KDD Nuggets 95:30, e-mailed 95-11-22 Contents: News: * GPS, Nov 95 WIRED and Nov 20 ComputerWorld on Data Mining * J. Boykin, Proposed legislation on NII Copyright Law * A. Oudshoff, Query: Data mining methodology ? Publications: * D. Rosen, Paper on "How Good Were Those Probability Predictions?" http://www.scs.unr.edu/~cbmr/people/rosen/erl/ Positions: * M. Bramer, Computer Science Professor at U. of Portsmouth, UK, http://www.sis.port.ac.uk/ Meetings: * M. Bramer, Expert Systems 95, Cambridge, UK, Dec 11-13 1995 * M. Klusch, CFP: CIA-97: Cooperative Information Agents, http://www.informatik.uni-kiel.de/~mkl/cia97.html -- The KDD Nuggets is a moderated mailing list on Data Mining and Knowledge Discovery in Databases (KDD). Contributions are welcome! Email contributions, with a DESCRIPTIVE subject line and a URL, when available, to . 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 . E-mail add/delete requests to . -- 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 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ If you want to see the results of your work immediately, you should become a cobbler. Albert Einstein >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Wed, 22 Nov 1995 9:33:18 -0500 From: gps@gte.com (Gregory Piatetsky-Shapiro) Subject: Nov WIRED and ComputerWorld on Data Mining Nov 1995 Wired magazine, p. 196, (thanks to Padhraic Smyth for the tip) features data mining among the 5 technology topics they think are over-hyped. WIRED says that Data Mining is nothing more than companies using their databases to learn more about their customers, and predicts that the fad will be over in about 3 months. [We will see (:-) GPS] In an unrelated story, ComputerWorld Nov 20, 1995 issue, article "Lightship software puts spotlight on data trends" by Dan Richman (p. 44), reports that Pilot Software in Cambridge is planning to build sophisticated data analysis features into its Lightship decision-support software. (see a full text of Pilot announcement in Nuggets 95:29) With these features, customers can drill into data to find new trends and sometimes even predict the future, the company said. Users said built-in data mining would give them a valuable opportunity for looking at corporate data. "A lot of people think that they understand trends in their data, but technology like data mining could identify trends that people didn't even have inklings about", said George Kossi, a consultant for Monsanto Co, in St. Louis. Six engineers who left the struggling Thinking Machines, Inc. in Cambridge, Mass, are leading the effort to create the Data Mining Engine, an add-on to the Lightship server. When the engine and several associated interface additions start shipping by mid-1996, they will let companies analyze databases as large as 300G bytes, said John Fleming, Pilot's vice president of marketing. Fleming said that SAS institute, Inc in Gary N.C, and Information Harvesting in Cambridge, Mass offer comparable products. >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Mon, 13 Nov 1995 13:06:36 -0500 From: boykin@gte.com (Joseph Boykin) Subject: copyright law FYI - intro statement for proposed legislation... > > STATEMENTS ON INTRODUCED BILLS AND JOINT RESOLUTIONS (Senate - > September 28, 1995) > > THE NATIONAL INFORMATION INFRASTRUCTURE COPYRIGHT PROTECTION ACT > > Mr. HATCH. Mr. President, today, together with my distinguished > colleague from Vermont, Senator Leahy, I am introducing the > National Information Infrastructure Copyright Protection Act of > 1995, which amends the Copyright Act to bring it up to date with > the digital communications age. > > The National Information Infrastructure or `NII' is a fancy name > for what is popularly known as the `information highway.' > Probably most people today experience the information highway by > means of their computers when they use electronic mail or > subscribe to a bulletin board service or use other on-line > services. But these existing services are only dirt roads > compared to the superhighway of information-sharing which lies > ahead. > > The NII of the future will link not only computers, but also > telephones, televisions, radios, fax machines, and more into an > advanced, high-speed, interactive, broadband, digital > communications system. Over this information superhighway, data, > text, voice, sound, and images will travel, and their digital > format will permit them not only to be viewed or heard, but also > to be copied and manipulated. The digital format will also ensure > that copies will be perfect reproductions, without the > degradation that normally occurs today when audio and videotapes > are copied. > > The NII has tremendous potential to improve and enhance our > lives, by providing quick, economical, and high-quality access to > information that educates and entertains as well as informs. When > linked up to a `Global Information Infrastructure,' the NII will > broaden our cultural experiences, and allow American products to > be more widely disseminated. > > Highways, of course, are meant to be used, and in order to be > used, they must be safe. That's why we have `rules of the road' > on our asphalt highways and that's why we need rules for our > digital highway. No