the involved
transformations. In this article, we present an
interactive framework for schema mapping specification
suited for non-expert users. The underlying key
intuition is to leverage a few exemplar tuples to infer
the underlying mappings and iterate the inference
process via simple user interactions under the form of
Boolean queries on the validity of the initial exemplar
tuples. The approaches available so far are mainly
assuming pairs of complete universal data examples,
which can be solely provided by data curation experts,
or are limited to poorly expressive mappings. We
present a quasi-lattice-based exploration of the space
of all possible mappings that satisfy arbitrary user
exemplar tuples. Along the exploration, we challenge
the user to retain the mappings that fit the user's
requirements at best and to dynamically prune the
exploration space, thus reducing the number of user
interactions. We prove that after the refinement
process, the obtained mappings are correct and
complete. We present an extensive experimental analysis
devoted to measure the feasibility of our interactive
mapping strategies and the inherent quality of the
obtained mappings.",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Beedkar:2019:UFF,
author = "Kaustubh Beedkar and Rainer Gemulla and Wim Martens",
title = "A Unified Framework for Frequent Sequence Mining with
Subsequence Constraints",
journal = j-TODS,
volume = "44",
number = "3",
pages = "11:1--11:??",
month = jun,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3321486",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3321486",
abstract = "Frequent sequence mining methods often make use of
constraints to control which subsequences should be
mined. A variety of such subsequence constraints has
been studied in the literature, including length, gap,
span, regular-expression, and hierarchy constraints. In
this article, we show that many subsequence
constraints-including and beyond those considered in
the literature-can be unified in a single framework. A
unified treatment allows researchers to study jointly
many types of subsequence constraints (instead of each
one individually) and helps to improve usability of
pattern mining systems for practitioners. In more
detail, we propose a set of simple and intuitive
``pattern expressions'' to describe subsequence
constraints and explore algorithms for efficiently
mining frequent subsequences under such general
constraints. Our algorithms translate pattern
expressions to succinct finite-state transducers, which
we use as computational model, and simulate these
transducers in a way suitable for frequent sequence
mining. Our experimental study on real-world datasets
indicates that our algorithms-although more general-are
efficient and, when used for sequence mining with prior
constraints studied in literature, competitive to (and
in some cases superior to) state-of-the-art specialized
methods.",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Deutsch:2019:VHA,
author = "Alin Deutsch and Yuliang Li and Victor Vianu",
title = "Verification of Hierarchical Artifact Systems",
journal = j-TODS,
volume = "44",
number = "3",
pages = "12:1--12:??",
month = jun,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3321487",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3321487",
abstract = "Data-driven workflows, of which IBM's Business
Artifacts are a prime exponent, have been successfully
deployed in practice, adopted in industrial standards,
and have spawned a rich body of research in academia,
focused primarily on static analysis. The present work
represents a significant advance on the problem of
artifact verification by considering a much richer and
more realistic model than in previous work,
incorporating core elements of IBM's successful
Guard-Stage-Milestone model. In particular, the model
features task hierarchy, concurrency, and richer
artifact data. It also allows database key and foreign
key dependencies, as well as arithmetic constraints.
The results show decidability of verification and
establish its complexity, making use of novel
techniques including a hierarchy of Vector Addition
Systems and a variant of quantifier elimination
tailored to our context.",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Seidemann:2019:CHP,
author = "Marc Seidemann and Nikolaus Glombiewski and Michael
K{\"o}rber and Bernhard Seeger",
title = "{ChronicleDB}: a High-Performance Event Store",
journal = j-TODS,
volume = "44",
number = "4",
pages = "13:1--13:??",
month = oct,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3342357",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3342357",
abstract = "Reactive security monitoring, self-driving cars, the
Internet of Things (IoT), and many other novel
applications require systems for both writing events
arriving at very high and fluctuating rates to
persistent storage as well as supporting analytical ad
hoc queries. As standard database systems are not
capable of delivering the required write performance,
log-based systems, key-value stores, and other
write-optimized data stores have emerged recently.
However, the drawbacks of these systems are a fair
query performance and the lack of suitable instant
recovery mechanisms in case of system failures. In this
article, we present ChronicleDB, a novel database
system with a storage layout tailored for high write
performance under fluctuating data rates and powerful
indexing capabilities to support a variety of queries.
In addition, ChronicleDB offers low-cost fault
tolerance and instant recovery within milliseconds.
Unlike previous work, ChronicleDB is designed either as
a serverless library to be tightly integrated in an
application or as a standalone database server. Our
results of an experimental evaluation with real and
synthetic data reveal that ChronicleDB clearly
outperforms competing systems with respect to both
write and query performance.",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Brijder:2019:EPQ,
author = "Robert Brijder and Floris Geerts and Jan {Van Den
Bussche} and Timmy Weerwag",
title = "On the Expressive Power of Query Languages for
Matrices",
journal = j-TODS,
volume = "44",
number = "4",
pages = "15:1--15:??",
month = oct,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3331445",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3331445",
abstract = "We investigate the expressive power of MATLANG, a
formal language for matrix manipulation based on common
matrix operations and linear algebra. The language can
be extended with the operation inv for inverting a
matrix. In MATLANG + inv, we can compute the transitive
closure of directed graphs, whereas we show that this
is not possible without inversion. Indeed, we show that
the basic language can be simulated in the relational
algebra with arithmetic operations, grouping, and
summation. We also consider an operation eigen for
diagonalizing a matrix. It is defined such that for
each eigenvalue a set of mutually orthogonal
eigenvectors is returned that span the eigenspace of
that eigenvalue. We show that inv can be expressed in
MATLANG + eigen. We put forward the open question
whether there are Boolean queries about matrices, or
generic queries about graphs, expressible in MATLANG +
eigen but not in MATLANG + inv. Finally, the evaluation
problem for MATLANG + eigen is shown to be complete for
the complexity class $ \exists R $.",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Martens:2019:DES,
author = "Wim Martens and Tina Trautner",
title = "Dichotomies for Evaluating Simple Regular Path
Queries",
journal = j-TODS,
volume = "44",
number = "4",
pages = "16:1--16:??",
month = oct,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3331446",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3331446",
abstract = "Regular path queries (RPQs) are a central component of
graph databases. We investigate decision and
enumeration problems concerning the evaluation of RPQs
under several semantics that have recently been
considered: arbitrary paths, shortest paths, paths
without node repetitions (simple paths), and paths
without edge repetitions (trails). Whereas arbitrary
and shortest paths can be dealt with efficiently,
simple paths and trails become computationally
difficult already for very small RPQs. We study RPQ
evaluation for simple paths and trails from a
parameterized complexity perspective and define a class
of simple transitive expressions that is prominent in
practice and for which we can prove dichotomies for the
evaluation problem. We observe that, even though simple
path and trail semantics are intractable for RPQs in
general, they are feasible for the vast majority of
RPQs that are used in practice. At the heart of this
study is a result of independent interest: the two
disjoint paths problem in directed graphs is W[1]-hard
if parameterized by the length of one of the two
paths.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Wang:2019:EAA,
author = "Sibo Wang and Renchi Yang and Runhui Wang and Xiaokui
Xiao and Zhewei Wei and Wenqing Lin and Yin Yang and
Nan Tang",
title = "Efficient Algorithms for Approximate Single-Source
Personalized {PageRank} Queries",
journal = j-TODS,
volume = "44",
number = "4",
pages = "18:1--18:??",
month = oct,
year = "2019",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3360902",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Oct 29 10:55:21 MDT 2019",
bibsource = "https://www.math.utah.edu/pub/tex/bib/pagerank.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/ft_gateway.cfm?id=3360902",
abstract = "Given a graph G, a source node s, and a target node t,
the personalized PageRank ( PPR ) of t with respect to
s is the probability that a random walk starting from s
terminates at t. An important variant of the PPR query
is single-source PPR ( SSPPR ), which enumerates all
nodes in G and returns the top- k nodes with the
highest PPR values with respect to a given source s.
