KDD Nuggets Index

--
Discovery community, focusing on the latest research and applications.

Contributions are most welcome and should be emailed,
with a DESCRIPTIVE subject line (and a URL, when available) to (kdd@gte.com).
E-mail add/delete requests to (kdd-request@gte.com).

Nuggets frequency is approximately weekly.
Back issues of Nuggets, a catalog of S*i*ftware (data mining tools),
and a wealth of other information on Data Mining and Knowledge Discovery
is available at Knowledge Discovery Mine site, URL http://info.gte.com/~kdd.

-- Gregory Piatetsky-Shapiro (moderator)

********************* Official disclaimer ***********************************
* All opinions expressed herein are those of the writers (or the moderator) *
* and not necessarily of their respective employers (or GTE Laboratories) *
*****************************************************************************

~~~~~~~~~~~~ Quotable Quote ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The advancement and diffusion of knowledge is the only guardian of
true liberty.....
James Madison, 4th U.S. President
(thanks to Kris Koperski, (koperski@cs.sfu.ca))

Previous 1 Next Top

>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From: 'Christoph Schommer' (schommer@dbis.informatik.uni-frankfurt.de)
Date: Fri, 6 Sep 1996 11:41:17 +0200
Subject: Data Mining Lab

Dear Dr. Piatetsky-Shapiro,

this is to inform you that the Dept. of. Computer
Science - Databases and Information System -
(Roberto Zicari) of the Goethe-University of Frankfurt/Main
has etablished a

'Laboratory for Data Mining'.

The lab has the following purposes:

The Laboratory for Data Mining aims at bringing together
research and industry and offers the following services
to industries and institutions:

o A location where advanced software and/or beta releases of
products or advanced appplications can be installed and tested.

o Joint projects with industry, ranging from joint master theses
up to more involved projects.

o Offering an open forum for presentations from industry

Currently we have two cooperations with industry but we
attempt to get more contacts and partners.

More Infos can be seen at the following URL:

http://www.dbis.informatik.uni-frankfurt.de/CC/LDM/

Could you please include this in the next nuggets issue?

Thank you very much!
Best Regards,
Christoph Schommer

--
____________________________________
_ _
_ Christoph Schommer, Johann Wolfgang Goethe-University, _
_ Dept. of Computer Science, Databases and Information Systems (DBIS) _
_ PO Box 11 19 32, Robert-Mayer-Str. 11-15, 60054 Frankfurt am Main, _
_ Germany, Phone: ++49.69.798.28823, Fax: ++49.69.747021, _
_ Email: schommer@informatik.uni-frankfurt.de _
_ URL: http://www.dbis.informatik.uni-frankfurt.de/~schommer/ _
_ _
____________________________________

Previous 2 Next Top

>~~~Publications:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Date: Thu, 5 Sep 1996 11:21:44 -0400
From: peter@ai.iit.nrc.ca (Peter Turney)

Geoff Webb's paper, 'Further Experimental Evidence against the Utility
of Occam's Razor', is available on-line, in the Journal of Artificial
Intelligence Research:

http://ai.iit.nrc.ca/cgi-bin/jair-abstract?webb96a

The above URL will give you the abstract of the paper and links to the
PostScript file. With JAIR's new 'Ask the Author' facility, it is
possible to post anonymous questions to JAIR authors, about their
papers.

Sincerely,
Peter Turney, peter@ai.iit.nrc.ca

Previous 3 Next Top

>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Date: Thu, 5 Sep 1996 15:51:30 +0100
From: M.Ramoni@open.ac.uk (Marco Ramoni)

The following reports are available on the WWW. Could you please post the
notice on your mailing list?

Thanks in advance

Marco Ramoni

--------------------------------------------------------------------------
Title: Robust Learning with Missing Data
Authors: Marco Ramoni [1] and Paola Sebastiani [2]
1.Knowledge Media Institute, The Open University.
2.Department of Actuarial Science and Statistics, City University.

Keywords: Bayesian Belief Networks; Machine Learning; Robustness;
Dirichlet Distribution; Missing Data; Gibbs Sampling.
TR number: KMI-TR-28
Date: July, 1996

Abstract:

Bayesian methods are becoming increasingly popular in the development
of intelligent machines. Bayesian Belief Networks (BBNs) are nowaday
a prominent reasoning method and, during the past few years, several
efforts have been addressed to develop methods able to learn BBNs
directly from databases. However, all these methods assume that the
database is complete or, at least, that unreported data are missing at
random. Unfortunately, real-world databases are rarely complete and
the 'Missing at Random' assumption is often unrealistic. This paper
shows that this assumption can dramatically affect the reliability of
the learned BBN and introduces a robust method to learn conditional
probabilities in a BBN, which does not rely on this assumption. In
order to drop this assumption, we have to change the overall learning
strategy used by traditional Bayesian methods: our method bounds the
set of all posterior probabilities consistent with the database and
proceed by refining this set as more information becomes available. An
experimental comparison - using both an artificial example and a real
medical application - of our method with a powerful stochastic
simulator will show a dramatic gain in robustness and the
computational advantages of our deterministic method.

Abstract: http://kmi.open.ac.uk/kmi-abstracts/kmi-tr-28-abstract.html
PS Version: ftp://kmi.open.ac.uk/web/techreports/papers/kmi-tr-28.ps.gz (33
pages, 268K)
Web Version: http://kmi.open.ac.uk/~marco/papers/kmi-tr-28

--------------------------------------------------------------------------
Title: Robust Parameter Learning in Bayesian Networks with Missing Data
Authors: Marco Ramoni [1] and Paola Sebastiani [2]
1.Knowledge Media Institute, The Open University.
2.Department of Actuarial Science and Statistics, City University.

Keywords: Bayesian Belief Networks; Robustness; Machine Learning; Dirichlet
Distribution; Missing Data; Monte Carlo Methods.
