KDD Nuggets 95:23, e-mailed 95-09-22 Contents: * GPS, Oct 95 BYTE "STATE of the ART" section on Data Mining * P. Turney, Proceedings of IJCAI-95 wrkshop on Data Engineering for Inductive Learning, http://ai.iit.nrc.ca/DEIL/ * B. Prior, HPCwire: Price Waterhouse Releases Data Mining Software * D. Conklin, Ph.D. abstract: KD in Molecular Structure Databases Job Ad: * C. Bergman, Positions in IBM Data Mining Group * J. Gama, STATLOG project pointer for Netscape http://www.up.pt/liacc/ML/statlog/index.html * N. Mameded, FINAL PROGRAM: EPIA'95, Madeira, Portugal, Oct 3-6 * Z. Ras, CFP: ISMIS'96 reminder, papers due Oct 15, 1995 http://www.ipipan.waw.pl/konferencje/ismis96/ The KDD Nuggets is a moderated mailing list for information relevant to Data Mining and Knowledge Discovery in Databases (KDD). Please include a DESCRIPTIVE subject line and a URL, when available, in your submission. Nuggets frequency is approximately weekly. Back issues of Nuggets, a catalog of S*i*ftware (data mining tools), references, FAQ, and other KDD-related information are available at Knowledge Discovery Mine, URL http://info.gte.com/~kdd by anonymous ftp to ftp.gte.com, cd /pub/kdd, get README E-mail add/delete requests to kdd-request@gte.com E-mail contributions to kdd@gte.com -- 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 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ "You can know a small truth because its opposite is a falsehood, you can know a great truth because its opposite is also true." -- Niels Bohr (thanks to Brij Masand, brij@gte.com) Without realistic plans, data warehousing can turn into a money sinkhole and a legacy boat anchor. Patricia Seybold, ComputerWorld, Sep 11, 1995. >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Thu, 21 Sep 1995 14:42:23 -0400 From: gps@gte.com (Gregory Piatetsky-Shapiro) Subject: Oct 95 BYTE "STATE of the ART" section on Data Mining The October 95 BYTE magazine has a whole section (3 articles) on the state of the art in Data Mining. The first article, "The Data Gold Rush", by Sarah Hedberg, very nicely shows the wide variety of applications of data mining, highlighting A.C Nielsen Spotlight system for retail data analysis, GTE KEFIR for health care data, and JPL's SKICAT system for cataloguing the stars. I was among the people interviewed for the article which also points to KD Mine website at http://info.gte.com/~kdd/, KDD-95 proceedings, and forthcoming Advances in KDDM book as additional resources. The second article, "A Data Miner's Tools", by Karen Watterson, examines three categories of software for data mining: query and reporting tools, multi-dimensional database systems (OLAP), and intelligent agents. It gives a good review of OLAP tools, but omits major KD/DM tools for classification, rule discovery, clustering, dependency inference, etc. I suspect this writer talked only to OLAP people who think that OLAP is all there is in Data Mining. The third article, "Data Mining Dynamite", by Cheryl Krivda, shows how to facilitate the data mining process. She examines the issues of data cleaning, building data warehouses, and utilizing parallel hardware. This article claims that some data-mining pioneers enjoy 1000 percent return on investment. In all, a very informative section which mention some of the published successes of KD/DM and raises expectations for more. It is now up to this community to deliver. -- Gregory Piatetsky-Shapiro [on a soapbox] >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Wed, 20 Sep 1995 13:55:05 +0500 From: peter@ai.iit.nrc.ca (Peter Turney) Subject: Workshop on Data Engineering for Inductive Learning On August 20, 1995, there was a workshop at IJCAI-95 on the topic of Data Engineering for Inductive Learning (DEIL). Some of the problems discussed in the DEIL workshop overlap with the concerns of the KDD community. The papers presented at the workshop are now available on the web