PPR in general and SSPPR in particular have important
applications in web search and social networks, e.g.,
in Twitter's Who-To-Follow recommendation service.
However, PPR computation is known to be expensive on
large graphs and resistant to indexing. Consequently,
previous solutions either use heuristics, which do not
guarantee result quality, or rely on the strong
computing power of modern data centers, which is
costly. Motivated by this, we propose effective
index-free and index-based algorithms for approximate
PPR processing, with rigorous guarantees on result
quality. We first present FORA, an approximate SSPPR
solution that combines two existing methods-Forward
Push (which is fast but does not guarantee quality) and
Monte Carlo Random Walk (accurate but slow)-in a simple
and yet non-trivial way, leading to both high accuracy
and efficiency. Further, FORA includes a simple and
effective indexing scheme, as well as a module for top-
k selection with high pruning power. Extensive
experiments demonstrate that the proposed solutions are
orders of magnitude more efficient than their
respective competitors. Notably, on a billion-edge
Twitter dataset, FORA answers a top-500 approximate
SSPPR query within 1s, using a single commodity
server.",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "http://portal.acm.org/browse_dl.cfm?idx=J777",
}
@Article{Jensen:2020:EUE,
author = "Christian S. Jensen",
title = "Editorial: Updates to the {Editorial Board}",
journal = j-TODS,
volume = "45",
number = "1",
pages = "1e:1--1e:1",
month = mar,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3381020",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 4 07:13:27 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3381020",
acknowledgement = ack-nhfb,
articleno = "1e",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{McCamish:2020:GTA,
author = "Ben McCamish and Vahid Ghadakchi and Arash Termehchy
and Behrouz Touri and Eduardo Cotilla-Sanchez and Liang
Huang and Soravit Changpinyo",
title = "A Game-theoretic Approach to Data Interaction",
journal = j-TODS,
volume = "45",
number = "1",
pages = "1:1--1:44",
month = mar,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3351450",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 4 07:13:27 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3351450",
abstract = "As most users do not precisely know the structure
and/or the content of databases, their queries do not
exactly reflect their information needs. The database
management system (DBMS) may interact with users and
use their feedback on the returned results \ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Zhang:2020:FDD,
author = "Dan Zhang and Ryan McKenna and Ios Kotsogiannis and
George Bissias and Michael Hay and Ashwin
Machanavajjhala and Gerome Miklau",
title = "{$ \epsilon $KTELO}: a Framework for Defining
Differentially Private Computations",
journal = j-TODS,
volume = "45",
number = "1",
pages = "2:1--2:44",
month = mar,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3362032",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 4 07:13:27 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3362032",
abstract = "The adoption of differential privacy is growing, but
the complexity of designing private, efficient, and
accurate algorithms is still high. We propose a novel
programming framework and system, $ \epsilon $KTELO for
implementing both existing and new privacy \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Florenzano:2020:EEA,
author = "Fernando Florenzano and Cristian Riveros and
Mart{\'\i}n Ugarte and Stijn Vansummeren and Domagoj
Vrgoc",
title = "Efficient Enumeration Algorithms for Regular Document
Spanners",
journal = j-TODS,
volume = "45",
number = "1",
pages = "3:1--3:42",
month = mar,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3351451",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 4 07:13:27 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3351451",
abstract = "Regular expressions and automata models with capture
variables are core tools in rule-based information
extraction. These formalisms, also called regular
document spanners, use regular languages to locate the
data that a user wants to extract from a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Livshits:2020:COR,
author = "Ester Livshits and Benny Kimelfeld and Sudeepa Roy",
title = "Computing Optimal Repairs for Functional
Dependencies",
journal = j-TODS,
volume = "45",
number = "1",
pages = "4:1--4:46",
month = mar,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3360904",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 4 07:13:27 MST 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3360904",
abstract = "We investigate the complexity of computing an optimal
repair of an inconsistent database, in the case where
integrity constraints are Functional Dependencies
(FDs). We focus on two types of repairs: an optimal
subset repair (optimal S-repair), which is \ldots{}",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Zhang:2020:SRF,
author = "Huanchen Zhang and Hyeontaek Lim and Viktor Leis and
David G. Andersen and Michael Kaminsky and Kimberly
Keeton and Andrew Pavlo",
title = "Succinct Range Filters",
journal = j-TODS,
volume = "45",
number = "2",
pages = "5:1--5:31",
month = jul,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3375660",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jul 19 08:40:15 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3375660",
abstract = "We present the Succinct Range Filter (SuRF), a fast
and compact data structure for approximate membership
tests. Unlike traditional Bloom filters, SuRF supports
both single-key lookups and common range queries:
open-range queries, closed-range queries, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fan:2020:AAP,
author = "Wenfei Fan and Ping Lu and Wenyuan Yu and Jingbo Xu
and Qiang Yin and Xiaojian Luo and Jingren Zhou and
Ruochun Jin",
title = "Adaptive Asynchronous Parallelization of Graph
Algorithms",
journal = j-TODS,
volume = "45",
number = "2",
pages = "6:1--6:45",
month = jul,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3397491",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jul 19 08:40:15 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3397491",
abstract = "This article proposes an Adaptive Asynchronous
Parallel (AAP) model for graph computations. As opposed
to Bulk Synchronous Parallel (BSP) and Asynchronous
Parallel (AP) models, AAP reduces both stragglers and
stale computations by dynamically adjusting \ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Khamis:2020:LMR,
author = "Mahmoud Abo Khamis and Hung Q. Ngo and Xuanlong Nguyen
and Dan Olteanu and Maximilian Schleich",
title = "Learning Models over Relational Data Using Sparse
Tensors and Functional Dependencies",
journal = j-TODS,
volume = "45",
number = "2",
pages = "7:1--7:66",
month = jul,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3375661",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jul 19 08:40:15 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3375661",
abstract = "Integrated solutions for analytics over relational
databases are of great practical importance as they
avoid the costly repeated loop data scientists have to
deal with on a daily basis: select features from data
residing in relational databases using \ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Kolaitis:2020:LNT,
author = "Phokion G. Kolaitis and Reinhard Pichler and Emanuel
Sallinger and Vadim Savenkov",
title = "On the Language of Nested Tuple Generating
Dependencies",
journal = j-TODS,
volume = "45",
number = "2",
pages = "8:1--8:59",
month = jul,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3369554",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jul 19 08:40:15 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3369554",
abstract = "During the past 15 years, schema mappings have been
extensively used in formalizing and studying such
critical data interoperability tasks as data exchange
and data integration. Much of the work has focused on
GLAV mappings, i.e., schema mappings \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fan:2020:CNI,
author = "Wenfei Fan and Xueli Liu and Ping Lu and Chao Tian",
title = "Catching Numeric Inconsistencies in Graphs",
journal = j-TODS,
volume = "45",
number = "2",
pages = "9:1--9:47",
month = jul,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3385031",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jul 19 08:40:15 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/abs/10.1145/3385031",
abstract = "Numeric inconsistencies are common in real-life
knowledge bases and social networks. To catch such
errors, we extend graph functional dependencies with
linear arithmetic expressions and built-in comparison
predicates, referred to as numeric graph \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Jermaine:2020:E,
author = "Chris Jermaine",
title = "Editorial",
journal = j-TODS,
volume = "45",
number = "3",
pages = "10:1--10:1",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3417730",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3417730",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Kara:2020:MTQ,
author = "Ahmet Kara and Hung Q. Ngo and Milos Nikolic and Dan
Olteanu and Haozhe Zhang",
title = "Maintaining Triangle Queries under Updates",
journal = j-TODS,
volume = "45",
number = "3",
pages = "11:1--11:46",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3396375",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3396375",
abstract = "We consider the problem of incrementally maintaining
the triangle queries with arbitrary free variables
under single-tuple updates to the input relations. We
introduce an approach called IVM$\epsilon$ that
exhibits a trade-off between the update time, the
space, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Shaikhha:2020:SIL,
author = "Amir Shaikhha and Mohammed Elseidy and Stephan Mihaila
and Daniel Espino and Christoph Koch",
title = "Synthesis of Incremental Linear Algebra Programs",
journal = j-TODS,
volume = "45",
number = "3",
pages = "12:1--12:44",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3385398",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3385398",
abstract = "This article targets the Incremental View Maintenance
(IVM) of sophisticated analytics (such as statistical
models, machine learning programs, and graph
algorithms) expressed as linear algebra programs. We
present LAGO, a unified framework for linear \ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Schirmer:2020:EDM,
author = "Philipp Schirmer and Thorsten Papenbrock and Ioannis
Koumarelas and Felix Naumann",
title = "Efficient Discovery of Matching Dependencies",
journal = j-TODS,
volume = "45",
number = "3",
pages = "13:1--13:33",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3392778",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3392778",
abstract = "Matching dependencies (MDs) are data profiling results
that are often used for data integration, data
cleaning, and entity matching. They are a
generalization of functional dependencies (FDs)
matching similar rather than same elements. As their
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Qi:2020:PTS,
author = "Jianzhong Qi and Yufei Tao and Yanchuan Chang and Rui
Zhang",
title = "Packing {$R$}-trees with Space-filling Curves:
Theoretical Optimality, Empirical Efficiency, and
Bulk-loading Parallelizability",
journal = j-TODS,
volume = "45",
number = "3",
pages = "14:1--14:47",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3397506",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3397506",
abstract = "The massive amount of data and large variety of data
distributions in the big data era call for access
methods that are efficient in both query processing and
index management, and over both practical and
worst-case workloads. To address this need, we
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fan:2020:DGF,
author = "Wenfei Fan and Chunming Hu and Xueli Liu and Ping Lu",
title = "Discovering Graph Functional Dependencies",
journal = j-TODS,
volume = "45",
number = "3",
pages = "15:1--15:42",
month = sep,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3397198",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sat Sep 26 07:22:54 MDT 2020",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3397198",
abstract = "This article studies discovery of Graph Functional
Dependencies (GFDs), a class of functional dependencies
defined on graphs. We investigate the fixed-parameter
tractability of three fundamental problems related to
GFD discovery. We show that the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Nakandala:2020:IAC,
author = "Supun Nakandala and Kabir Nagrecha and Arun Kumar and
Yannis Papakonstantinou",
title = "Incremental and Approximate Computations for
Accelerating Deep {CNN} Inference",
journal = j-TODS,
volume = "45",
number = "4",
pages = "16:1--16:42",
month = dec,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3397461",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Mar 28 09:41:59 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3397461",
abstract = "Deep learning now offers state-of-the-art accuracy for
many prediction tasks. A form of deep learning called
deep convolutional neural networks (CNNs) are
especially popular on image, video, and time series
data. Due to its high computational cost, CNN
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Khamis:2020:FAQ,
author = "Mahmoud Abo Khamis and Ryan R. Curtin and Benjamin
Moseley and Hung Q. Ngo and Xuanlong Nguyen and Dan
Olteanu and Maximilian Schleich",
title = "Functional Aggregate Queries with Additive
Inequalities",
journal = j-TODS,
volume = "45",
number = "4",
pages = "17:1--17:41",
month = dec,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3426865",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Mar 28 09:41:59 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3426865",
abstract = "Motivated by fundamental applications in databases and
relational machine learning, we formulate and study the
problem of answering functional aggregate queries (FAQ)
in which some of the input factors are defined by a
collection of additive \ldots{}",
acknowledgement = ack-nhfb,
articleno = "17",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Ciaccia:2020:FSD,
author = "Paolo Ciaccia and Davide Martinenghi",
title = "Flexible Skylines: Dominance for Arbitrary Sets of
Monotone Functions",
journal = j-TODS,
volume = "45",
number = "4",
pages = "18:1--18:45",
month = dec,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3406113",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Mar 28 09:41:59 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3406113",
abstract = "Skyline and ranking queries are two popular,
alternative ways of discovering interesting data in
large datasets. Skyline queries are simple to specify,
as they just return the set of all non-dominated
tuples, thereby providing an overall view of \ldots{}",
acknowledgement = ack-nhfb,
articleno = "18",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Zimanyi:2020:MMD,
author = "Esteban Zim{\'a}nyi and Mahmoud Sakr and Arthur
Lesuisse",
title = "{MobilityDB}: a Mobility Database Based on
{PostgreSQL} and {PostGIS}",
journal = j-TODS,
volume = "45",
number = "4",
pages = "19:1--19:42",
month = dec,
year = "2020",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3406534",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Mar 28 09:41:59 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3406534",
abstract = "Despite two decades of research in moving object
databases and a few research prototypes that have been
proposed, there is not yet a mainstream system targeted
for industrial use. In this article, we present
MobilityDB, a moving object database that \ldots{}",
acknowledgement = ack-nhfb,
articleno = "19",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Traub:2021:SGE,
author = "Jonas Traub and Philipp Marian Grulich and Alejandro
Rodr{\'\i}guez Cu{\'e}llar and Sebastian Bre{\ss} and
Asterios Katsifodimos and Tilmann Rabl and Volker
Markl",
title = "{Scotty}: General and Efficient Open-source Window
Aggregation for Stream Processing Systems",
journal = j-TODS,
volume = "46",
number = "1",
pages = "1:1--1:46",
month = apr,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3433675",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 15 14:48:28 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3433675",
abstract = "Window aggregation is a core operation in data stream
processing. Existing aggregation techniques focus on
reducing latency, eliminating redundant computations,
or minimizing memory usage. However, each technique
operates under different assumptions \ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Amarilli:2021:CDE,
author = "Antoine Amarilli and Pierre Bourhis and Stefan Mengel
and Matthias Niewerth",
title = "Constant-Delay Enumeration for Nondeterministic
Document Spanners",
journal = j-TODS,
volume = "46",
number = "1",
pages = "2:1--2:30",
month = apr,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3436487",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 15 14:48:28 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3436487",
abstract = "We consider the information extraction framework known
as document spanners and study the problem of
efficiently computing the results of the extraction
from an input document, where the extraction task is
described as a sequential variable-set \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Mitchell:2021:ESM,
author = "Rory Mitchell and Eibe Frank and Geoffrey Holmes",
title = "An Empirical Study of Moment Estimators for Quantile
Approximation",
journal = j-TODS,
volume = "46",
number = "1",
pages = "3:1--3:21",
month = apr,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3442337",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 15 14:48:28 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3442337",
abstract = "We empirically evaluate lightweight moment estimators
for the single-pass quantile approximation problem,
including maximum entropy methods and orthogonal series
with Fourier, Cosine, Legendre, Chebyshev and Hermite
basis functions. We show how to apply \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Meduri:2021:EML,
author = "Venkata Vamsikrishna Meduri and Kanchan Chowdhury and
Mohamed Sarwat",
title = "Evaluation of Machine Learning Algorithms in
Predicting the Next {SQL} Query from the Future",
journal = j-TODS,
volume = "46",
number = "1",
pages = "4:1--4:46",
month = apr,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3442338",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Thu Apr 15 14:48:28 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3442338",
abstract = "Prediction of the next SQL query from the user, given
her sequence of queries until the current timestep,
during an ongoing interaction session of the user with
the database, can help in speculative query processing
and increased interactivity. While existing machine
learning-(ML) based approaches use recommender
systems to suggest relevant queries to a user, there
has been no exhaustive study on applying temporal
predictors to predict the next user issued
query.\par
In this work, we experimentally compare ML algorithms
in predicting the immediate next future query in an
interaction workload, given the current user query or
the sequence of queries in a user session thus far. As
a part of this, we propose the adaptation of two
powerful temporal predictors: (a) Recurrent Neural
Networks (RNNs) and (b) a Reinforcement Learning
approach called Q-Learning that uses Markov Decision