TR number: KMI-TR-29
Date: July, 1996

Abstract:

Bayesian belief Networks (BBNs) are a powerful formalism for knowledge
representation and reasoning under uncertainty. During the past few
years, Artificial Intelligence met Statistics in the quest to develop
effective methods to learn BBNs directly from real-world databases.
Unfortunately, real-world databases include missing and/or unreported
data whose presence challenges traditional learning techniques, from
both the theoretical and computational point of view. This paper
outlines a new method to learn the probabilities defining a BBNs from
incomplete databases. The basic assumption of this method is that the
BBN generated by the learning process should enable the problem solver
to reason and make decisions on the basis of the currently available
information. This assumption requires the learning method to return
results whose precision is a monotonic increasing function of the
available information. The intuition behind our method is close to the
robust sensitivity analysis interpretation of probability: the method
computes the convex set of possible distributions defined by the
available information and proceeds by refining this set as more
information becomes available. Finally, experimental results will be
presented comparing this approach to a popular Monte Carlo method.

Abstract: http://kmi.open.ac.uk/kmi-abstracts/kmi-tr-29-abstract.html
PS Version: ftp://kmi.open.ac.uk/web/techreports/papers/kmi-tr-29.ps.gz (5
pages, 70K)
Web Version: http://kmi.open.ac.uk/~marco/papers/kmi-tr-29

--
Marco Ramoni
Knowledge Media Institute Phone: +44-1908-65-5721
The Open University Fax: +44-1908-65-3169
Walton Hall Email: M.Ramoni@open.ac.uk
Milton Keynes MK7 6AA URL: http://kmi.open.ac.uk/~marco
UNITED KINGDOM CUSeeMe: 137.108.81.18

Previous 4 Next Top

>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Date: Sun, 8 Sep 1996 14:34:02 -0700
From: datamine@ix.netcom.com (IDI)

Decision Tree and Rule Induction method have been adopted by data mining
applications among many other algorithms.

Many customers ask us what is the difference between Rule Induction and
Decision Tree and how to select the method for different applications in
order to make the best of each approach.

Therefore, Information Discovery, Inc. worked with several industry analysts
and produced a report,'Rule is better than Decision Tree' in some area of
data mining critical applications. If any reader like to receive a copy of
this research report, please forward their requst with company name, address
and telephone number to

datamine@ix.netcom.com.

The report is free.

Diana Lin
Information Discovery, Inc.
Tel: 310-937-3600

Previous 5 Next Top

>~~~Siftware:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From: Wan Gong (wgong@cs.sfu.ca)
Date: Fri, 6 Sep 1996 11:37:07 -0700 (PDT)
Subject: Siftware entry for DBMiner

Siftware: DBMiner

*URL: http://db.cs.sfu.ca/DBMiner

*Description:
DBMiner, has been developed for interactive mining of multiple-level knowledge in large relational dtabases. It is based on our studies of data mining techniques and our experience in the development of an early system prototype, DBLearn. The system implements a wide spectrum of data mining functions, including generalization, characterization, association, classification, and prediction. By incorporation of several interesting data mining techniques, including attribute-oriented induction, statistical analysis, progressive deepening for mining multiple-level knowledge, and meta-rule guided mining, the system provides a user-friendly, interactive data mining environment with good performance.

*Discovery tasks: Classification, Summarization, Dependency analysis, Visualization, Prediction, Class Comparison

*Comments:
The system has the following distinct features:

It incorporates several interesting data mining techniques, including attribute-oriented induction, progressive deepening for mining
multiple-level rules and meta-rule guided knowledge mining, etc., and implements
a wide spectrum of data mining functions including generalization, characterization, association, classification, and prediction.
It performs interactive data mining at multiple concept levels on any user-specified set of data in a database using an SQL-like Data Mining Query Language, DMQL, or a graphical user interface. Users may interactively set and adjust various thresholds, control a data mining process, perform roll-up or drill-down at multiple concept levels, and generate different forms of outputs, including generalized relations, generalized feature tables, multiple forms of generalized rules, visual presentation of rules, charts, curves, etc.
Efficient implementation techniques have been explored using different data structures, including generalized relations and multiple-dimensional data cubes, and being integrated with relational database techniques. The data mining process may utilize user- or expert-defined set-grouping or schema-level concept hierarchies which can be specified flexibly, adjusted dynamically based on data distribution, and generated automatically for numerical attributes.
Both UNIX and PC (Windows/NT) versions of the system adopt a client/server architecture. The latter communicates with various commercial database systems for data mining using the ODBC technology.

*Platform(s): Windows (95, NT), Unix

*Contact:



 Jiawei Han

 School of Computing Science

 Simon Fraser University

 Burnaby, B.C

 Canada V5A 1S6

 tel: (604)291-4411

 fax: (604)291-3045

 email: han@cs.sfu.ca

*Status: Research Prototype

*Source of information: DBLab of SFU

*Updated: 1996-09-06 by Wan Gong, (i)wgong@cs.sfu.ca

Previous 6 Next Top

>~~~Positions:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From: Graham Williams (Graham.Williams@cbr.dit.csiro.au)
Subject: Position in Computational and Statistical Data Mining (ANU)
Date: 10 Sep 1996 09:13:06 +1000

ACSys Cooperative Research Centre for
Advanced Computational Systems

The Cooperative Research Centre for Advanced Computational Systems
(ACSys) has been established under the Australian Government's CRC
Program with the mission of establishing an internationally
competitive research capability in the area of high performance
advanced computational systems. Facilities include access to a
128-cell Fujitsu AP1000, a 13-processor Fujitsu VPP-300 and a Digital
Alpha ATM Cluster. The Centre's institutional participants are The
Australian National University and CSIRO and its principal commercial
participants are Digital Equipment Corporation, Fujitsu Australia
Limited and Sun Microsystems Australia. ACSys is based at the ANU in
Canberra.