as compressed PostScript files: http://ai.iit.nrc.ca/DEIL/ The web site includes abstracts in HTML, papers in PostScript, the original CFP for the workshop, and pointers to related material. --------------------------------------------------------------------------- ___ __ _____ ____ | /_ /\ /_/| /____/ \ /___ /| | Peter D. Turney (peter@ai.iit.nrc.ca) | |\ \ | || | __ \ /| / ___|/ | Institute for Information Technology | ||\ \| || | |__) |/ | | |__ | National Research Council Canada | || \ || | __ /\ | |/__ /| | Ottawa, Ontario, Canada, K1A 0R6 |_|/ \__|/ |_|/ \_\/ \____|/ | (613) 993-8564 FAX: 952-7151 >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Fri, 08 Sep 95 13:51:11 From: prior@MIT.EDU (Bob Prior - MIT Press) Subject: 5876 PRICE WATERHOUSE RELEASES REVVED UP DATAMINING SOFTWARE HPCwire PRICE WATERHOUSE RELEASES REVVED UP DATAMINING SOFTWARE HPCwire COMMERCIAL NEWS Sept. 8, 1995 ========================================================================= New York, NY -- Price Waterhouse LLP has released Version 3.2 of its Geneva V/T software which mines multi-hundred gigabyte databases on mainframe computers while they are being updated by OLTP processes. Geneva V/T exploits the high data bandwidth, parallel processing and shared memory/disk architecture of the S/390 platform and MVS operating system, Price Waterhouse noted in press release. Geneva V/T operates on bipolar and CMOS versions of the S/390 platform as well as on single, CEC, basic sysplex and parallel sysplex configurations. "Most mainframe software has been focused on high-end on-line transaction processing (OLTP); virtually no attention has been given to data scanning applications, especially those that need simultaneous access to files being updated by mission critical OLTP processes," said Richard Roth, partner-in-charge of the Price Waterhouse LLP Geneva Systems Group. "The absence of a software engine that focuses the multitasking power and enormous data bandwidth of the mainframe on scanning applications that also have minimal impact on OLTP has forced data warehouse implementors to seek alternative hardware architectures that feature cheap MIPS and duplicate copies of operational databases. But with Geneva V/T, data warehouse architects can achieve a 4- to 50-fold increase in relative MVS efficiency and directly process DB2 or VSAM OLTP files in place where necessary. When combined with the continuing decline in the cost of S/390 MIPS, this 'hyper-efficiency' turns basic cost/performance calculations dramatically in favor of the MVS platform. For companies who need access to large databases that already exist on MVS mainframes, this is very good news." Geneva V/T can be used as an engine for extracting, cleansing and reformatting data from operational systems to feed lightly and heavily summarized data warehouses on client/server platforms, a Price Waterhouse spokesperson explained. It also feeds specialized data mining processes from multiple sources. Long-running or resource-intensive batch processes can be 'encapsulated' to reduce wall or CPU times. And, in combination with MVS/BatchPipes, Geneva V/T can create parallelism in the very common and otherwise serial extract, sequence, summarize and report processes.  ***************************************************************************** H P C w i r e S P O N S O R S Product specifications and company information in this section are available to both subscribers and non-subscribers. 