Processes. We represent each query as a comprehensive
set of fragment embeddings that not only captures the
SQL operators, attributes, and relations but also the
arithmetic comparison operators and constants that
occur in the query. Our experiments on two real-world
datasets show the effectiveness of temporal predictors
against the baseline recommender systems in predicting
the structural fragments in a query w.r.t. both quality
and time. Besides showing that RNNs can be used to
synthesize novel queries, we find that exact Q-Learning
outperforms RNNs despite predicting the next query
entirely from the historical query logs.",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Carmeli:2021:ECU,
author = "Nofar Carmeli and Markus Kr{\"o}ll",
title = "On the Enumeration Complexity of Unions of Conjunctive
Queries",
journal = j-TODS,
volume = "46",
number = "2",
pages = "5:1--5:41",
month = jun,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3450263",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jun 6 07:07:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3450263",
abstract = "We study the enumeration complexity of Unions of
Conjunctive Queries (UCQs). We aim to identify the UCQs
that are tractable in the sense that the answer tuples
can be enumerated with a linear preprocessing phase and
a constant delay between every \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Mhedhbi:2021:OOT,
author = "Amine Mhedhbi and Chathura Kankanamge and Semih
Salihoglu",
title = "Optimizing One-time and Continuous Subgraph Queries
using Worst-case Optimal Joins",
journal = j-TODS,
volume = "46",
number = "2",
pages = "6:1--6:45",
month = jun,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3446980",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jun 6 07:07:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3446980",
abstract = "We study the problem of optimizing one-time and
continuous subgraph queries using the new worst-case
optimal join plans. Worst-case optimal plans evaluate
queries by matching one query vertex at a time using
multiway intersections. The core problem in \ldots{}",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Wei:2021:EFD,
author = "Ziheng Wei and Sebastian Link",
title = "Embedded Functional Dependencies and Data-completeness
Tailored Database Design",
journal = j-TODS,
volume = "46",
number = "2",
pages = "7:1--7:46",
month = jun,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3450518",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jun 6 07:07:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3450518",
abstract = "We establish a principled schema design framework for
data with missing values. The framework is based on the
new notion of an embedded functional dependency, which
is independent of the interpretation of missing values,
able to express completeness and \ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Chen:2021:GIE,
author = "Yangjun Chen and Gagandeep Singh",
title = "Graph Indexing for Efficient Evaluation of
Label-constrained Reachability Queries",
journal = j-TODS,
volume = "46",
number = "2",
pages = "8:1--8:50",
month = jun,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3451159",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Sun Jun 6 07:07:25 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3451159",
abstract = "Given a directed edge labeled graph G, to check
whether vertex v is reachable from vertex u under a
label set S is to know if there is a path from u to v
whose edge labels across the path are a subset of S.
Such a query is referred to as a label-. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Trummer:2021:SRB,
author = "Immanuel Trummer and Junxiong Wang and Ziyun Wei and
Deepak Maram and Samuel Moseley and Saehan Jo and
Joseph Antonakakis and Ankush Rayabhari",
title = "{SkinnerDB}: Regret-bounded Query Evaluation via
Reinforcement Learning",
journal = j-TODS,
volume = "46",
number = "3",
pages = "9:1--9:45",
month = sep,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3464389",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Sep 29 06:47:23 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3464389",
abstract = "SkinnerDB uses reinforcement learning for reliable
join ordering, exploiting an adaptive processing engine
with specialized join algorithms and data structures.
It maintains no data statistics and uses no cost or
cardinality models. Also, it uses no \ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Song:2021:SDC,
author = "Shaoxu Song and Fei Gao and Aoqian Zhang and Jianmin
Wang and Philip S. Yu",
title = "Stream Data Cleaning under Speed and Acceleration
Constraints",
journal = j-TODS,
volume = "46",
number = "3",
pages = "10:1--10:44",
month = sep,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3465740",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Sep 29 06:47:23 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3465740",
abstract = "Stream data are often dirty, for example, owing to
unreliable sensor reading or erroneous extraction of
stock prices. Most stream data cleaning approaches
employ a smoothing filter, which may seriously alter
the data without preserving the original \ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Lin:2021:EBL,
author = "Xuelian Lin and Shuai Ma and Jiahao Jiang and Yanchen
Hou and Tianyu Wo",
title = "Error Bounded Line Simplification Algorithms for
Trajectory Compression: an Experimental Evaluation",
journal = j-TODS,
volume = "46",
number = "3",
pages = "11:1--11:44",
month = sep,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3474373",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Sep 29 06:47:23 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3474373",
abstract = "Nowadays, various sensors are collecting, storing, and
transmitting tremendous trajectory data, and it is well
known that the storage, network bandwidth, and
computing resources could be heavily wasted if raw
trajectory data is directly adopted. Line \ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Khamis:2021:BQC,
author = "Mahmoud Abo Khamis and Phokion G. Kolaitis and Hung Q.
Ngo and Dan Suciu",
title = "Bag Query Containment and Information Theory",
journal = j-TODS,
volume = "46",
number = "3",
pages = "12:1--12:39",
month = sep,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3472391",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Sep 29 06:47:23 MDT 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3472391",
abstract = "The query containment problem is a fundamental
algorithmic problem in data management. While this
problem is well understood under set semantics, it is
by far less understood under bag semantics. In
particular, it is a long-standing open question whether
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Ma:2021:DDS,
author = "Chenhao Ma and Yixiang Fang and Reynold Cheng and Laks
V. S. Lakshmanan and Wenjie Zhang and Xuemin Lin",
title = "On Directed Densest Subgraph Discovery",
journal = j-TODS,
volume = "46",
number = "4",
pages = "13:1--13:45",
month = dec,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3483940",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Dec 10 10:59:16 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3483940",
abstract = "Given a directed graph G, the directed densest
subgraph (DDS) problem refers to the finding of a
subgraph from G, whose density is the highest among all
the subgraphs of G. The DDS problem is fundamental to a
wide range of applications, such as fraud \ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Singh:2021:TRH,
author = "Shikha Singh and Prashant Pandey and Michael A. Bender
and Jonathan W. Berry and Mart{\'\i}n Farach-Colton and
Rob Johnson and Thomas M. Kroeger and Cynthia A.
Phillips",
title = "Timely Reporting of Heavy Hitters Using External
Memory",
journal = j-TODS,
volume = "46",
number = "4",
pages = "14:1--14:35",
month = dec,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3472392",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Dec 10 10:59:16 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3472392",
abstract = "Given an input stream $S$ of size $N$, a $\phi$-heavy
hitter is an item that occurs at least $\phi N$ times
in $S$. The problem of finding heavy-hitters is
extensively studied in the database literature. We
study a real-time heavy-hitters variant in which an
element must \ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Benedikt:2021:BEI,
author = "Michael Benedikt and Pierre Bourhis and Louis Jachiet
and Efthymia Tsamoura",
title = "Balancing Expressiveness and Inexpressiveness in View
Design",
journal = j-TODS,
volume = "46",
number = "4",
pages = "15:1--15:40",
month = dec,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3488370",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Dec 10 10:59:16 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3488370",
abstract = "We study the design of data publishing mechanisms that
allow a collection of autonomous distributed data
sources to collaborate to support queries. A common
mechanism for data publishing is via views: functions
that expose derived data to users, usually \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Grez:2021:FFC,
author = "Alejandro Grez and Cristian Riveros and Mart{\'\i}n
Ugarte and Stijn Vansummeren",
title = "A Formal Framework for Complex Event Recognition",
journal = j-TODS,
volume = "46",
number = "4",
pages = "16:1--16:49",
month = dec,
year = "2021",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3485463",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Dec 10 10:59:16 MST 2021",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3485463",
abstract = "Complex event recognition (CER) has emerged as the
unifying field for technologies that require processing
and correlating distributed data sources in real time.