Applications are invited to fill the following position in the
Computational and Statistical Methods for Data Mining Applications
Project. The aim of this project is to develop and investigate new
statistical methods, algorithms and software to be used in practical
data mining applications. The research will be done in close
collaboration with the Data Mining Demonstrator Project of the CRC.

Applicants should have a strong research record and interests in
one or more of the following areas: computational statistics,
statistical methods for large data sets, parallel numerical algorithms
for linear systems and optimisation and data mining algorithms.

Appointment will be for a fixed period of up to two years with the
possibility of extension. Secondments will be considered.

Contact: Dr Markus Hegland, phone (06) 249 3011, fax (06) 249 4812,
email Markus.Hegland@anu.edu.au

Further particulars and selection criteria must be obtained before
applying from Ms Amanda Erbacher or Mr Tim Surendonk, phone (06) 249
2035, fax (06) 249 0747.

Further information including the selection criteria is available
from ftp://acsys.anu.edu.au/pub/ParAlgs

Closing Date: 27 September 1996.

Ref: ACS 28.8.1

Salary: Postdoctoral Fellow (Level A) $34,008 - $41,421 pa
or Research Fellow (Level B) $43,602 - $51,777 pa

Applications addressing the selection criteria should be submitted in
duplicate to: The Secretary, The Australian National University,
Canberra, ACT 0200 quoting the reference number and including
curriculum vitae, list of publications and names and addresses and fax
numbers of at least three referees. The University has a 'no smoking'
policy in all university buildings and vehicles.

THE UNIVERSITY IS AN EQUAL OPPORTUNITY EMPLOYER

--
Dr Graham.Williams@cbr.dit.csiro.au ,--_| Tel: (+61 6) 216 7042
Senior Research Scientist, Data Mining / Fax: (+61 6) 216 7112
CSIRO Div of Info Tech, Aust Nat Univ _.--_*/ GPO Box 664 Canberra
http://www.dit.csiro.au/~gjw v ACT 2601 Australia

Previous 7 Next Top

>~~~Meetings:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Date: Mon, 9 Sep 1996 03:51:06 +0900
From: tsumoto.com@mri.tmd.ac.jp (Shusaku Tsumoto)

**** C A L L F O R PARTICIPATION ****
(Preliminary Version)

THE FOURTH INTERNATIONAL WORKSHOP ON
ROUGH SETS, FUZZY SETS AND MACHINE DISCOVERY (RSFD'96)

Sanjoh Conference Hall,
The University of Tokyo
Hongo,
Tokyo, JAPAN

November 6-8, 1996

Web Page: http://ylab-gw.cs.uec.ac.jp/RSFD96.html
Email: rsfd96@mri.tmd.ac.jp

---------------------------------------------------------------------------
Sponsored by: Information Processing Society of Japan

In Cooperation with
* International Rough Sets Society
* Institute of Electronics, Information and Communication
Engineers of Japan (IEICE)
* Japanese Society for Artificial Intelligence (JSAI)
* Society of Instrument and Control Engineers of Japan (SICE)
* Japan Society for Fuzzy Theory and Systems
* Japan Research Group on Multiple-Valued Logic
Supported by: Inoue Foundation for Science
The Telecommunications Advancement Foundation
Center for Computational Medicine, Tokyo Med. and Dent. Univ.

--------------------------------------------------------------------------

Honorary Chairs: Z. Pawlak, L.A. Zadeh

CALL FOR PARTICIPATION

Rough sets and fuzzy sets are complementary generalizations of classical
sets. The rapid developments of these two approaches form a beginning of
a 'soft mathematics' and provide a basis for 'soft computing', which
includes, along with rough sets, fuzzy logic, neural networks,
probabilistic reasoning, belief networks, learning,
connectionist computing, genetic algorithms.

Machine Discovery is also a growing area, encompassing knowledge
discovery in databases, discovery of regularities (such as
rules, dependencies, empirical equations),
causal structures by using methods of database theory,
artificial intelligence (including machine learning),
rough sets and statistics.

This workshop will allow researchers to present their recent research
results and to exchange their views of
rough sets, fuzzy sets, and machine discovery.
The exchange should lead to mutually beneficial co-operation.

WORKSHOP FORMAT

The workshop is planned as a three-day interdisciplinary conference
focused on various theoretical, methodological, and practical aspects
of rough sets, fuzzy sets and machine discovery. It will be a
combination of invited talks, oral presentations,
system demonstrations,
and a series of 'round-table' discussions intended to stimulate
the development of interdisciplinary understanding. The format will
include the presentation of the fundamentals of rough sets, fuzzy sets
and machine discovery as well as will provide ample time
for discussion and the exchange of ideas.

(Workshop programme will be available in the midst of September,
at the Web page.)

IMPORTANT DATES

September 15: Deadline for the Final Manuscript
October 1: Deadline for Early Registration
November 6-8, Workshop Technical Sessions held

REGISTRATION

People who would like to attend the workshop should fill in a
registration form attached below and send it to the local
chair via air mail, email or FAX:

RSFD96 c/o Shusaku Tsumoto
Department of Information Medicine,
Medical Research Institute,
Tokyo Medical and Dental University
1-5-45 Yushima, Bunkyo-city
Tokyo 113 Japan

FAX: +81-3-5803-0247
Email: rsfd96@mri.tmd.ac.jp

ORGANIZATION

Program Chair: Akira Nakamura
Program Co-Chair: Masao Mukaidono
General Chairs: Wojciech Ziarko and Tsau Young Lin
Organizing Chair: Hiroshi Tanaka
Local Chair: Shusaku Tsumoto

Publicity: Y.Y. Yao , North America, yyao@thunder.lakeheadu.ca
J. Stefanowski, Europe, stefanj@pozn1v.tup.edu.pl
T. Yokomori, Asia, yokomori@base.cs.uec.ac.jp

STEERING COMMITTEE

Z. Pawlak
R. Slowinski
W. Ziarko
T.Y. Lin
J. Grzymala-Busse
A. Nakamura
S. Tsumoto
J. Zytkow

PROGRAM COMMITTEE

James Bezdek, University of West Florida, U.S.A.