manufacturer would ship his or her goods on a > highway if his trucks were routinely hijacked and his or her > goods plundered. Likewise, no producer of intellectual property > will place his or her works on the information superhighway if > they are routinely pirated. We might end up having enormous > access to very little information, unless we can protect property > rights in intellectual works. The piracy problem is particularly > acute in the digital age where perfect copies can be made quickly > and cheaply. > > Protecting the property rights of the owners of intellectual > property not only induces them to make their products available, > it also encourages the creation of new products. Our copyright > laws are based on the conviction that creativity increases when > authors can reap benefits of their creative activity. > > But the NII also promises to increase creativity in a more > dramatic way by providing individual creators with public > distribution of their works outside traditional channels. For > example, authors who have been unsuccessful in finding a > publisher will be able to distribute their works themselves to > great numbers of people at very low cost. > > The bill that I am introducing today begins the process of > designing the rules of the road for the information superhighway. > It was drafted by the Working Group on Intellectual Property > Rights of the Information Infrastructure Task Force. Chaired by > the Honorable Bruce A Lehman, Assistant Secretary of Commerce and > Commissioner of Patents and Trademarks, the Working Group labored > for 2 years examining the intellectual property implications of > the NII to determine if changes were necessary to intellectual > property law and to recommend appropriate statutory language. > > The Working Group drew upon the expertise of 26 departments and > agencies of the Federal Government; it heard the testimony of 30 > witnesses and received some 70 written statements from all > interested parties. On July 7, 1994, it produced a preliminary > draft (`Green Paper'), which opened another period of extensive > testimony and comment. The Final Report, containing a draft of > the legislation that I am introducing today, was unveiled on > September 5, 1995. > > The length and scope of the Working Group's investigation would > alone > commend its recommendations to serious attention, but I have also > studied the legislation and find it an excellent basis for the > Committee on the Judiciary to begin its own examination of the > issues with a view to fine-tuning the solutions proposed by the > Working Group. > > The bill deals with five major areas: > > (1) transmission of copies, > > (2) exemptions for libraries and the visually impaired, > > (3) copyright protection systems, > > (4) copyright management information, and > > (5) remedies. > > In general, the bill provides as follows: > > Transmission of Copies. The bill makes clear that the right of > public distribution in the Copyright Act applies to transmission > of copies and phonorecords of copyrighted works. For example, > this means that transmitting a copy of a computer > > program from one computer to ten other computers without > permission of the copyright owner would ordinarily be an > infringement. > > Exemptions for Libraries and the Visually Impaired. The bill > amends the current exemption for libraries to allow the > preparation of three copies of works in digital format, and it > authorizes the making of a limited number of digital copies by > libraries and archives for purposes of preservation. > > The bill adds a new exemption for non-profit organizations to > reproduce and distribute to the visually impaired--at > cost--Braille, large type, audio or other editions of previously > published literary works, provided that the owner of the > exclusive right to distribute the work in the United States has > not entered the market for such editions during the first year > following first publication. > > Copyright Protection Systems. The bill adds a new section which > prohibits the importation, manufacture or distribution of any > device or product, or the provision of any service, the primary > purpose or effect of which is to deactivate any technological > protections which prevent or inhibit the violation of exclusive > rights under the copyright law. > > Copyright Management Information. `Copyright management > information' is information that identifies the author of the > work, the copyright owner, the terms and conditions for uses of > the work, and other information that the Register of Copyrights > may prescribe. The bill prohibits the dissemination of copyright > management information known to be false and the unauthorized > removal or alteration of copyright management information. > > Remedies. The bill provides for civil penalties for circumvention > of copyright protection systems and for tampering with copyright > management information, including injunction, impoundment, actual > or statutory damages, costs, attorney's fees, and the > modification or destruction of products and devices. > > The bill provides criminal penalties for tampering with copyright > management information--a fine of not more than $500,000 or > imprisonment of not more than 5 years or both. > > There is widespread support for the general thrust of the bill > among interested parties. However, during the hearing process, I > am sure that issues will arise that no one has yet anticipated. > Already, some potential discussion points have been identified: > the scope of the library exemption and the exemption for the > visually impaired, the absence of criminal penalties for > circumvention of copyright protection systems, the use of > encryption as a copyright protection system, the application of > the doctrine of fair use, the development of efficient licensing > models, and the liability of on-line service providers. > > In the interest of time, it may be that fuller discussion and > solution may have to be deferred for those points not covered > expressly in the bill. The fully commercial information > superhighway is not yet here, and we must resign ourselves to a > period of experimentation. We want to be on the cutting edge, not > the bleeding edge of new technology. > > Once again, I would like to commend the Working Group on > Intellectual Property Rights of the Information Infrastructure > Task Force for providing an excellent model for us to work with. > I also recommend to all interested parties that they read the > full report of the Working Group. Without endorsing any of the > specific language of that report, I believe that it provides > useful background material for the recommended changes. > > In conclusion, Mr. President, I would like to thank my colleague > from Vermont, Senator Leahy, for joining me in introducing this > important legislation. > > Mr. President, I ask unanimous consent that a copy of this bill > be printed in the Record. > > There being no objection, the bill was ordered to be printed in > the Record, as follows.... > >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Tue, 14 Nov 1995 16:06 +0100 From: "Oudshoff, A.M." Subject: Data mining methodology We are also working on a methodology for data mining projects, ie which steps are there to take when doing data mining and where are the pitfalls etcetera. Have you ever heard of related work in this area and if not, could you include this question in the KDD nuggets for me? Sincerely yours, Sandra [GPS: There is a good overview of data mining methodology in our forthcoming (december 95?) book Advances in Knowledge Discovery and Data Mining, eds. Fayyad, Piatetsky-Shapiro, Smyth, and Uthurusamy, AAAI/MIT Press, 1995, Chapter 2: The Process of Knowledge Discovery in Databases: A Human-Centered Approach Ronald J. Brachman and Tej Anand URL Apart from that, I am not aware of much work on data mining methodology.] >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >~~~Publications:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Wed, 15 Nov 1995 22:06:31 -0800 Subject: "How Good Were Those Probability Predictions?" (Paper available) From: "David B. Rosen" Announcing availability of the following preprint: How Good Were Those Probability Predictions? The Expected Recommendation Loss (ERL) Scoring Rule David B. Rosen To appear in: Maximum Entropy and Bayesian Methods. (Proceedings of the Thirteenth International Workshop, August 1993.) G. Heidbreder, ed. Kluwer, Dordrecht, The Netherlands, 1996. 8 pages. We present a new way to choose an appropriate scoring rule for evaluating the performance of a "soft classifier", i.e. of a supplier of predicted (inferred/estimated/learned/guessed) probabilities. A scoring rule (probability loss function) is a function of a single such prediction and the corresponding outcome event (true class); its expectation over the data space is the generalization performance of ultimate interest, while its sum or average over some benchmark test data set is an empirical performance measure. A user of probability predictions can apply his own decision threshold, preferring to err on one side, for example, to the extent that the consequences of an erroneous decision are more severe on the other side; this process is the subject of decision theory/analysis. We are not able to specify in advance, with certainty, these relative consequences, i.e. the user's cost matrix (indexed by decision and outcome event) defining his decision-making problem. So we represent this uncertainty itself by a distribution, from which we think of the cost matrix as being drawn. Specifying this distribution determines a uniquely appropriate scoring rule. We can interpret and characterize common scoring rules, such as the logarithmic (cross-entropy), quadratic (squared error or Brier), and the "0-1" misclassification score, as representing different assumptions about the probability that the predictions will be used in various decision-making problems. We discuss the connection to the theory of proper (truth- or honesty-rewarding) scoring rules. PostScript and plain-text versions are available via this Web page: http://www.scs.unr.edu/~cbmr/people/rosen/erl/ Also in Jordan Pollack's NEUROPROSE anon ftp archive as: ftp://archive.cis.ohio-state.edu/pub/neuroprose/rosen.exp-rec-loss.ps.Z (This supersedes an unannounced early version rosen.scoring.ps.Z) Hardcopies cannot be provided. -- David Rosen OR New York Medical