912) Avalon Computer 915) Genias Software 905) MAXIMUM STRATEGY 934) Convex Computer Corp. 930) HNSX Supercomputers 916) MasPar Computer 921) Cray Research Inc. 902) IBM Corp. 932) Portland Group 909) Fujitsu America 904) Intel Corp. 935) Silicon Graphics ***************************************************************************** Copyright 1995 HPCwire. To receive the weekly HPCwire at no charge, send e-mail without text to "trial@hpcwire.tgc.com". >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Tue, 12 Sep 1995 10:27:29 -0700 From: (Christy D. Bergman) To: kdd@gte.com Subject: Positions in IBM Data Mining Group DATA MINING POSITIONS AT IBM Join the team! We are an entrepreneurial organization within IBM developing data mining solutions. We have three groups, a consulting services group, research & development group, and software application development group. We are looking for qualified individuals for all three areas: - ANALYSTS Analysts will be responsible for performing consulting engagements in any of the following areas: finance, insurance, retail, telecommunications, media, and healthcare. Familiarity with databases, statistics, data preparation, and high-end data mining techniques and tools required. Applicants must have advanced degrees in CS, Statistics, or Mathematics, or equivalent, good communication skills, willingness to travel, and be application oriented. These positions provide excellent customer contact with high level executives in FORTUNE 500 companies. - APPLICATION DEVELOPERS Application Developers will be responsible for developing data mining applications and solutions for any of the following industries: finance, insurance, retail, telecommunications, media, and healthcare. Strong C/C++, UNIX, Windows, high end graphics and GUI development (MOTIF, Windows), database, and object oriented design skills required. These positions provide opportunity to learn the latest data mining technology as well as interface with world class scientists to address challenging problems. - RESEARCH AND DEVELOPMENT Research Scientists will be responsible for conducting research in the areas of data mining, inductive learning (classfication and clustering), neural networks, visualization and databases. Qualified individuals should have a Ph.D. degree in CS, EE, Statistics, Mathematics, or equivalent, demonstrated initiative and research experience in the above areas, a strong publication record, and a desire to work with others on real problems. Our world class research labs are located at both coasts. Almaden Research Center in San Jose, CA is located in beautifully situated rolling hills in Silicon Valley close to top universities such as Stanford University and UC Berkeley. T.J. Watson Research Center, in Yorktown Heights, NY is located in the wooded Hudson River Valley far enough away from New York City to be rural yet close enough to visit easily and is also close to top universities such as Columbia University and New York University. For further information, please send your resume, indicate the position you are applying for and list of references. If applying for the research positions, please also send a list of publications to Christy Bergman PHP/802 IBM Almaden Research Center 650 Harry Road, San Jose, CA 95120 cbergman@almaden.ibm.com 408-927-3012 (FAX) >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Fri, 15 Sep 1995 16:43:24 +0200 From: Joao Gama Subject: Statlog Mr. Gregory: About the link to "ftp://ftp.ncc.up.pt/pub/statlog/" there some problem on our ftp server when talking with Netscape. We try to solve it as soon as possible. But, it works when accessing by ftp. There are another source of information about StatLog datasets: "http://www.up.pt/liacc/ML/statlog/index.html" I hope that it works at all. Joao Gama [ STATLOG (an Esprit project) did excellent comparative studies of different machine learning, neural and statistical classification algorithms. About 20 different algorithms were evaluated on more than 20 different datasets. The results were published in several papers and in a book "Machine Learning, Neural, and Statistical Classifcation, ed. Michie, Spiegelhalter, and Taylor, Ellis Horwood, 1994, GPS] >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Date: Sun, 17 Sep 1995 16:47:42 -0700 (PDT) From: Darrell Conklin Subject: kdd