Nick Cercone, University of Regina, Canada
Didier Dubois, Universite Paul-Sabatier CNRS, France
Jerzy Grzymala-Busse, University of Kansas, U.S.A.
Mitsuru Ishizuka, The University of Tokyo, Japan
Willi Kloesgen, GMD, Germany
Satoshi Kobayashi, The University of Electrocommunication, Japan
Shigenobu Kobayashi, Tokyo Institute of Technology, Japan
Tsau Young Lin, San Jose State University, U.S.A.
Ryszard Michalski, George Mason University, U.S.A.
Masao Mukaidono, Meiji University, Japan
Toshinori Munakata, Cleveland State University, U.S.A.
Hiroshi Motoda, Osaka University, Japan
Kaoru Hirota, Tokyo Institute of Technology, Japan
Masahiro Inuiguchi, Hiroshima University, Japan
Kazuo Nakamura, Nagaoka University of Technology, Japan
Charles Nguyen, Catholic University of America, U.S.A.
Masayuki Numao, Tokyo Institute of Technology, Japan
Zdzislaw Pawlak, Warsaw University of Technology, Poland
Zbigniew Ras, University of North Carolina, U.S.A.
Andrzej Skowron, Warsaw University, Poland
Gregory Piatetsky-Shapiro, GTE Laboratories, U.S.A.
Roman Slowinski, Technical University of Poznan, Poland
Jerzy Stefanowski, Technical University of Poznan, Poland
Roman Swiniarski, San Diego State University, U.S.A.
Hideo Tanaka, Universiy of Osaka Prefecture, Japan
Anita Wasilewska, State University of New York, U.S.A.
Michael Wong, University of Regina, Canada
Yiyu Yao, Lakehead University, Canada
Takahira Yamaguchi, Shizuoka University, Japan
Wojciech Ziarko, University of Regina, Canada
Jan Zytkow, Wichita State University, U.S.A.

PUBLICATION

The proceedings will be firstly published by Tokyo University Press,
and distributed to all registered participants at the workshop.
After the workshop, the revised papers will be under a review
process, and the proceedings will be published as a book.

Moreover, the best selected papers are considered to
include in the special volume of academic journals.

-----------------------------------------------------------------

==========================================================================
REGISTRATION FORM
==========================================================================

If you are going to attend the conference (submitting or not a paper),
please send the following registration form, preferably by electronic mail
(rsfd96@mri.tmd.ac.jp) to the Secretariat.

......................... cut here .............................

Registration Form

Surname.........................................................
First Name .....................................................
Title :................................................................
Affiliation.....................................................
Address ........................................................
City .................... Zip Code.......... Country ........
Phone: ................. Fax: ...............................
E-mail .........................................................

Question: If the banquet will be held, would you like to attend ?

Yes [ ] No [ ]

......................... cut here .............................

==========================================================================
PAYMENT FORM
==========================================================================

Send the following payment form, by surface mail or Facsimile to
the Secretariat. For security reasons, electronic submissions are not
accepted.

Surface Address :
RSFD96 c/o Shusaku Tsumoto
Department of Information Medicine,
Tokyo Medical and Dental University
1-5-45 Yushima
Bunkyo-city, Tokyo 113
JAPAN

FAX Address: +81-3-5803-0247

Conference Fees (including proceedings, reception party, coffee breaks)

Before Oct 1st 15,000.- Yen
After Oct 1st 20,000.- Yen
Special fee for students (not including reception party)
5000.- Yen (Before Oct 1st)
7500.- Yen (After Oct 1st)

Additional Proceedings 5000.Yen

= 108 Yen is approximately equal to 1 US$.

......................... cut here .............................

Payment Form

A) Bring Money to the Conference site.

B) Credit Card
I, .......................................................
authorize the withdraw of ........................... Yen
plus 7%, corresponding to credit card charge:
( )Visa ( )Master Card
Card Number: .............................................
Expiration date: .........................................
Date: ....................................................
Signature:

-------------------------------------------------------------------------
HOTELS

a) Hotel Kizankan
b) Suidobashi Grand
c) Asia Kaikan
d) Ikenohata Culture Center

a) b) c)
d)
Double 13,000- 12,000.- 7,800.- 11,000.-
Single 8,000- 7,000.- 6,100.- (5,500.-)

Walking time to
Conference site 15 m. 25 m. 35 m.* 20 m.
Credit Card Accept Accept Not Accept

= Hotels are located in the heart of the city and within walking
distance from the University of Tokyo.
= Prices are per room - not per person.
= Prices are in Japanese Yen, without including breakfast and taxes.
* It takes 20 min by subway to get to the Nezu station(180), and 15 min by foot
to get from the station to the conference site.

-------------------------------------------------------------------------

.......................... cut here ............................

HOTEL & TRANSFER RESERVATION FORM

Surname: _______________________ Hotel choice: a)|_| b)|_| c)|_| d)|_|
_ _
First Name: _______________________ Occupancy: Twin|_| Single |_|

Mailing Address:_________________________ (Number of rooms and type )

_____________________________________ Date of arrival: ______________

_____________________________________ Number of nights:______

Phone:______________________________ Fax:_____________________________

Transfer in:
Flight number ___________ Date: ___________ Pers:___

Transfer out:
Flight number ___________ Date: ___________ Pers:___

......................... cut here .............................