College >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >~~~Positions:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ From: bramerma@cv.port.ac.uk Date: Tue, 21 Nov 1995 20:53:09 EST Subject: Vacancy for Professor of Computer Science: University of Portsmouth UNIVERSITY OF PORTSMOUTH FACULTY OF TECHNOLOGY DEPARTMENT OF INFORMATION SCIENCE PROFESSOR OF COMPUTER SCIENCE Salary: circa 36000 pounds sterling Closing Date: 12th December 1995 Reference: TEC 7047 Applications are invited for this new post in a rapidly expanding department in the Faculty of Technology which also includes the School of Mathematical Studies, the Department of Electrical and Electronic Engineering and the Department of Mechanical and Manufacturing Engineering. The Faculty of Technology home page is available on the WWW at http://www.port.ac.uk/tech.html The department offers a wide range of courses in Computer Science and Information Systems at levels ranging from HNC/HND to Master of Science and Doctor of Philosophy as well as short courses for industry. Its main teaching areas are Systems Analysis, Software Engineering, Systems Architecture and Communications. Members of the Department are active in a variety of research areas including Human Computer Interaction, Artificial Intelligence, Parallel Processing, Software Engineering, Information Systems and Intelligent Tutoring Systems. Further information on research in the department is available on the WWW at http://www.sis.port.ac.uk/research/index.html The successful applicant will be expected to provide academic leadership in his/her research area, and to make appropriate contributions to teaching, curriculum development and inter-disciplinary projects. Priority will be given to those with expertise in one or more of the main departmental research areas but those with research specialisms in other areas will also be considered. Applicants with recent industrial experience will be particularly welcome. Further particulars are available from : The Personnel Office, University of Portsmouth, University House, Winston Churchill Avenue, Portsmouth PO1 2UP. Telephone 01705-843421 (24-hour answer phone). Email: jobs@pers.port.ac.uk For an informal discussion prior to application, contact the Head of Department, Professor Max Bramer on 01705-844444 (email: bramerma@csovax.portsmouth.ac.uk), or Professor Tom Addis on 01705-844088. Further information about the department is available via the World-Wide Web at http://www.sis.port.ac.uk/ >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >~~~Meetings:~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Return-Path: From: bramerma@cv.port.ac.uk Date: Sat, 18 Nov 1995 19:43:26 EST To: kdd@gte.com Cc: bramerma@cv.port.ac.uk Subject: Expert Systems 95: December 11th-13th 1995 Content-Type: text Content-Length: 18330 EXPERT SYSTEMS '95 INFORMATION AND REGISTRATION LEAFLET 15th Annual Conference of the British Computer Society Specialist Group on Expert Systems 11-13 December 1995 Queens' College, Cambridge, UK Co-sponsored by:The Institution of Electrical Engineers Endorsed by:the Department of Trade and Industry and The Engineering and Physical Sciences Research Council Conference Chairman: Dr. Robert Milne, IA Ltd. For more information: kstonestct@cix.compulink.co.uk http://www.sis.port.ac.uk/sges/es95_details.html EXPERT SYSTEMS 95: DEVELOPMENTS IN TECHNOLOGY; SUCCESSES IN APPLICATION INTRODUCTION Expert Systems '95 is the fifteenth 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, ES95 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 ES95 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. KEYNOTE SPEAKERS OPENING APPLICATIONS KEYNOTE ADDRESS Professor Mark Fox:University of Toronto, Canada Mark Fox is Professor of Industrial Engineering and holder of the NSERC Industrial Research Chair in Enterprise Integration. Prior to his return to Toronto, he was director of the Centre for Integrated Manufacturing Systems of The Robotics Institute at Carnegie Mellon University and supervised one of the largest efforts in the United States focused on extending and Applying Intelligent Systems, including Artificial Intelligence and Operations Research, to engineering and manufacturing problems. He is also co-founder and past president of Carnegie Group, Inc., a knowledge-based software company that focuses on engineering, manufacturing and telecommunications applications. TECHNICAL KEYNOTE ADDRESS Towards Soft Computing - E H Mamdani:Imperial College, England This talk will re-examine the epistemology of AI and suggest that to make further progress requires an eclectic approach to various available techniques. This fusion of methods of AI and also fusion of AI and HCI has been termed Soft Computing. Any attempt at fusion brings with it new problems that have to be solved. That is the main challenge for Soft Computing. Professor Mamdani is one of the originators of fuzzy logic and is heavily involved in the integration of fuzzy logic with other computing paradigms. THE GREAT DEBATE "Does the Knowledge Acquisition Bottleneck Still Exist?" CHAIRMAN:Professor Derek Sleeman:University of Aberdeen INCLUDING: Nigel Shadbolt:Nottingham University; Ian Nabney:Aston University; John Hunt:University