digest submission PhD dissertation announcement Knowledge Discovery in Molecular Structure Databases ____________________________________________________ by Darrell Conklin ABSTRACT In recent years there has been an explosion of information generated on molecular structures. This information is usually three-dimensional in nature, and is normally appended to the existing molecular database in the form of raw coordinate data. There is a recognized need for new tools to structure, manage, and analyze these data. This thesis presents a knowledge discovery technique, based on a theory of conceptual clustering, in which recurrent associations between molecular constitution and conformation can be discovered in three-dimensional molecular structure databases. These associations are defined in first-order logic as structured concepts, and are maintained in a taxonomy partially ordered by subsumption. The knowledge discovery method is applied to two large molecular structure databases. In the Cambridge Structural Database the technique is used to perform conformational clustering of several small molecule datasets. The resultant conformational templates are evaluated by comparison with hand analyses and statistical clusterings of the same data. In the Protein Data Bank the technique is used to discover recurrent protein motifs which have sequences predictive of their associated structure. The resultant rules are evaluated with respect to the average structural variation of their instances, and according to a test of statistical correlation between sequence and structure. In both molecular structure databases interesting and significant associations were discovered. Darrell Conklin conklin@zgi.com ZymoGenetics Inc. Tel: (206) 442-6664 1201 Eastlake Avenue East Fax: (206) 442-6608 Seattle WA, 98102 >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ From: Nuno Joao Mamede Subject: FINAL PROGRAM: EPIA'95 Date: Sun, 17 Sep 95 20:25:19 +0100 EPIA'95 - PRELIMINARY PROGRAM SEVENTH PORTUGUESE CONFERENCE ON ARTIFICIAL INTELLIGENCE Casino Park Hotel, Funchal, Madeira Island, Portugal 3-6 October, 1995 (Under the auspices of the Portuguese Association for AI) The 7th Portuguese Conference on Artificial Intelligence will be held at Funchal, Madeira Island, Portugal, October 3-6, 1995. As in the past, EPIA 95 is an international conference with English as the official language. The conference covers all areas of Artificial Intelligence, including theoretical areas, foundational areas, and applications. The scientific program consists of invited lectures, tutorials, demonstrations and paper presentations. There will also be parallel workshops on Expert Systems, Fuzzy Logic and Neural Networks, and Applications of AI to Robotics and Vision Systems. ====================================================================== FINAL PROGRAM (Summary) ====================================================================== Tuesday - October, 3 95 ~~~~~~~~~~~~~~~~~~~~~~~ 9:00 - 12:30 TUTORIAL 1 - Artificial Life and Autonomous Robots Luc Steels 9:00 - 12:30 TUTORIAL 3 - Introduction to Artificial Intelligence Ernesto Costa (in Portuguese) 14:30 - 18:00 TUTORIAL 2 - Virtual Reality - The AI perspective David Hogg 14:30 - 18:00 TUTORIAL 4 - Design of Expert Systems Ernesto Morgado (in Portuguese) Wednsday - October, 4 95 ~~~~~~~~~~~~~~~~~~~~~~~~ 9:00 - 9:30 OPENING SESSION 9:40 - 10:30 QUALITATIVE REASONING 10:30 - 10:50 Coffee break 10:50 - 12:30 NEURAL NETWORKS & DISTRIBUTED ARTIFICIAL INTELLIGENCE 10:50 - 12:30 FUZZY LOGIC & NEURAL NETWORKS WORKSHOP 12:30 - 14:00 Lunch 14:00 - 15:30 Invited Lecture by LUIS B. ALMEIDA (IST - Portugal) "The Connectionist Paradigm and AI" 15:30 - 15:50 Coffee break 15:50 - 18:00 BELIEF REVISION & NON-MONOTONIC REASONING 15:50 - 18:30 FUZZY LOGIC & NEURAL NETWORKS WORKSHOP 15:50 - 18:30 APPLICATIONS OF EXPERT SYSTEMS WORKSHOP 20:00 - Welcome Dinner (With