+----------------------------------------------------------------------+
| |& %| | Shusaku Tsumoto |
| | & % | |~~| | Assistant Professor |
| | V | |~~|& | Department of Information Medicine |
| Medical Research Institute |
| TEL: +81-3-5803-5840 Tokyo Medical and Dental Unversity |
| FAX: +81-3-5803-0247 1-5-45 Yushima, Bunkyo-city, |
| E-mail: tsumoto.com@mri.tmd.ac.jp Tokyo 113 Japan |
| << Forever Voyaging ....>> |
+----------------------------------------------------------------------+

Previous 8 Next Top

>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From: 'Max Bramer' (bramerma@sis.port.ac.uk)
Organization: University of Portsmouth
To: ai-sges@mailbase.ac.uk, kdd@gte.com, kaw@swi.psy.uva.nl,
HCINews@cs.ucl.ac.uk
Date: Fri, 6 Sep 1996 14:56:13 +0100
Subject: Expert Systems 96: Information and Registration Leaflet

*Please share this information with your friends and colleagues*
(We apologise if you receive multiple copies)
--------------------------
For further details see http://www.sis.port.ac.uk/sges.html
--------------------------
INFORMATION AND REGISTRATION LEAFLET
EXPERT SYSTEMS '96
16th Annual Conference of the
British Computer Society
Specialist Group on Expert Systems
Cambridge, UK : 16-18 December 1996

(BCS SGES is a member of ECCAI)

APPLICATION KEYNOTE ADDRESS
Knowledge Technology: Which way forward?
Mari Georges : ILOG, France

TECHNICAL KEYNOTE ADDRESS
Soft Computing and Fuzzy Logic in Intelligent Systems
Professor Lotfi Zadeh : University of California, USA

Co-sponsored by:
Augusta Technology
British Airways
Cogsys
Hewlett Packard
Integral Solutions
The Institution of Electrical Engineers
Welsh Development Agency

Endorsed by:
The Department of Trade and Industry
The Engineering and Physical Sciences Research Council and
The Information Society Initiative

This conference qualifies for the IEE and BCS CPD Schemes

EXPERT SYSTEMS 96
DEVELOPMENTS IN TECHNOLOGY; SUCCESSES IN APPLICATION
INTRODUCTION
Expert Systems '96 is the sixteenth Annual Conference of the British
Computer Society's Specialist Group on Expert Systems (SGES). The two
principal aims of the Conference are to review the recent technical
advances in Knowledge-based systems technology and, importantly, show
how this leading edge technology has been applied to solve business
problems. To meet these objectives, ES96 has a number of parallel
sessions on both the technology and applications. The programme also
includes tutorials to provide greater depth in four selected topics.
We are confident that ES96 has the widest possible appeal to the
industrial,commercial and academic communities throughout Europe.

WHO SHOULD ATTEND?
The Conference is aimed at those who wish to update themselves with
news and views of recent developments, understand how other groups are
applying the technology and exchange ideas with leading international
experts in the field. Our goal, as always, is for ES95 to be a meeting
place for the international knowledge based systems community. The
two-track Conference, the Tutorials and the Exhibition are designed to
provide a wide range of options for delegates, whether they are
newcomers to the technology or seasoned practitioners. The social
programme provides an opportunity to relax, meet old friends and make
new contacts.

TUTORIALS
ES96 is supported by four state-of-the-art tutorials:
Knowledge Asset Management
I Filby, A Macintosh : AIAI, University of Edinburgh, Scotland

Intelligent Assistant Systems
P Brezillon : LAFORIA, Universite de Paris VI, France

Effective Diagnostic Systems
J Hunt, C Price : University of Wales

Knowledge Discovery & Data Mining
M Bramer, I Dattani, S Thompson, W Liu : University of Portsmouth,
England

The presenters are all technical authorities in their own right.
Delegates will find these tutorials to be especially valuable where
there is a current need to consider the introduction of these
technologies into their own organisations.

TWO-DAY CONFERENCE
The papers in both the Technical and Application Streams have been
selected through a rigorous process of refereeing. The papers in the
Application Track have been chosen to reflect the practical issues of
applying the technology to real world problems. Papers from both
tracks will be published as separate volumes of the Conference
proceedings - Research and Development in Expert Systems XIII and
Applications and Innovations in Expert Systems IV.

THE DTI/EPSRC ISIP PROGRAMME
Once again the event this year is endorsed by both the DTI and EPSRC
and there will be two sessions containing papers for the dissemination
of information from their jointly funded 13 million pound Intelligent
Systems Integration Programme (ISIP). The 8 projects are : ADEPT -
Advanced Decision Environment for Process Task CAKE - Computer Aided
Knowledge Engineering CHRONOS - A multi Agent View of Planning &
Scheduling ENTERPRISE - Managing Change through Enterprise Models IA -
Intelligent Architecture IMIS - Intelligent Marketing Integrated
System MOBIT - Model Based Intelligent Tutoring STAR - Standardised
Argument Report Companies involved include: Avanti Architects, Bovis
Construction, British Steel (Teeside), Broadgate Properties, BT Labs,
Cogsys, Criterian Software, DEGW London, Digital Equipment, Henley
Centre for Forecasting, IBM UK, ICI Engineering, ICRF, LHASA UK,
Lloyds Register, Logic Programming Associates, Logica Cambridge,
PowerGen, Qualum, Richard Rogers Partnership, Scomagg, Scottish
Nuclear, Smallworld Systems, SUBSL, TSB, Unilever, United Distillers.

THE GREAT DEBATE
'Intelligent Agents that Learn are Dangerous'
CHAIRMAN : Professor Max Bramer, Portsmouth University, England
Supported by a panel of experts

AWARDS AND SPONSORSHIP
Our thanks to British Airways and Hewlett Packard, who will once again
be sponsoring the prizes for the best submitted applications and
technical papers. There will also be a best presentation award.
Winners of the best submitted papers have already been invited by the
Conference Committee to make extended presentations of their papers,
at which time they will receive their prizes. The Best Presentation
Award will be based on the voting of delegates at the conference. All
winners will receive a trophy and a generous cash prize.