of Aberystwyth; Stephen Muggleton:Oxford University; Colin Shearer:Integral Solutions Ltd TUTORIALS a.m.Integration of Finite Constraint Satisfaction Programming Techniques in Object Oriented Languages P Roy, F Pachet:LAFORIA-IBP, Universite Paris 6, France This tutorial aims at introducing the area of finite domain constraint satisfaction programming (CSP) and its integration with full-fledged object-oriented languages. In the first part the main principles of CSP are presented, through the use of simple examples (algorithms for arc-consistency and enumeration). In the second part we show how object structures may be used in conjunction with CSP and what kind of problems this combination of techniques allows us to solve naturally. The BackTalk system (a canonical integration of CSP techniques in Smalltalk) will be used as an exemplar system throughout the tutorial and demos of working systems will illustrate the course. A basic knowledge of object-oriented programming is required. Merging Symbolic Reasoning with Subsymbolic Tasks J Zeleznikow:La Trobe University; D Hunter:University of Melbourne, Australia Traditional expert systems used deductive reasoning to model expert's knowledge. Such systems have failed to directly use data, do not provide alternative and possibly completing strategies and perform inadequate argumentation and explanation. We propose the use of induction, case-based reasoning and neural networks and an integration of these strategies, to build second generation expert systems. The aim of this tutorial is to demonstrate how traditional symbolic artificial intelligence paradigms can be supplemented with numerical and statistical techniques to build second generation expert systems. Attendees should have a minimal knowledge of rule based expert systems. p.m.Effective Diagnosis Systems C Price and John Hunt:University of Aberystwyth, Wales This tutorial will be of relevance to anyone planning to build practical systems for the following diagnostic tasks:diagnosis of complex machinery - remediation of real-time process problems - intelligent user-oriented help. It will look at the main types of successful diagnostic applications and explain the choices for building each type, with examples and some demonstrations, and considering techniques used, information required, how the systems have been built and how maintainable they are. Technologies covered will include case-based reasoning, rule- based systems, real-time diagnostic tools, causal nets, functional models and reasoning from first principles. Case Based Reasoning Development Tools I Watson:University of Salford, England A follow up to the successful tutorial on Case-Based Reasoning (CBR) held at ES94, this will be of value to companies or researchers planning to investigate the potential of CBR and require advice on software selection and to people who would like to see how the theory of CBR is implemented. The tutorial will introduce delegates to features of the CBR tools currently on the market and the functionality of CBR Express, ESTEEM and ReMind will be demonstrated in detail, thus providing a comprehensive review and comparison of available CBR software. Delegates will be provided with a report summarising the content of thetutorial. TECHNICAL STREAM TUESDAY 12 DECEMBER 1995 SESSION 1 DEKLARE:Knowledge Acquisition and Support System for Re-Design P Fothergill, I Arana:Aberdeen University, Scotland; J Forster, J A Lakunza:Ikerlan, Spain Knowledge Acquisition for Engineering Systems using Bond Graphs W J Crowther, D R Bull, C A Burrows, K A Edge:University of Bath; R M Atkinson, P G Hawkins, D J Woollons:University of Exeter, England Knowledge Elicitation Techniques for Grounded Theory A C Chisnall,R I John, S C Bennett:De Montfort University,England Proof Scheme:A Model to Explicit Strategic Knowledge S Zerhouni-Bendali:Universite P et M Curie; C Jimenez-Dominguez: EDF/DER, France SESSION 2 ELEM:A Method for Inducing Rules from Examples A An, N Shan, C Chan, N Cercone:University of Regina, Canada; X Huang:City University, England Using Induction in Legal Expert Systems J Zeleznikow, A Stranieri, B Lewis:La Trobe University,Australia Refiner+:An Efficient System for Detecting and Removing Inconsistencies in Example Sets M Winter, D Sleeman:University of Aberdeen, Scotland A Theoretical Framework for Evaluating the Performance of Case-Based Reasoning Systems I Dattani, M Bramer, G Leonard:University of Portsmouth,England Integrating Machine Learning, Problem Solving and Explanation D McSherry:University of Ulster, N Ireland SESSION 3 Decision Making and Planning by Autonomous Agents; a Generic Architecture for Safety-Critical Applications J Fox:Imperial Cancer Research Fund; S Das:Imperial College;D Elsdon:Integral Solutions Ltd;P Hammond:Brunel University,England Intelligent Agents for Dynamic Information Management - An Application Development Framework M Andersen, R Smith:Cambridge Consultants Limited; D Catton : Strand Software Technologies Limited, England A Distributed Economic Architectural Shell for Controlling Agent Interactions within Blackboard Systems CJ Satchell,GP Fletcher,CJ Hinde:Loughborough University, England A Methodological Approach for Object Knowledge