CER finds applications in diverse domains, which has
resulted in a large number of proposals \ldots{}",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Berger:2022:SEC,
author = "Gerald Berger and Georg Gottlob and Andreas Pieris and
Emanuel Sallinger",
title = "The Space-Efficient Core of {Vadalog}",
journal = j-TODS,
volume = "47",
number = "1",
pages = "1:1--1:46",
month = mar,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3488720",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue May 3 06:36:04 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3488720",
abstract = "Vadalog is a system for performing complex reasoning
tasks such as those required in advanced knowledge
graphs. The logical core of the underlying Vadalog
language is the warded fragment of tuple-generating
dependencies (TGDs). This formalism ensures \ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Tong:2022:URP,
author = "Yongxin Tong and Yuxiang Zeng and Zimu Zhou and Lei
Chen and Ke Xu",
title = "Unified Route Planning for Shared Mobility: an
Insertion-based Framework",
journal = j-TODS,
volume = "47",
number = "1",
pages = "2:1--2:48",
month = mar,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3488723",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue May 3 06:36:04 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3488723",
abstract = "There has been a dramatic growth of shared mobility
applications such as ride-sharing, food delivery, and
crowdsourced parcel delivery. Shared mobility refers to
transportation services that are shared among users,
where a central issue is route planning. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Binna:2022:HOT,
author = "Robert Binna and Eva Zangerle and Martin Pichl and
G{\"u}nther Specht and Viktor Leis",
title = "Height Optimized Tries",
journal = j-TODS,
volume = "47",
number = "1",
pages = "3:1--3:46",
month = mar,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3506692",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue May 3 06:36:04 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3506692",
abstract = "We present the Height Optimized Trie (HOT), a fast and
space-efficient in-memory index structure. The core
algorithmic idea of HOT is to dynamically vary the
number of bits considered at each node, which enables a
consistently high fanout and thereby good \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Aumuller:2022:SNN,
author = "Martin Aum{\"u}ller and Sariel Har-Peled and Sepideh
Mahabadi and Rasmus Pagh and Francesco Silvestri",
title = "Sampling a Near Neighbor in High Dimensions --- Who is
the Fairest of Them All?",
journal = j-TODS,
volume = "47",
number = "1",
pages = "4:1--4:40",
month = mar,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3502867",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue May 3 06:36:04 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3502867",
abstract = "Similarity search is a fundamental algorithmic
primitive, widely used in many computer science
disciplines. Given a set of points S and a radius
parameter $ r > 0 $, the $r$-near neighbor ($r$-NN)
problem asks for a data structure that, given any query
point $q$, \ldots{}",
acknowledgement = ack-nhfb,
articleno = "4",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Schmid:2022:CRP,
author = "Markus L. Schmid",
title = "Conjunctive Regular Path Queries with Capture Groups",
journal = j-TODS,
volume = "47",
number = "2",
pages = "5:1--5:52",
month = jun,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3514230",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 6 06:55:46 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3514230",
abstract = "In practice, regular expressions are usually extended
by so-called capture groups or capture variables, which
allow to capture a subexpression by a variable that can
be referenced in the regular expression in order to
describe repetitions of subwords. We \ldots{}",
acknowledgement = ack-nhfb,
articleno = "5",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fan:2022:IGC,
author = "Wenfei Fan and Chao Tian",
title = "Incremental Graph Computations: Doable and Undoable",
journal = j-TODS,
volume = "47",
number = "2",
pages = "6:1--6:44",
month = jun,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3500930",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 6 06:55:46 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3500930",
acknowledgement = ack-nhfb,
articleno = "6",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Cheng:2022:MOP,
author = "Ji Cheng and Da Yan and Wenwen Qu and Xiaotian Hao and
Cheng Long and Wilfred Ng and Xiaoling Wang",
title = "Mining Order-preserving Submatrices under Data
Uncertainty: a Possible-world Approach and Efficient
Approximation Methods",
journal = j-TODS,
volume = "47",
number = "2",
pages = "7:1--7:57",
month = jun,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3524915",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 6 06:55:46 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3524915",
abstract = "Given a data matrix $D$, a submatrix $S$ of $D$ is an
order-preserving submatrix (OPSM) if there is a
permutation of the columns of $S$, ! under which the
entry values of each row in $S$ are strictly
increasing. OPSM mining is \ldots{}",
acknowledgement = ack-nhfb,
articleno = "7",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Arroyuelo:2022:OJU,
author = "Diego Arroyuelo and Gonzalo Navarro and Juan L.
Reutter and Javiel Rojas-Ledesma",
title = "Optimal Joins Using Compressed Quadtrees",
journal = j-TODS,
volume = "47",
number = "2",
pages = "8:1--8:53",
month = jun,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3514231",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jun 6 06:55:46 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3514231",
abstract = "Worst-case optimal join algorithms have gained a lot
of attention in the database literature. We now count
several algorithms that are optimal in the worst case,
and many of them have been implemented and validated in
practice. However, the implementation \ldots{}",
acknowledgement = ack-nhfb,
articleno = "8",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Carmeli:2022:AUC,
author = "Nofar Carmeli and Shai Zeevi and Christoph Berkholz
and Alessio Conte and Benny Kimelfeld and Nicole
Schweikardt",
title = "Answering (Unions of) Conjunctive Queries using Random
Access and Random-Order Enumeration",
journal = j-TODS,
volume = "47",
number = "3",
pages = "9:1--9:49",
month = sep,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3531055",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 19 08:39:08 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3531055",
abstract = "As data analytics becomes more crucial to digital
systems, so grows the importance of characterizing the
database queries that admit a more efficient
evaluation. We consider the tractability yardstick of
answer enumeration with a polylogarithmic delay
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "9",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Asudeh:2022:FRR,
author = "Abolfazl Asudeh and Gautam Das and H. V. Jagadish and
Shangqi Lu and Azade Nazi and Yufei Tao and Nan Zhang
and Jianwen Zhao",
title = "On Finding Rank Regret Representatives",
journal = j-TODS,
volume = "47",
number = "3",
pages = "10:1--10:37",
month = sep,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3531054",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 19 08:39:08 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3531054",
abstract = "Selecting the best items in a dataset is a common task
in data exploration. However, the concept of ``best''
lies in the eyes of the beholder: Different users may
consider different attributes more important and,
hence, arrive at different rankings. \ldots{}",
acknowledgement = ack-nhfb,
articleno = "10",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Zeng:2022:PS,
author = "Tianjing Zeng and Zhewei Wei and Ge Luo and Ke Yi and
Xiaoyong Du and Ji-Rong Wen",
title = "Persistent Summaries",
journal = j-TODS,
volume = "47",
number = "3",
pages = "11:1--11:42",
month = sep,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3531053",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 19 08:39:08 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3531053",
abstract = "A persistent data structure, also known as a
multiversion data structure in the database literature,
is a data structure that preserves all its previous
versions as it is updated over time. Every update
(inserting, deleting, or changing a data record) to
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "11",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Guo:2022:IMR,
author = "Qintian Guo and Sibo Wang and Zhewei Wei and Wenqing
Lin and Jing Tang",
title = "Influence Maximization Revisited: Efficient Sampling
with Bound Tightened",
journal = j-TODS,
volume = "47",
number = "3",
pages = "12:1--12:45",
month = sep,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3533817",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Aug 19 08:39:08 MDT 2022",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3533817",
abstract = "Given a social network G with n nodes and m edges, a
positive integer k, and a cascade model C, the
influence maximization (IM) problem asks for k nodes in
G such that the expected number of nodes influenced by
the k nodes under cascade model C is \ldots{}",
acknowledgement = ack-nhfb,
articleno = "12",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Ketsman:2022:DRL,
author = "Bas Ketsman and Christoph Koch and Frank Neven and
Brecht Vandevoort",
title = "Deciding Robustness for Lower {SQL} Isolation Levels",
journal = j-TODS,
volume = "47",
number = "4",
pages = "13:1--13:??",
month = dec,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3561049",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:50 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3561049",
abstract = "While serializability always guarantees application
correctness, lower isolation levels can be chosen to
improve transaction throughput at the risk of
introducing certain anomalies. A set of transactions is
robust against a given isolation level if every
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "13",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{TenCate:2022:CQU,
author = "Balder {Ten Cate} and Victor Dalmau",
title = "Conjunctive Queries: Unique Characterizations and
Exact Learnability",
journal = j-TODS,
volume = "47",
number = "4",
pages = "14:1--14:??",
month = dec,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3559756",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:50 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3559756",
abstract = "We answer the question of which conjunctive queries
are uniquely characterized by polynomially many
positive and negative examples and how to construct
such examples efficiently. As a consequence, we obtain