a performance of the Univ. of Madeira "tuna") Thursday - October, 5 95 ~~~~~~~~~~~~~~~~~~~~~~~~ 9:00 - 10:30 Invited Lecture by RODNEY BROOKS (MIT - USA) "The Evolutionist Approach - Past, Present and Future of AI" 10:30 - 10:50 Coffee break 10:50 - 12:30 APPLICATIONS OF EXPERT SYSTEMS WORKSHOP 10:50 - 11:40 ROBOTICS AND CONTROL 11:40 - 12:30 POSTER SECTION 12:30 - 14:00 Lunch 14:00 - 15:15 MACHINE LEARNING 15:15 - 15:35 Coffee break 15:35 - 17:05 Invited Lecture by MARVIN MINSKY (MIT - USA) "Why Human Brains Can't Really Think" 17:15 - 18:30 Visit to the Madeira Wine Cellars Friday - October, 6 95 ~~~~~~~~~~~~~~~~~~~~~~ 9:00 - 10:30 INVITED LECTURE by Manuela Veloso (CMU - USA) "Planning and Learning in Intelligent Agents" 10:30 - 10:50 Coffee break 10:50 - 12:30 STREAM 1: PLANNING AND CASE-BASED REASONING 10:50 - 12:30 STREAM 2: CONSTRAINT-BASED REASONING 10:50 - 12:30 APPLICATIONS OF AI TO ROBOTICS AND VISION SYSTEMS WORKSHOP 12:30 - 14:00 Lunch 14:00 - 15:30 STREAM 1: AUTOMATED REASONING AND THEOREM PROVING 14:00 - 15:30 STREAM 2: GENETIC ALGORITHMS & THEORY OF COMPUTATION 14:00 - 15:30 APPLICATIONS OF AI TO ROBOTICS AND VISION SYSTEMS WORKSHOP 15:30 - 15:50 Coffee break 15:50 - 17:30 PANNEL (The Next Frontiers of AI: the Role of Foundations) 18:00 - 19:00 APPIA meeting 20:00 Farewell Dinner (with folklore dances show) Saturday - October, 7 95 ~~~~~~~~~~~~~~~~~~~~~~~~ TOUR 1 - Island Tour (full day) TOUR 2 - Ribeiro Frio/Portela Walking Tour (full day) TOUR 3 - Eira do Serrado (half day) ====================================================================== PAPERS TO BE PRESENTED IN EACH SESSION ====================================================================== AUTOMATED REASONING AND THEOREM PROVING ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Terminological Meta-Reasoning by Reification and Multiple Contexts Klemens Schnattinger, Udo Hahn, Manfred Klenner CLIF, Freiburg University, Germany A New Continuous Propositional Logic Riccardo Poli, Mark Ryan, Aaron Sloman SCS, The University of Birmingham, UK Super-Polynomial Speed-Ups in Proof Length by New Tautologies Uwe Egly FG Intellektik, TH Darmstadt, Germany BELIEF REVISION ~~~~~~~~~~~~~~~ Belief Revision in Non-Monotonic Reasoning Jose Alferes, Luis Moniz Pereira, T. Przymusinski DM, U. Evora, and CRIA, U. Nova de Lisboa, Portugal, and University of California at Riverside, USA A New Representation of JTMS Truong Quoc Dung IRIDIA, Universite Libre de Bruxelles, Belgium CONSTRAINT-BASED REASONING ~~~~~~~~~~~~~~~~~~~~~~~~~~ The Retrieval Problem in a Concept Language with Number Restrictions Aida Vitoria, Margarida Mamede, Luis Monteiro DI, Universidade Nova de Lisboa, Portugal Formalizing Local Propagation in Constraint Maintenance Systems Gilles Trombettoni INRIA-CERMICS, France A Dependency Parser of Korean Based on Connectionist/Symbolic Techniques Jong-Hyeok Lee, Geunbae Lee Pohang University of Science and Technology, Korea A Symbiotic Approach to Arc and Path Consistency Checking Pierre Berlandier INRIA-CERMICS, France DISTRIBUTED ARTIFICIAL INTELLIGENCE ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Where Do Intentions Come From?: A Framework for Goals and Intentions Adoption, Derivation and Evolution Graca Gaspar, Helder Coelho Faculdade de Ciencias de Lisboa, and INESC, Portugal A Closer Look to Artificial Learning Environments Helder Coelho, Augusto Eusebio, Ernesto Costa INESC, Portugal, and DEI, Universidade de Coimbra, Portugal Building Multi-Agent Societies from Descriptions to Systems: Inter-Layer Translations Helder Coelho, Luis Antunes, Luis Moniz INESC, Portugal GENETIC ALGORITHMS ~~~~~~~~~~~~~~~~~~ GA/TS: A Hybrid Approach for Job Shop Scheduling in a Production System Jose Ramon Zubizarreta, Javier Arrieta Facultad de Informatica de San Sebastian, Spain MACHINE LEARNING ~~~~~~~~~~~~~~~~ A Controlled Experiment: Evolution for Learning Difficult Image Classification