Bases S Garlatti:Ecole Nationale Superieure des Telecommunications de Bretagne; E Montabord,B Gibaud,Ch Barillot:Laboratoire SIM, France WEDNESDAY 13 DECEMBER 1995 BEST TECHNICAL PAPER Integrating Constraint Satisfaction Techniques with Complex Object Structures F Pachet, P Roy:LAFORIA-IBP, Universite Paris 6, France SESSION 4 VIM:3D Co-operative Diagrams as KBS Surfaces D Dodson, J Secker, R Scott, H Reeves:City University, England Diagrams for Design:A Schema Interpreter for Knowledge Systems T R Addis, J J Townsend Addis:University of Portsmouth, England An Integrated Methodology for the Development of Hybrid Information Systems X Chen,S Kendal,I Potts,P Smith:University of Sunderland,England A Deferred Communication in a Parallel Distributed Expert System Shell W Lejouad:INRIA/CERMICS, France SESSION 5 Experiments in the use of Neighbourhood Search Techniques for Vehicle Routing T Duncan:AIAI, University of Edinburgh, Scotland Ticker:A Qualitative Model of the Electrical System of the Heart J Hunter, I Kirby:University of Aberdeen, Scotland Knowledge Level Planning in the Search and Rescue Domain H Cottam,N Shadbolt:University of Nottingham,England;J Kingston,H Beck,A Tate:AIAI,University of Edinburgh, Scotland Qualitative Probabilities for Ordering Diagnostic Reasoning in Causal Graphs P Fuster Parra:University of Balearic Islands, Spain; A Ligeza : Institute of Automatics AGH, Poland A Hybrid Rule-Based System with Rule-Refinement Mechanisms R Poli, M Brayshaw, A Sloman:University of Birmingham, England APPLICATION STREAM TUESDAY 12 DECEMBER 1995 BEST APPLICATION PAPER TIGER:Knowledge Based Gas Turbine Condition Monitoring R Milne, C Nicol:Intelligent Applications Ltd; R Fisher:Exxon Chemicals, Scotland; L Trave-Massuyes:CNRS/LAAS, France; J Quevedo:Polytechnic University of Catalonia, Spain A condition monitoring system in continuous use at Exxon for over two years. SESSION 1: BUSINESS INFORMATION MANAGEMENT A Knowledge-Based System for Contract Staff Time-Recording M Moulton:University of Portsmouth, England An operational system for a major UK manufacturing site. A Knowledge Based Support System for Competitive Bidding S Gallagher, J Trainor:Short Brothers plc; M Murphy, E Curran: University of Ulster, N Ireland System has captured the company's key business rationale forbid/no-bid decisions. KBST:A Support Tool for Business Modelling in BSMD Y-H Chen-Burger, D Robertson:University of Edinburgh; J Fraser: AIAI, University of Edinburgh; C Lissoni:International Business Machines Corporations UK Ltd, Scotland Uses case-based reasoning techniques to build business models. DRS Assistant:Intelligent Advice for Operating and Maintaining a World-Wide Information System S Greenwood:Oxford Brookes University;M Davis:Reuters Ltd,England A multi-media expert system. SESSION 2: DECISION SUPPORT An Agent Based Helicopter Decision Support System R Zanconato:Cambridge Consultants Ltd; H Howells:DRA Farnborough, England A real-time KBS involving 24 separate agents running concurrently on 10 processors. Prediction without Modelling:A Demonstration of the Use of Case-Based Reasoning for the Prediction of Process Behaviour S Rougegrez:LAFORIA-IBP, Universite Paris 6, France Applying case-based reasoning to forest fires An Expert System for Strategic Oil Storage J Hartman:Israel Institute for Biological Research, Israel Integrates knowledge of a number of experts in different fields of fuel quality. Detection of Oceanographic Fronts:A Knowledge Based Approach N Rees, J Aiken:Plymouth Marine Laboratory, England Overcomes limitations of signal detection algorithms by incorporating knowledge from oceanographers. An Integrated Approach to the Route Autofinder Problem K P Lam, K K Yiu, H C Leung:Chinese University of Hong Kong Multimedia approach to finding optimal routes in a city street map. SESSION 3: MANUFACTURING Improving Cake Product Quality R Petryszak, L Young, S Cauvain:CCFRA, England A KBS to solve faults in production of cakes and sponges Adding Multimedia Interfaces to Simplify the World of Circuit Board Assembly Line Production F McCaffery, M McTear:University of Ulster, N Ireland The user can respond by either using the keyboard or speaking into a microphone. A Feasibility Study into the Use of a Real-Time Emergency Advisory System for Batch Reactors K Y Mau, P F Nolan, C H Steele:South Bank University, England Uses an expert system shell, a knowledge base derived from case histories and hazop and fault-tree analysis. A Hypermedia/Knowledge Based System to Promote Energy Efficiency in UK Companies J L Gordon, M Edge, T Fort, M Holden:Blackburn College, England A KBS to give companies advice on energy management. WEDNESDAY 13 DECEMBER SESSION 4: FINANCE AND MEDICAL Tackling Cognitive Biases in the Detection of Top Management Fraud with the Use of Case-Based Reasoning O Curet:Touche Ross & City University Business School; M Jackson:London Business School, England An expert system to assist accountants. Using a Genetic Algorithm to Data Mine in the Financial Services Sector V J Rayward-Smith, J C W Debuse, B de la Iglesia:University of East Anglia, England A technical approach is described using commercial company data. A Comparative Study of Three Machine Learning