a new efficient exact learning algorithm for a
\ldots{}",
acknowledgement = ack-nhfb,
articleno = "14",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Wei:2022:PQT,
author = "Victor Junqiu Wei and Raymond Chi-Wing Wong and Cheng
Long and David Mount and Hanan Samet",
title = "Proximity Queries on Terrain Surface",
journal = j-TODS,
volume = "47",
number = "4",
pages = "15:1--15:??",
month = dec,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3563773",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:50 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3563773",
abstract = "Due to the advance of the geo-spatial positioning and
the computer graphics technology, digital terrain data
has become increasingly popular nowadays. Query
processing on terrain data has attracted considerable
attention from both the academic and the \ldots{}",
acknowledgement = ack-nhfb,
articleno = "15",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Do:2022:ESD,
author = "Thanh Do and Goetz Graefe and Jeffrey Naughton",
title = "Efficient Sorting, Duplicate Removal, Grouping, and
Aggregation",
journal = j-TODS,
volume = "47",
number = "4",
pages = "16:1--16:??",
month = dec,
year = "2022",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3568027",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:50 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3568027",
abstract = "Database query processing requires algorithms for
duplicate removal, grouping, and aggregation. Three
algorithms exist: in-stream aggregation is most
efficient by far but requires sorted input; sort-based
aggregation relies on external merge sort; and hash
aggregation relies on an in-memory hash table plus hash
partitioning to temporary storage. Cost-based query
optimization chooses which algorithm to use based on
several factors, including the sort order of the input,
input and output sizes, and the need for sorted output.
For example, hash-based aggregation is ideal for output
smaller than the available memory (e.g., Query 1 of
TPC-H), whereas sorting the entire input and
aggregating after sorting are preferable when both
aggregation input and output are large and the output
needs to be sorted for a subsequent operation such as a
merge join.\par
Unfortunately, the size information required for a
sound choice is often inaccurate or unavailable during
query optimization, leading to sub-optimal algorithm
choices. In response, this article introduces a new
algorithm for sort-based duplicate removal, grouping,
and aggregation. The new algorithm always performs at
least as well as both traditional hash-based and
traditional sort-based algorithms. It can serve as a
system's only aggregation algorithm for unsorted
inputs, thus preventing erroneous algorithm choices.
Furthermore, the new algorithm produces sorted output
that can speed up subsequent operations. Google's F1
Query uses the new algorithm in production workloads
that aggregate petabytes of data every day.",
acknowledgement = ack-nhfb,
articleno = "16",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Carmeli:2023:TOD,
author = "Nofar Carmeli and Nikolaos Tziavelis and Wolfgang
Gatterbauer and Benny Kimelfeld and Mirek Riedewald",
title = "Tractable Orders for Direct Access to Ranked Answers
of Conjunctive Queries",
journal = j-TODS,
volume = "48",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3578517",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:51 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3578517",
abstract = "We study the question of when we can provide direct
access to the k-th answer to a Conjunctive Query (CQ)
according to a specified order over the answers in time
logarithmic in the size of the database, following a
preprocessing step that constructs a \ldots{}",
acknowledgement = ack-nhfb,
articleno = "1",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Do:2023:RES,
author = "Thanh Do and Goetz Graefe",
title = "Robust and Efficient Sorting with Offset-value
Coding",
journal = j-TODS,
volume = "48",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3570956",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:51 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3570956",
abstract = "Sorting and searching are large parts of database
query processing, e.g., in the forms of index creation,
index maintenance, and index lookup, and comparing
pairs of keys is a substantial part of the effort in
sorting and searching. We have worked on \ldots{}",
acknowledgement = ack-nhfb,
articleno = "2",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Huang:2023:ECS,
author = "Ruihong Huang and Jianmin Wang and Shaoxu Song and
Xuemin Lin and Xiaochen Zhu and Jian Pei",
title = "Efficiently Cleaning Structured Event Logs: a Graph
Repair Approach",
journal = j-TODS,
volume = "48",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3571281",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Fri Mar 31 10:14:51 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3571281",
abstract = "Event data are often dirty owing to various recording
conventions or simply system errors. These errors may
cause serious damage to real applications, such as
inaccurate provenance answers, poor profiling results,
or concealing interesting patterns from \ldots{}",
acknowledgement = ack-nhfb,
articleno = "3",
ajournal = "ACM Trans. Database Syst.",
ajournal = "ACM Trans. Database Syst.",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fakas:2023:PSD,
author = "Georgios J. Fakas and Georgios Kalamatianos",
title = "Proportionality on Spatial Data with Context",
journal = j-TODS,
volume = "48",
number = "2",
pages = "4:1--4:??",
month = jun,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3588434",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 3 07:30:46 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3588434",
abstract = "More often than not, spatial objects are associated
with some context, in the form of text, descriptive
tags (e.g., points of interest, flickr photos), or
linked entities in semantic graphs (e.g., Yago2,
DBpedia). Hence, location-based retrieval should be
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "4",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Hu:2023:RDW,
author = "Donghui Hu and Qing Wang and Song Yan and Xiaojun Liu
and Meng Li and Shuli Zheng",
title = "Reversible Database Watermarking Based on
Order-preserving Encryption for Data Sharing",
journal = j-TODS,
volume = "48",
number = "2",
pages = "5:1--5:??",
month = jun,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3589761",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 3 07:30:46 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3589761",
abstract = "In the era of big data, data sharing not only boosts
the economy of the world but also brings about problems
of privacy disclosure and copyright infringement. The
collected data may contain users' sensitive
information; thus, privacy protection should be
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "5",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Chen:2023:EBO,
author = "Yaxing Chen and Qinghua Zheng and Zheng Yan",
title = "Efficient Bi-objective {SQL} Optimization for Enclaved
Cloud Databases with Differentially Private Padding",
journal = j-TODS,
volume = "48",
number = "2",
pages = "6:1--6:??",
month = jun,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3597021",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Jul 3 07:30:46 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3597021",
abstract = "Hardware-enabled enclaves have been applied to
efficiently enforce data security and privacy
protection in cloud database services. Such enclaved
systems, however, are reported to suffer from I/O-size
(also referred to as communication-volume)-based
side-\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "6",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Pavan:2023:MCM,
author = "A. Pavan and N. V. Vinodchandran and Arnab
Bhattacharyya and Kuldeep S. Meel",
title = "Model Counting Meets {$ F_0 $} Estimation",
journal = j-TODS,
volume = "48",
number = "3",
pages = "7:1--7:??",
month = sep,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3603496",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Sep 18 08:53:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3603496",
abstract = "Constraint satisfaction problems (CSPs) and data
stream models are two powerful abstractions to capture
a wide variety of problems arising in different domains
of computer science. Developments in the two
communities have mostly occurred independently and
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "7",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Sarkar:2023:ETP,
author = "Subhadeep Sarkar and Tarikul Islam Papon and Dimitris
Staratzis and Zichen Zhu and Manos Athanassoulis",
title = "Enabling Timely and Persistent Deletion in
{LSM}-Engines",
journal = j-TODS,
volume = "48",
number = "3",
pages = "8:1--8:??",
month = sep,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3599724",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Sep 18 08:53:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3599724",
abstract = "Data-intensive applications have fueled the evolution
of log-structured merge (LSM) based key-value engines
that employ the out-of-place paradigm to support high
ingestion rates with low read/write interference. These
benefits, however, come at the cost \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "8",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Leventidis:2023:DHD,
author = "Aristotelis Leventidis and Laura {Di Rocco} and
Wolfgang Gatterbauer and Ren{\'e}e J. Miller and Mirek
Riedewald",
title = "{DomainNet}: Homograph Detection and Understanding in
Data Lake Disambiguation",
journal = j-TODS,
volume = "48",
number = "3",
pages = "9:1--9:??",
month = sep,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3612919",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Mon Sep 18 08:53:16 MDT 2023",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3612919",
abstract = "Modern data lakes are heterogeneous in the vocabulary
that is used to describe data. We study a problem of
disambiguation in data lakes: How can we determine if a
data value occurring more than once in the lake has
different meanings and is therefore a \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "9",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Shangqi:2023:POM,
author = "Lu Shangqi and Wim Martens and Matthias Niewerth and
Yufei Tao",
title = "Partial Order Multiway Search",
journal = j-TODS,
volume = "48",
number = "4",
pages = "10:1--10:??",
month = dec,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3626956",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 9 07:07:31 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3626956",
abstract = "Partial order multiway search (POMS) is a fundamental
problem that finds applications in crowdsourcing,
distributed file systems, software testing, and more.