Astro Teller, Manuela Veloso Carnegie Mellon University, USA Minimal Model Complexity Search Chris McConnell CMU School of Computer Science, USA Characterization of Classification Algorithms Joao Gama, Pavel Brazdil LIACC, Universidade do Porto, Portugal NEURAL NETWORKS ~~~~~~~~~~~~~~~ Neurons, Glia and the Borderline Between Subsymbolic and Symbolic Processing J. G. Wallace, K. Bluff Swinburne University of Technology, Australia NON-MONOTONIC REASONING ~~~~~~~~~~~~~~~~~~~~~~~ Arguments and Defeat in Argument-Based Nonmonotonic Reasoning Bart Verheij University of Limburg, The Netherlands A Preference Semantics for Ground Nonmonotonic Modal Logics Daniele Nardi, Riccardo Rosati DIS, Universita di Roma ``la Sapienza", Italy Logical Omniscience vs. Logical Ignorance On a Dilemma of Epistemic Logic Ho Ngoc Duc ILPS, University of Leipzig, Germany PLANNING AND CASE-BASED REASONING ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ On the Role of Splitting and Merging Past Cases for Generation of New Solutions Carlos Bento, Penousal Machado, Ernesto Costa DEI, Universidade de Coimbra, Portugal Theorem Proving by Analogy - A Compelling Example Erica Melis Department of AI, University of Edimburgh, Scotland Non-Atomic Actions in the Situation Calculus Jose Julio Alferes, Renwei Li, Luis Moniz Pereira CRIA and DCS, Universidade Nova de Lisboa, Portugal Planning under Uncertainty: A Qualitative Approach Nikos Karacapilidis FIT.KI, GMD, Sankt Augustin, Germany QUALITATIVE REASONING ~~~~~~~~~~~~~~~~~~~~~ Qualitative Reasoning under Uncertainty Daniel Pacholczyk DMI, U.F.R., Science d'Angers, France Systematic Construction of Qualitative Physics-Based Rules for Process Diagnostics Jaques Reifman, Thomas Y.C. Wei Argonne National Laboratory, USA ROBOTICS AND CONTROL ~~~~~~~~~~~~~~~~~~~~ Integrated Process Supervision (IPS): A Structured Approach to Expert Control Chai Quek, P.W. Ng, M. Pasquier Nanyang Technological University, Singapore Using Stochastic Grammars to Learn Robotic Tasks Pedro Lima, George Saridis ISR, Technical Univ. of Lisbon, Portugal, and Rensselaer Polytechnic Institute, USA THEORY OF COMPUTATION ~~~~~~~~~~~~~~~~~~~~~ Constraint Categorial Grammars Luis Damas, Nelma Moreira LIACC, Universidade do Porto, Portugal A New Translation Algorithm from Lambda Calculus into Combinatory Logic Sabine Broda, Luis Damas LIACC, Universidade do Porto, Portugal POSTER SECTION ~~~~~~~~~~~~~~ Interlocking Multi-Agent and Blackboard Architectures Bernhard Kipper DCS, University of Saarbrucken, Germany A Model Theory for Paraconsistent Logic Programming Carlos Viegas Damasio, Luis Moniz Pereira CRIA, and DCS, Universidade Nova de Lisboa, Portugal Promoting Software Reuse Through Explicit Knowledge Representation Carmen Fernandez-Chamizo, Pedro A. Gonzalez-Calero, Mercedes Gomez-Albarran Universidad Complutense, Spain Efficient Learning in Multi-Layered Perceptron Using the Grow-And-Learn Algorithm Gildas Cherruel, Bassel Solaiman, Yvon Autret Univ. de Bretagne Occidentale, and TNI, and ENSTB, France An Non-Diffident Combinatorial Optimization Algorithm Gilles Trombettoni, Bertrand Neveu INRIA-CERMICS, France Modelling Diagnosis Systems with Logic Programming Iara Mora, Jose Alferes CRIA, U. Nova de Lisboa, and DM, U. Evora, Portugal Agreement: A Logical Approach to Approximate Reasoning Luis Custodio, Carlos Pinto-Ferreira ISR, Technical University of Lisbon, Portugal Constructing Extensions by Resolving a System of Linear Equations Messaoudi Nadia Universite Aix-Marseille II, France Presenting Significant Information in Expert System Explanation Michael Wolverton Daresbury Rutherford Appleton Laboratory, UK A Cognitive Model of Problem Solving with Incomplete Information Nathalie Chaignaud LIPN, Universite Paris-Nord, France Filtering Software Specifications Written In Natural Language Nuria Castell, Angels Hernandez Universitat Politecnica de Catalunya, Spain