Approaches to the Treatment of Patients at Anticoagulant Out-Patient Clinics P B Musgrove, J Davies:University of Wolverhampton, England Results show case-based reasoning as the most appropriate technique for applications of this type. An Expert System for Selection of Artificial Pacemakers and Lessons Learned from Development V P Lane:AFBIS, South Bank Business School; N Moghaddam : Kingston College, England An operational system used in the clinical environment for on-line consultation. SESSION 5: ENGINEERING Practical Applications of Multiple Models - The Need for Simplicity and Reusability D Pugh, C Price, N Snooke:University of Wales Experience gained from transferring a system to Ford and Jaguar Incorporation of a Process Model into a Generative Design Product Model C B Chapman:University of Warwick, England Using this method, 3 man months of design time can be reduced to 2 days. CSELECT:Seal Selection Without the Aid of Acronyms! J P Carr, D A Hughes:John Crane UK Ltd, England To be used as a key selection tool by 1000 sales persons and sales engineers. A New Graphical Representation for Rule Definition and Explanation in an Expert System J M Evans:Data Sciences UK Ltd, England; M J Fear:BP Exploration; N C Meany:Hughes Christensen Company, Scotland Expert system to give advice on drill bit selection for the oil industry. NIRMANI:A Case-Based Expert System for Integrated Design and Estimating I Watson:University of Salford, England; S Perera:University of Moratuwa, Sri Lanka Produces a conceptual design and first cost plan for warehouse buildings. ISIP PROJECT PRESENTATIONS IMIS - Intelligent Marketing Integrated System Project Partners: Henley Centre for Forecasting, Manchester Metropolitan University, United Distillers, TSB CHRONOS Project Partners: ICL, Lloyds Register, IC-PARC (Imperial College), UMIST IA - Intelligent Architecture Project Partners: Richard Rogers Partnership, Bovis Construction, Smallworld Systems, PowerGen, DEGW London, Broadgate Properties, Criterion Software, Qualum, Avanti Architects, Department of Computer Science UCL, Bartlett School of Architecture and Planning UCL. STAR - Standardised Argument Report Project Partners: Imperial Cancer Research Fund, City University, LHASA UK, Logic Programming Associates ADEPT, ENTERPRISE, MOBIT and CAKE Summarised by DTI/ISIP Representative 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. ES95 CONFERENCE COMMITTEE Dr Rob Milne, Intelligent Applications Ltd (Conference Chairman) Dr Ian Watson,University of Salford (Deputy Conference Chairman/Tutorial Co-ordinator) Professor Max Bramer, University of Portsmouth (Technical Programme Chairman) Dr John Nealon,Oxford Brookes University (Deputy Technical Programme Chairman) Ann Macintosh,AIAI, University of Edinburgh (Application Programme Chairman) Mr Chris Cooper,Coopers & Lybrand (Deputy Application Programme Chairman) Dr Alan Montgomery,Integral Solutions Ltd (ExhibitionCo-ordinator) FURTHER INFORMATION AND ENQUIRIES ES95 is organised by The Conference Team on behalf of the BCS Specialist Group on Expert Systems. Enquiries should be addressed to Mrs Kit Stones, The Conference Team 17 Spring Road, Kempston, Bedford MK42 8LS Telephone/Fax:(01234) 343384 International Dialling:+ 44 (1234) 343384 E.mail:kstonestct@cix.compulink.co.uk >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Thu, 16 Nov 1995 10:56:42 +0100 From: Matthias Klusch Subject: CIA-97 CFP FIRST ANNOUNCEMENT and CALL FOR PAPERS ***************************************************************************** 1. International Workshop CIA-97 COOPERATIVE INFORMATION AGENTS - DAI meets Database Systems 26th (Wed) - 28th (Fri) of February 1997 University of Kiel, Computer Science Department, Kiel, Germany ***************************************************************************** The workshop will be held in cooperation with the research group FG 1.1.6 on Distributed Artificial Intelligence (DAI) of the German Society for Computer Science (GI). DESCRIPTION: This workshop will focus on issues concerning approaches for an integrated use of methodologies from both research areas, DAI and Database Systems, especially for the development of cooperative information agents. The idea of a partial synthesis of both, the DAI as well as the Database research area seems to be very promising. One attempt to capture possible benefits from such a synthesis has lead to the introduction of the paradigm of Cooperative Information Systems (CIS) in 1992. In our context a CIS is constituted by a set of intelligent agents where each of them is uniquely attached to one database system. Such information agents behave like active, intelligent database front-ends trying to satisfy their own application-specific task goals alone or in cooperation with others. In particular the necessity to respect the database autonomy requirements hinders such cooperation e.g. for information gathering. The design of information agents inherently requires knowledge from several different research areas like DAI, Database and Expert Systems, and AI. Unfortunately, practical and theoretical work which is relevant for the development of information agents tends to be scattered across several different forums of respective computing