Thanks also Cogsys, Augusta Technology and WDA for their generous
support and to Integral Solutions Limited (ISL) who will sponsor two
day attendance at ES96 for up to two academic attendees who have not
previously attended an SGES Conference.

TECHNICAL STREAM
Tuesday 17 December 1996
SESSION 1: KNOWLEDGE MODELLING AND REFINEMENT
Building Ontologies : Towards a Unified Methodology
M Uschold : AIAI, University of Edinburgh, Scotland

Knowledge Refinement & Generation
A Basden : ITI, University of Salford, England; P R Hibberd :
University of Glamorgan, Wales

A Platform for Knowledge Modelling and Knowledge Integration
G Willumsen, O Brevik : SINTEF Telecom and Informatics; I Nordbo :
NOVIT, Norway

The Role of Test Cases in Automated Knowledge Refinement
G J Palmer, S Craw : Robert Gordon University, Scotland

SESSION 2: KNOWLEDGE REPRESENTATION & MANAGEMENT
Dynamically Assessed and Reasoned Task (DART) Networks
P Jarvis, G Winstanley : University of Brighton, England

An Antecedent-First Algorithm to Support Inference on Networks of
Rules A Brown, A Basden : ITI, University of Salford, England

Experience-Guided Machine Translation - an Expert System Approach G
Zhao, J Tsujii : UMIST, England

A Three-Layer Hierarchy for Representing Chinese Characters
M Ren, D Al-Dabass, D Su : Nottingham Trent University, England

Foundations for a Proposed Method of Applying Software Metrics in
Knowledge Engineering E Tovar : Universidad Politecnica de Madrid,
Spain

SESSION 3: CASE-BASED REASONING
Introducing an Immune Response into a CBR System for Data Mining
J Hunt, A Fellows : University of Wales

Using NLP in CBR Systems
D Job, V Shankararaman : Napier University, Scotland; B Cordingley :
BT Laboratories, England

Towards a Methodology for Case-Based Systems
O Curet : City University; M Jackson : London Business School, England

The Effect of Standardized Case Representation and Cross-Structural
Similarity on Retrieval Robustness M A Montazeri : Isfahan University
of Technology, Iran

Wednesday 18 December 1996
BEST TECHNICAL PAPER
FLARE : Induction with Prior Knowledge
C Giraud-Carrier : University of Bristol, UK

SESSION 4: MACHINE LEARNING & DATA MINING
Qualitative Assessment of Rule Interest in Data Mining
D McSherry : University of Ulster, N Ireland

Subsetting as an Approach to Distributed Learning
S Thompson, M Bramer : University of Portsmouth, England

The Identification of Training Examples which cause Difficulties for
Machine Learning K Whelan, P E File, W B Samson, A Milne : University
of Abertay Dundee, Scotland

Deriving Statistical Aggregates for Knowledge Discovery in Distributed
Databases S McClean, B Scotney : University of Ulster, N Ireland

SESSION 5: EXPERT SYSTEMS TOOLS & HYBRID SYSTEMS
Class Hierarchies as a Multi-Purpose Knowledge Representation in a
Requirements Capture and Design Tool J Levine : University of
Edinburgh, Scotland; I Rogers : University of Sussex, England; T
Bennington : Racal Instruments Ltd, England; C Pattison : Intelligent
Applications Ltd, Scotland

A Tool for Creative Design of Knowledge Bases
A Basden, A J Brown, S D A Tetlow : ITI, University of Salford,
England; P R Hibberd : University of Glamorgan, Wales

Family-Negotiator : An Intelligent Tool for Supporting Human
Negotiation E Bellucci, J Zeleznikow : La Trobe University, Australia

A Technique for Generating Partial Rule-based Advice from a Hybrid
Knowledge Base K Pal, J A Campbell : University College London,
England

APPLICATION STREAM
Tuesday 17 December 1996
BEST APPLICATION PAPER
The GhostWriter Project : A Demonstration of the Use of AI Techniques
in the Production of Technical Publications B P Marchant : British
Aerospace Defence, England; F Cerbah : Dassault Aviation, France; C S
Mellish : University of Edinburgh, Scotland

SESSION 1. - MANUFACTURING & ENGINEERING - DESIGN
Application of Knowledge Based Engineering in a Design and
Manufacturing Environment for the 21st Century J Saggu : CEST, England

The Collaborative Requirements Capture Tool : A Multiparadigm Solution
to a Real-World Problem I Rogers, L Plowman : Sussex University,
England; J Levine : Edinburgh University; C Pattison : Intelligent
Applications Ltd, Scotland

Intelligent Agents Architecture for Concurrent Engineering Design
Support B Lees, D G Jenkins : University of Paisley, Scotland

Formation - Knowledge-Based Layout of Classified Telephone Directories
G Anderson, A Casson, A Macintosh, R Rae : AIAI, University of
Edinburgh, Scotland; B Gleeson, S Carter : Pindar Set Ltd, England

SESSION 2. - MEDICAL AND DECISION SUPPORT SYSTEMS
The Comparison of Two Classification Techniques in Screening for
Gastro-oesophageal Cancer A P White, M T Hallissey, L W L Fielding :
University of Birmingham; W Z Liu : University of Portsmouth, England

Uncertain Standards : The NHS Standards Selection System
C Dobbyn, N Crook : Oxford Brookes University, England

Decision Support Paradigms for Presenting in General Practice -
Lessons from the PRODIGY Trials B Sugden, I Purves : University of
Newcastle upon Tyne, England

An AI Approach to Energy Cost Minimisation within a Wastewater
Treatment Environment P Case-Upton : United Utilities plc; G Page :
Liverpool John Moores University, England

ESADI - A Knowledge Based Advisory System Shell
A Kispal, M A Bramer : University of Portsmouth, England

SESSION 4. - MANUFACTURING & ENGINEERING - FAULT DIAGNOSIS
Automotive Diagnosis using Generated Fault Trees
C Price, M Wilson : University of Wales, Aberystwyth; C Cain : Ford
Scientific Research Laboratory, USA

Inductive Learning for Detection of Surface Defects in Flat Steel
Products W Z Liu : University of Portsmouth, England