Parsimonious Diagnosis in SNePS Pedro A. Matos, Joao P. Martins DEM, Technical University of Lisbon, Portugal Syntactic and Semantic Filtering in a Chart Parser Sayan Bhattacharyya, Steven L. Lytinen University of Michigan, and DePaul University, USA GA Approach to solving Multiple Vehicle Routing Problem Slavko Krajcar, Davor Skrlec, Branko Pribicevic, Snjezana Blagajac Faculty of Electrical Eng. and Computing, Croatia Multilevel Refinement Planning in an Interval-Based Temporal Logic Werner Stephan and Susanne Biundo German Research Center for AI, Germany APPLICATIONS OF EXPERT SYSTEMS WORKSHOP ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Wednesday, 4 15:50 - 16:15 CGD - An Expert System for Loan Analysis Decision Vasco Moreira, Andre Frazao, Elisabete Silva, Ernesto Costa Caixa Geral de Depositos, Dir. Organizacao Informatica Lisboa, Portugal 16:15 - 16:40 A Quantitative Method for Performing A Cost-Benefit Analysis of Expert System Projects Ramu Kannan, Reza Khorramshahgol, Mohan Tanniru Dept. of Management Science and Economics, Coppin State College, Baltimore, USA 16:40 - 17:05 DARE: a Knowledge-Based System for the Diagnosis of Neuromuscular Disorders J. Cruz, P. Barahona, A. P. Figueiredo, M. Veloso, M. Carvalho UNINOVA, Portugal 17:05 - 17:30 A Cooperative Multi-Agent System for Strategic Decision Making Suzanne Pinson Jorge Louca Universite Paris IX - Dauphine, Paris, France 17:30 - 17:55 A Hybrid Model for Classification Expert Systems Sergio Rosa, Beatriz Leao Instituto de Informatica UFRGS, Porto Alegre, Brasil Thursday, 5 10:50 - 11:15 PERMEX - Expert System for Corrosion Failure Analysis Fernando Lopes, A. Novais, N. Mamede, C. Rangel INETI, DMS, Lisboa, Portugal 11:15 - 11:40 Architectural Aspects of an Intelligent DSS for Flow Shop Production Control Ioannis Hatzilygeroudis, D. Sofotassios, N. Dendris, P. Spirakis, A. Tsakalidis Dept. of Computer Engin. and Informatics, Univ. of Patras, Greece 11:40 - 12:05 Advances in Explanation Facilities for Expert Systems Keith Darlington School of Computing, Information Systems and Mathematics South Bank University, London, UK 12:05 - 12:30 A Deferred Communication in a Parallel Distributed Expert System Shell Wided Lejouad SECOIA Project, Sophia Antipolis, France APPLICATIONS OF AI TO ROBOTICS AND VISION SYSTEMS WORKSHOP ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Friday, 6 10:50 - 11:15 Designing and Implementing Real Walking Agents Using Virtual Environments Aleix Martinez Universitat Autonoma de Barcelona, Dept. Informatica, Spain 11:15 - 11:40 Multi-Layer Perceptrons for Task Visual Servoing in Robotics Nadine Rondel, Gilles Burel Thomson CSF-LER, France 11:40 - 12:05 Heuristic Autonomous Mobile Robot Using Visual Servoing Jean-Charles Bonin, Fernandoo De Carvalho Gomes Laboratorio de Inteligencia Artificial-LIA, Fortaleza, Brasil 12:05 - 12:30 An Integrated Approach to Position a Robot Arm in a System for Planar Part Grasping Pedro Sanz, Juan Domingo Universitat Jaume I, Dpto. Informatica, Castellon, Spain 14:00 - 14:25 Learning and Recall of Robot Manipulator Motions Using Driver Programs Frank Smieja, Uwe Bayer GMD, Schloss Birlinghoven, Germany 14:25 - 14:50 Selective Visual Perception Driven by Cues from Speech Processing Reinhard Moratz AG Angewandte Informatikj, Universitaet Bielefeld, Germany 14:50 - 15:15 Autonomous Robots and Active Vision Systems: Issues on Architectures an Integration Helder Araujo, Jorge Dias, Jorge Batista, Paulo Peixoto ISR-Coimbra, Universidade de Coimbra, Portugal 15:15 - 15:35 Learning from Perception, Success and Failure in a Team of Autonomous Mobile Robots Arvin Agah, George Bekey Inst. for Robotics and Intell.Syst., Univ. of Southern California, USA FUZZY LOGIC & NEURAL NETWORKS WORKSHOP IN ENGINEERING ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Wednesday, 4 - Session 1 10:50 - 11:15 A Fuzzy Logic Controller for