subareas: There is an obvious need for a survey of these works, their advantages and limitations. Thus, the workshop aims for being a small but intensive forum for a presentation and exchange of ideas, work in progress, reviews as well as an engaged discussion between all attendees. TOPICS of interest include, but are not limited to: o architecture of information agents o autonomy requirements and their impacts for the development of information agents and systems o decentralized construction and management of common ontologies for cooperative information agents o knowledge discovery and data mining for information evolution in large database networks o use of object-oriented modelling within the design of information agents o methods for coalition formation among autonomous agents o approaches towards a theory of organization in multi-agent systems o adaptation and self-organization of information agents o planning in cooperative search for information o user interface issues for information agents o evaluation and development environments for information agents CONTRIBUTIONS: Authors are invited to submit papers describing both theoretical and practical work dealing with the use of methods from distributed artificial intelligence for cooperation between a set of heterogeneous, autonomous databases. Papers describing ongoing research are in particular welcome. Topics of interest include, but are not limited to the ones listed above. The paper must be in A4 size (basic font 12 point). Each submission must have a separate title page and a body. The title page must include a title, a 300-400 word abstract, a list of keywords, the names and addresses of all authors, their email addresses, and their telephone and fax numbers. The body must also include the title and abstract, but the author information must be excluded. The length of submitted papers (excluding the title page) must be no more than 12 single-spaced, single-column pages including all figures, tables, and bibliography. All papers must be written in English. and neither accepted nor under review by other conferences or journals. Papers not conforming to the above requirements may be rejected without review. Papers can be submitted both by mail and electronic mail. Electronic submission must be in postscript format. Send three hard-copies or the postscript file of your contribution to Matthias Klusch Institut f"ur Informatik und Praktische Mathematik Christian-Albrechts-Universit"at zu Kiel, Olshausenstr. 40, 24118 Kiel EMail: mkl@informatik.uni-kiel.d400.de In order to inform us about your submission send an email to: {pk,mkl}@informatik.uni-kiel.d400.de All accepted papers will be published in the proceedings of the workshop. IMPORTANT DATES: --------------- Paper Submission Deadline : 3.11.1996 Notification to the Authors : 15.12.1996 Camera Ready Due : 20.1.1997 PARTICIPATION: The number of participants will be restricted to atmost 80 peoples. Preference is given to people with accepted contributions. Early registration is recommended. For registration please send your name, full address (incl. phone/fax), affiliation, and a short description about your current research interests to the Organization Committee (see below). Let us also know if you intend to submit a paper. DATE AND LOCATION: The workshop starts on Wednesday, 26.2.1997, at 8 am and ends on Friday, 28.2.1997, about 1 pm. It takes place at the University of Kiel. (Address: CAU Kiel, Institut f"ur Informatik, Olshausenstr. 40, 24118 Kiel, Germany) Nearest international airport is located in Hamburg. The city of Kiel is easily reachable by train from Hamburg in about one hour. A direct connection from the Hamburg airport to Kiel and back is provided by an airport express bus (named 'Kielius'). There are also some national flights to Kiel airport available. PROGRAM COMMITTEE: Sonia Bergamaschi (Universita' di Modena, Italy) Hans-Dieter Burkhard (Humboldt University Berlin, Germany) Misbah Deen (University of Keele, England) Tim Finin (University of Maryland, USA) Joachim Hammer (Stanford University, USA) Peter Kandzia (University of Kiel, Germany) Larry Kerschberg (George Mason University, USA) Stefan Kirn (University of M"unster, Germany) Matthias Klusch (University of Kiel, Germany) Sarit Kraus (Bar Ilan University, Israel) Aris Ouksel (University of Illinois, USA) Mike P. Papazoglou (QUT Brisbane, Australia) Jeffrey Rosenschein (Hebrew University, Israel) Onn Shehory (Bar Ilan University, Israel) Antonio Si (Polytechnic University, Hong Kong) General Chairs and Organization Committee: Matthias Klusch (University of Kiel, Germany) Peter Kandzia (University of Kiel, Germany) ------------------------------------------------------------------------------- UP-TO-DATE-INFORMATION about the workshop will be given on the WorldWideWeb WWW: http://www.informatik.uni-kiel.de/~mkl/cia97.html For further information about the workshop please contact:\\ Matthias Klusch Institut f"ur Informatik Christian-Albrechts-Universit"at zu Kiel, Olshausenstr. 40, 24118 Kiel PHONE : +49-431-880-4474 Fax : +49-431-880-4054 EMail : mkl@informatik.uni-kiel.d400.de WWW : http://www.informatik.uni-kiel.de/~mkl/ >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~