An Expert System for Fault Diagnosis in the Scanning Electron
Microscope N H M Caldwell, B C Breton, D M Holburn : Cambridge
University, England

A Review and Evaluation of the Application of Case-Based Reasoning
(CBR) Technology in Aircraft Maintenance I Dattani, M A Bramer :
University of Portsmouth, R V Magaldi : British Airways plc, England

SESSION 5. - MANUFACTURING & ENGINEERING - MONITORING/ASSESSMENT
& TRAINING
AMaDeOS - A Computerised Knowledge Based Expert System for Structural
Integrity Assurance J A R Ibrahim, J K Ward : BOMEL Engineering
Consultants; J A Secker : City University, England

Building a KBS for Health and Safety Assessment
J Kingston : AIAI, University of Edinburgh, Scotland

An Intelligent Rules Based Data Stream Processor
M Moulton : University of Portsmouth, England

The Application of Model Based Industrial Training
A van de Brug : Digital Equipment Scotland Limited; S Ross : Scottish
Nuclear Limited, Scotland

SESSION 6: INFORMATION & KNOWLEDGE MANAGEMENT
Discovering Knowledge in the Legal Domain : The Split-Up System
J Zeleznikow, A Stranieri : La Trobe University, Australia

The Swiss Bank Corporation Know-How Project
F Block : Swiss Bank Corporation, Switzerland; L Poynter : Inference
International, England

Case-Based Reasoning for Knowledge Capitalisation
G Simon; M Grandbastien : CRIN/CNRS, Universite Henri Poincare, France

Knowledge-Based Large Screen Command Situation Display
R E T Kissane : MOD Procurement Executive; J A H Miles : DRA
Portsdown; V V S S Sastry : Cranfield University, RMCS Shrivenham,
England

SPECIALIST GROUP ON EXPERT SYSTEMS
The SGES is one of Europe's longest established groups working to
support the local community of expert and knowledge-based systems
developers and users. In addition to the Annual Conference, membership
of the SGES provides access to a wealth of technical information,
including a regular newsletter, monthly information packs, workshops,
local events, special interest groups and more. For further
information about the SGES, including details of Corporate Membership,
call the SGES Administration on + 44(0)1256 55899. You do not need to
be a member of the British Computer Society to join the SGES.

**N.B.All non-members registering to attend ES96 will receive free
membership of the group from the date of the conference to the end of
1997, thus entitling them to all membership benefits including
members-rate registration for ES97. Details of membership benefits
can be obtained from
http://www.sis.port.ac.uk/sges,html
or
sges@bcs.org.uk**

ES95 CONFERENCE COMMITTEE
Dr Ian Watson, University of Salford
(Conference Chair)
Professor Max Bramer, University of Porsmouth
(Deputy Conference Chair/Tutorial Co-ordinator)
Mr John Nealon, Oxford Brookes University
(Technical Programme Chair)
Dr John Hunt, University of Wales, Aberystwyth
(Deputy Technical Programme Chair)
Mrs Ann Macintosh, AIAI, University of Edinburgh
(Application Programme Chairman)
Mr Chris Cooper, Coopers & Lybrand
(Deputy Application Programme Chairman)
Dr Alan Montgomery, Integral Solutions Ltd
(Exhibition Co-ordinator)

THE EXHIBITION
As in previous years we are keen to provide a Conference with the
widest possible interest and greatest value to the delegates. The
suppliers of products and services are essential members of the KBS
community in the UK, and the conference programme can only benefit
from the demonstrations and hands-on opportunities provided by an
Exhibition. A table-top Exhibition will run alongside the Conference
and will include demonstrations by most of the ISIP groups. There will
be a limited number of spaces available and potential exhibitors are
encouraged to book early. The exhibition package includes: * display
space (approx 2m2) with table, chairs & power points * lunches and
refreshments daily * full address list of all delegates

SPONSORSHIP
Conferences such as ES96 are, for many companies, an excellent
opportunity to create or reinforce their image within a community such
as the KBS and expert systems users in the UK. This does not only
apply to suppliers of products and services, but also to larger
corporate users and software developers for whom recruitment is a
major issue. Many opportunities exist at ES96 where financial support
in the form of sponsorship will be invaluable in ensuring that we
provide the most memorable event for every participant.

PROMOTIONAL LITERATURE SERVICE
There is an opportunity for companies to insert their promotional
literature in the delegates' wallets, at a cost of 250.00. A sample of
literature must be sent when making your booking for this service.

PROCEEDINGS
The proceedings will be published by SGES. The bound set will be
available from TCT once the Conference has closed.

VENUE
The college of St John the Evangelist is set on the Backs of the River
Cam in one of the most beautiful sits in the city of Cambridge. The
serene atmosphere of the ancient 16th and 17th century courts is
complemented by the comfort of its modern accommodation and lecture
theatres, with the very latest in audio-visual and presentation
technology.

WELCOME RECEPTION & GALA DINNER
Delegates are invited to attend a Welcome Reception on the evening of
Monday 16 December 1996. The reception will be held in the Exhibition
area and will be an ideal opportunity to meet up with old friends and
colleagues and make new ones. The Gala Dinner will be held on the
evening of Tuesday 17 December 1996 and will take place within the
Dining Hall at St John's College. The Mayor of Cambridge, Councillor
Mr John Durrant and the Mayoress Mrs Elena Durrant will be our guests.
We are delighted to have as this year's after dinner speaker Mr Aaron
Sloman of Birmingham University.