This problem involves an interaction between an
algorithm A and an oracle, conducted on a \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "10",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Herodotou:2023:CBD,
author = "Herodotos Herodotou and Elena Kakoulli",
title = "Cost-based Data Prefetching and Scheduling in Big Data
Platforms over Tiered Storage Systems",
journal = j-TODS,
volume = "48",
number = "4",
pages = "11:1--11:??",
month = dec,
year = "2023",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3625389",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Tue Jan 9 07:07:31 MST 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3625389",
abstract = "The use of storage tiering is becoming popular in
data-intensive compute clusters due to the recent
advancements in storage technologies. The Hadoop
Distributed File System, for example, now supports
storing data in memory, SSDs, and HDDs, while OctopusFS
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "11",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Gottlob:2024:FPH,
author = "Georg Gottlob and Matthias Lanzinger and Cem Okulmus
and Reinhard Pichler",
title = "Fast Parallel Hypertree Decompositions in Logarithmic
Recursion Depth",
journal = j-TODS,
volume = "49",
number = "1",
pages = "1:1--1:??",
month = mar,
year = "2024",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3638758",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 13 07:26:47 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3638758",
abstract = "Various classic reasoning problems with natural
hypergraph representations are known to be tractable if
a hypertree decomposition (HD) of low width exists. The
resulting algorithms are attractive for practical use
in fields like databases and constraint \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "1",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Fan:2024:LEA,
author = "Wenfei Fan and Ping Lu and Kehan Pang and Ruochun Jin
and Wenyuan Yu",
title = "Linking Entities across Relations and Graphs",
journal = j-TODS,
volume = "49",
number = "1",
pages = "2:1--2:??",
month = mar,
year = "2024",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3639363",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 13 07:26:47 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3639363",
abstract = "This article proposes a notion of parametric
simulation to link entities across a relational
database D and a graph G. Taking functions and
thresholds for measuring vertex closeness, path
associations, and important properties as parameters,
parametric \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "2",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Wang:2024:AHT,
author = "Zhaoguo Wang and Chuzhe Tang and Xiaodong Zhang and
Qianmian Yu and Binyu Zang and Haibing Guan and Haibo
Chen",
title = "Ad Hoc Transactions through the Looking Glass: an
Empirical Study of Application-Level Transactions in
{Web} Applications",
journal = j-TODS,
volume = "49",
number = "1",
pages = "3:1--3:??",
month = mar,
year = "2024",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3638553",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 13 07:26:47 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3638553",
abstract = "Many transactions in web applications are constructed
ad hoc in the application code. For example, developers
might explicitly use locking primitives or validation
procedures to coordinate critical code fragments. We
refer to database operations \ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "3",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@Article{Currim:2024:IRC,
author = "Sabah Currim and Richard T. Snodgrass and Young-Kyoon
Suh",
title = "Identifying the Root Causes of {DBMS} Suboptimality",
journal = j-TODS,
volume = "49",
number = "1",
pages = "4:1--4:??",
month = mar,
year = "2024",
CODEN = "ATDSD3",
DOI = "https://doi.org/10.1145/3636425",
ISSN = "0362-5915 (print), 1557-4644 (electronic)",
ISSN-L = "0362-5915",
bibdate = "Wed Mar 13 07:26:47 MDT 2024",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "https://dl.acm.org/doi/10.1145/3636425",
abstract = "The query optimization phase within a database
management system (DBMS) ostensibly finds the fastest
query execution plan from a potentially large set of
enumerated plans, all of which correctly compute the
same result of the specified query. Sometimes
\ldots{}",
acknowledgement = ack-nhfb,
ajournal = "ACM Trans. Database Syst.",
articleno = "4",
fjournal = "ACM Transactions on Database Systems",
journal-URL = "https://dl.acm.org/loi/tods",
}
@InProceedings{Litwin:1980:LHN,
author = "W. Litwin",
title = "Linear Hashing: a New Tool for File and Table
Addressing",
crossref = "Lochovsky:1980:SIC",
pages = "212--223",
year = "1980",
bibdate = "Tue Jul 19 00:55:06 1994",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Reprinted in
\cite[p.~570--581]{Stonebraker:1988:RDS}.",
annote = "On excess collisions create new bucket and modify
hash. Leads to constant performance.",
}
@Article{Regnier:1985:AGF,
author = "Mireille Regnier",
title = "Analysis of Grid File Algorithms",
journal = j-BIT,
volume = "25",
number = "2",
pages = "335--357",
month = jun,
year = "1985",
CODEN = "BITTEL, NBITAB",
DOI = "https://doi.org/10.1007/BF01934379",
ISSN = "0006-3835 (print), 1572-9125 (electronic)",
ISSN-L = "0006-3835",
MRclass = "68P10",
MRnumber = "86m:68019",
bibdate = "Wed Jan 4 18:52:19 MST 2006",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/bit.bib;
https://www.math.utah.edu/pub/tex/bib/hash.bib;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
URL = "http://www.springerlink.com/openurl.asp?genre=article&issn=0006-3835&volume=25&issue=2&spage=335",
abstract = "Grid File is a generic name for geometric algorithms
used to map multiple-key indices onto primary files or
databases. Two existing methods by other authors
\cite{Fagin:1979:EHF,Larson:1978:DH} are generalized to
the multidimensional environment. The presence of a
hashing function is the primary difference between the
two algorithms; it is recommended to provide uniformity
when presented with biased key distributions.",
acknowledgement = ack-nhfb,
affiliationaddress = "Inst Natl de Recherche en Informatique et en
Automatique, Chesnay, Fr",
classification = "723",
fjournal = "BIT (Nordisk tidskrift for informationsbehandling)",
journal-URL = "http://link.springer.com/journal/10543",
journalabr = "BIT (Copenhagen)",
keywords = "computer programming --- Algorithms; data processing;
database systems; dynamic data structures; File
Organization; grid file algorithms; hashing; multi-key
access",
}
@Proceedings{Kerr:1975:PIC,
editor = "Douglas S. Kerr",
booktitle = "{Proceedings of the International Conference on Very
Large Data Bases, Framingham, MA, USA, September
22--24, 1975}",