ACCOMMODATION
A limited number of bedrooms have been reserved at St Johns College.
These can be booked using the registration form and will be allocated
on a first come, first served basis. A list of alternative
accommodation is available from the Secretariat.

STUDENTS
There are a limited number of places at a special rate for bona fide
research students, available on application. Special group discounts
and day delegate rates may also be available.

CANCELLATIONS
Fees will be refunded in full for cancellations received at least six
weeks prior to the event. Cancellations received more than 28 days and
less than six weeks prior to the event will attract a 15%
administration charge. No refund will be made for cancellations
received less than 28 days prior to the event. However substitutions
may be made at any time.

METHODS OF PAYMENT
FULL PAYMENT OF THE REGISTRATION FEE MUST ACCOMPANY FORMS.
Please submit one form for each delegate. Photocopies of a blank form
may be used. * Cheques should be made payable to The Conference
Team and drawn in sterling on a UK bank. * Bank transfers in
sterling should be paid to their account at: National Westminster
Bank, 231 Bedford Road, Kempston, Bedford MK42 8DA Account no:82844003
Bank Sort Code:60-12-45 NB There is an additional charge of
5 pounds for overseas sterling bank transfers * Sterling Bank
Drafts should be used by delegates wishing to attend from countries
with currency restrictions. Quote ES96 and name of delegate and
company on all transactions. THE REGISTRATION FORM IS AN INVOICE AND
WILL BE RETURNED TO YOU AS AN OFFICIAL VAT RECEIPTED INVOICE WHEN
PAYMENT HAS BEEN RECEIVED AND THE DELEGATE NUMBER ALLOCATED. NO OTHER
FORM OF INVOICE WILL BE ISSUED.

FURTHER INFORMATION AND ENQUIRIES
ES96 is organised by The Conference Team on behalf of the BCS
Specialist Group on Expert Systems. Enquiries should be addressed to
Ms Kit Stones The Conference Team, ES96 17 Spring Road Kempston
Bedford MK42 8LS UK Tel/Fax: (0)1234 302490 Email:
kstonestct@cix.compulink.co.uk
================================================ CONFERENCE INVOICE
AND REGISTRATION FORM EXPERT SYSTEMS 96 Cambridge, UK : 16-18 December
1996

Payment MUST accompany this form

Return to: The Conference Team, 17 Spring Road, Kempston
Bedford MK42 8LS United Kingdom
Tel/Fax:(01234) 302490
VAT Reg No. GB 608 6660 26
F.A.O. Ms Kit Stones, Conference Secretariat

Prof/Dr/Eur.Ing/Mr/Mrs/Miss/Ms (delete as applicable)

Forename

Surname

Position/Appointment

Organisation/Company

Postal Address

Post/ZipCode

Country

Telephone

Fax

SGES/IEE Memb No

Email

O Payment enclosed by cheque, in pounds sterling, made
payable to The Conference Team and drawn on a UK bank

O Payment is being made by Bank Transfer on.......(date)

On receipt of payment your form will be numbered, stamped and
returned as confirmation of your place at the Conference.

To qualify for members' reduction, you must be a member of SGES/IEE as
at 30/9/96 For each of the following options please tick your
status/choice and complete the amount due.

VAT is charged at 17.5% All amounts are in pounds sterling

IF BOOKING FOR FULL CONFERENCE ALSO TICK CHOSEN TUTORIALS
Full Conference Fee received on or before 18 November 1996
Non-Member 690 + VAT 120.75 = 810.75
Non-Member Academic 535 + VAT 93.63 = 628.63
SGES/IEE Member 565 + VAT 98.88 = 663.88
SGES/IEE Academic Member 430 + VAT 75.25 = 505.25

Two Day Conference Fee received on or before 18 November 1996
Non-Member 465 + VAT 81.38 = 546.38
Non-Member Academic 310 + VAT 54.25 = 364.25
SGES/IEE Member 400 + VAT 70.00 = 470.00
SGES/IEE Academic Member 270 + VAT 47.25 = 317.25

Payment received after 18 November 1996 (all categories)
Late payment penalty 50 + VAT 8.75 = 58.75

Tutorial Options
2 x Half-Day Tutorials @ 310 + VAT 54.25 = 364.25
1 x Half-Day Tutorial @ 200 + VAT 35.00 = 235.00

Please tick to show which Tutorial(s) you wish to attend
O Knowledge Asset Management
O Intelligent Assistant Systems
O Effective Diagnostic Systems
O Knowledge Discovery & Data Mining

To Exhibit
Non members 675 + VAT 118.13 = 793.13
SGES/IEE Members 575 + VAT 100.63 = 675.63

Promotional Literature Service 250

Conference Dinner:
I require...extra ticket(s) 40 each

Accommodation: Student accommodation
at St John's College per night B&B 38 + VAT 6.65 = 44.65

Please tick for appropriate nights:
15 16 17 18 December 1995

TOTAL PAYABLE

N.B. Full Conference Fee includes:two half-day tutorials, two-day
conference, three-volume proceedings, lunch and refreshments daily,
invitation to Welcome Reception, one ticket to Gala Dinner.

2-Day Conference Fee excludes tutorials

NOTE:This will become a formal VAT invoice only when a delegate number
has been assigned. ------------------------
For office use only Delegate no Tax point
------------------------
==================================================================
_______________________________________________________

Professor Max Bramer
Department of Information Science
University of Portsmouth
Milton, Southsea PO4 8JF, England
Tel: +44-(0)1705-844444 Fax: +44-(0)1705-844006
email: bramerma@sis.port.ac.uk

Previous 9 Next Top

>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

KDD Nuggets Index

Siftware: DBMiner

Both UNIX and PC (Windows/NT) versions of the system adopt a client/server architecture. The latter communicates with various commercial database systems for data mining using the ODBC technology.