title = "{Proceedings of the International Conference on Very
Large Data Bases, Framingham, MA, USA, September
22--24, 1975}",
publisher = pub-ACM,
address = pub-ACM:adr,
pages = "viii + 592",
year = "1975",
ISSN = "0278-2596",
LCCN = "QA76.9.D3 I55 1975",
bibdate = "Fri Sep 16 12:12:29 1994",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "ACM SIGMOD v. 1, no. 1, September 1975.",
price = "US\$15.00",
acknowledgement = ack-nhfb,
}
@Proceedings{Lochovsky:1980:SIC,
editor = "Frederick H. Lochovsky and ?. Taylor",
key = "VLDB'80",
booktitle = "{Sixth International Conference on Very Large Data
Bases: reprinted from Very large data bases}",
title = "{Sixth International Conference on Very Large Data
Bases: reprinted from Very large data bases}",
publisher = pub-IEEE,
address = pub-IEEE:adr,
pages = "ix + 435",
year = "1980",
bibdate = "Wed Jul 20 12:37:29 1994",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "IEEE Catalog Number 80CH1534-7C. ACM Order Number
471800. Long Beach Order Number 322.",
acknowledgement = ack-nhfb,
}
@Proceedings{Schkolnick:1983:ICV,
editor = "Mario Schkolnick and C. (Costantino) Thanos",
booktitle = "{9th International Conference on Very Large Data Bases
(Florence, Italy, October 31--November 2, 1983)}",
title = "{9th International Conference on Very Large Data Bases
(Florence, Italy, October 31--November 2, 1983)}",
publisher = "VLDB Endowment",
address = "P.O. Box 2245, Saratoga, CA, USA",
pages = "xiii + 416",
year = "1983",
ISBN = "0-934613-15-X",
ISBN-13 = "978-0-934613-15-6",
LCCN = "QA 76.9 D3 I61 1983",
bibdate = "Sat Dec 7 13:05:35 MST 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "This conference is sponsored by VLDB Endowment and
co-sponsored by IFIP et al.",
acknowledgement = ack-nhfb,
keywords = "database management -- congresses",
}
@Proceedings{ACM:1985:PFA,
editor = "{ACM}",
key = "ACM-PODS'85",
booktitle = "{Proceedings of the Fourth ACM SIGACT-SIGMOD Symposium
on Principles of Database Systems, March 25--27, 1985,
Portland, Oregon}",
title = "{Proceedings of the Fourth ACM SIGACT-SIGMOD Symposium
on Principles of Database Systems, March 25--27, 1985,
Portland, Oregon}",
publisher = pub-ACM,
address = pub-ACM:adr,
pages = "275",
year = "1985",
ISBN = "0-89791-153-9",
ISBN-13 = "978-0-89791-153-5",
LCCN = "QA 76.9 D3 A296 1985",
bibdate = "Sat Sep 17 10:24:09 1994",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
}
@Book{Kambayashi:1986:TIC,
editor = "Yahiko Kambayashi and Wesley Chu and Georges Gardarin
and Setsuo Ohsuga",
booktitle = "{Twelfth International Conference on Very Large Data
Bases, Proceedings (VLDB '86)}",
title = "{Twelfth International Conference on Very Large Data
Bases, Proceedings (VLDB '86)}",
publisher = pub-MORGAN-KAUFMANN,
address = pub-MORGAN-KAUFMANN:adr,
pages = "xiii + 512",
year = "1986",
ISBN = "0-934613-18-4",
ISBN-13 = "978-0-934613-18-7",
LCCN = "QA 76.9 D3 I61 1986",
bibdate = "Tue Nov 10 07:59:52 1998",
bibsource = "Compendex database;
https://www.math.utah.edu/pub/tex/bib/tods.bib",
abstract = "This conference proceeding contains 54 papers, 3 of
them are in abstract form only. The purpose of these
papers is the promotion of an understanding of current
research, and the exchange of ideas, experiences and
future directions in database systems. The main
subjects are office systems, database machines,
computer aided design\slash computer aided
manufacturing, query processing, relational operation
optimization, extended data models, historical database
systems, distributed database systems, knowledge-based
systems and managing of unformatted data, such as text
and graphical images.",
acknowledgement = ack-nhfb,
classification = "723; 903; 912",
conference = "Twelfth International Conference on Very Large Data
Bases, Proceedings (VLDB '86)",
conferenceyear = "1986",
keywords = "Artificial Intelligence --- Applications; Computer
Metatheory --- Formal Logic; Data Processing, Business
--- Data Description; Database Integrity; Database
Systems; Information Retrieval Systems --- Evaluation;
Knowledge Base Systems; Logic Programming; Management
--- Information Systems; Query Processing; Research",
meetingabr = "Twelfth Int Conf Very Large Data Bases Proc VLDB 86",
meetingaddress = "Kyoto, Jpn",
meetingdate = "Aug 25--28 1986",
meetingdate2 = "08/25--28/86",
sponsor = "VLDB Endowment, Jpn; IFIP; INRIA; Information
Processing Soc of Japan; DARPA; et al",
}
@Book{Stonebraker:1988:RDS,
editor = "Michael Stonebraker",
booktitle = "Readings in Database Systems",
title = "Readings in Database Systems",
publisher = pub-MORGAN-KAUFMANN,
address = pub-MORGAN-KAUFMANN:adr,
pages = "xii + 644",
year = "1988",
ISBN = "0-934613-65-6",
ISBN-13 = "978-0-934613-65-1",
LCCN = "QA76.9.D3 R4 1988",
bibdate = "Tue Jul 19 00:53:02 1994",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
note = "Contains reprint of \cite{Litwin:1980:LHN}.",
price = "US\$29.95",
abstract = "The purpose of this collection is to assemble
significant research contributions so they are easily
access-ible to anyone interested in database research.
It is appropriate for use as an introduction for
students or professionals from industry, and as a
reference volume to anyone active in database systems
\ldots. It is intended to serve as a core of material
that any DBMS professional should be familiar with.
Moreover, any industrial practitioner or graduate
student who wishes to be current on the important
research themes would be well advised to read these
papers.",
acknowledgement = ack-nhfb,
bookpages = "xii + 644",
}
@Proceedings{Garcia-Molina:1990:PAS,
editor = "H{\'e}ctor Garc{\'\i}a-Molina and H. V. Jagadish",
booktitle = "{Proceedings of the 1990 ACM SIGMOD International
Conference on Management of Data, May 23--25, 1990,
Atlantic City, NJ}",
title = "{Proceedings of the 1990 ACM SIGMOD International
Conference on Management of Data, May 23--25, 1990,
Atlantic City, NJ}",
volume = "19(2)",
publisher = pub-ACM,
address = pub-ACM:adr,
pages = "xii + 388",
month = jun,
year = "1990",
ISBN = "0-89791-365-5",
ISBN-13 = "978-0-89791-365-2",
LCCN = "QA 76.9 D3 S53 v.19 no.2 1990",
bibdate = "Mon Dec 09 07:53:58 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
series = "SIGMOD Record",
acknowledgement = ack-nhfb,
}
@Book{Zdonik:1990:ROO,
editor = "B. Zdonik and David Maier",
booktitle = "Readings in Object-Oriented Database Systems",
title = "Readings in Object-Oriented Database Systems",
publisher = pub-MORGAN-KAUFMANN,
address = pub-MORGAN-KAUFMANN:adr,
pages = "x + 629",
year = "1990",
ISBN = "1-55860-000-0",
ISBN-13 = "978-1-55860-000-3",
LCCN = "QA76.9.D3 R42 1990",
bibdate = "Mon Dec 09 07:31:31 1996",
bibsource = "https://www.math.utah.edu/pub/tex/bib/tods.bib",
price = "US\$29.95",
series = "Morgan Kaufmann series in data management systems",
acknowledgement = ack-nhfb,
}