Supraconductivity Measuring N. Zimic, J. Ficzko, M. Mraz, J. Virant Faculty of Electrical & Computer Engineering Science University of Ljubljana, Slovenia 11:15 - 11:40 Complex Data and Fuzziness in Database Applications Adnan Yazici Dept. of Computer Engineering, Middle East Technical University, Turkey 11:40 - 12:05 Car License Plate Recognition with Neural Networks and Fuzzy Logic J. Nijhuis, et.al. Dept. of Computer Science, Groningen University, The Netherlands 12:05 - 12:30 Similarity-Based Self-organized Clustering Jurgen Rahmel Center for Learning Systems & Applications, University of Kaiserslautern, Germany 15:50 - 16:15 On the Representation of Data for Optimal Learning M. Brugge, J. Nijhuis, W. Jansen, H. Drenth, L. Spaanenburg Dept. of Computer Science, Groningen University, The Netherlands 16:15 - 16:40 Artificial Neural Net-Based Controllers for Real Process Control Petr Pivonka, Jan Zizka Dept. of Automatic Control and Instrumentation Technical University of Brno, Czech Republic 16:40 - 17:05 A Production Line for Generating Clinical Decision Support Systems Patrik Eklund Dept. of Computing Science, Umea University, Sweden 17:05 - 17:30 Knowledge Discovery Using Hierarchical Connectionist Marie Pai, Robin Ying AT&T Bell Laboratories, USA 17:30 - 17:55 Growing Filters for Finite Impulse Response Networks M. Diepenhorst, J. Nijhuis, R. Venema, L. Spaanenburg Dept. of Computer Science, Groningen University, The Netherlands ====================================================================== ENQUIRIES ADDRESS ====================================================================== EPIA'95 - INESC E-mail: epia95@inesc.pt Av. Alves Redol, 9 Fax: 351-1-525843 1000 Lisboa Voice: 351-1-3100325 PORTUGAL Home Page: http://www.isr.ist.utl.pt/~cpf/epia95 ====================================================================== SUPPORTERS ====================================================================== Banco Nacional Ultramarino Governo Regional da Madeira Instituto Superior Tecnico SISCOG - Sistemas Cognitivos INESC CITMA IBM TAPair Portugal >~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ From: Zbigniew W Ras Date: Wed, 20 Sep 1995 09:48:22 -0400 Subject: ISMIS'96/reminder ---------- **** C A L L F O R P A P E R S **** NINTH INTERNATIONAL SYMPOSIUM ON METHODOLOGIES FOR INTELLIGENT SYSTEMS (ISMIS'96) Tatry Hotel, Zakopane, Poland June 10-13, 1996 SPONSORS UNC-Charlotte, Oak Ridge National Laboratory, Polish Academy of Sciences, Warsaw Univ. of Technology and others. PURPOSE OF THE SYMPOSIUM This Symposium is intended to attract individuals who are actively engaged both in theoretical and practical aspects of intelligent systems. The goal is to provide a platform for a useful exchange between theoreticians and practitioners, and to foster the cross-fertilization of ideas in the following areas: * Approximate Reasoning * Evolutionary Computation * Intelligent Information Systems * Knowledge Representation and Integration * Learning and Knowledge Discovery * Logic for Artificial Intelligence * Methodologies (modeling, design, validation, performance evaluation). In addition, we solicit papers dealing with Applications of Intelligent Systems in complex/novel domains, e.g. human genome, global change, manufacturing, health care, etc. INVITED SPEAKERS Michael Brodie (GTE Lab.) Matthias Jarke (RWTH Aachen, Germany) Gregory Piatetsky-Shapiro (GTE Lab.) Henri Prade (Univ. Paul Sabatier, France) Erik Sandewall (Linkoping U., Sweden) PAPER SUBMISSION Authors are invited to submit four copies of their manuscript (maximum 15 pages) to: Dr. Zbigniew W. Ras Univ. of North Carolina Dept. of Comp. Science Charlotte, N.C. 28223 e-mail: ras@mosaic.uncc.edu fax: 704-547-3516 Submissions should include a separate title page (1 copy) specifying the title, all authors with their affiliations, abstract (100-200 words), up to 10 keywords (begin the keyword list with at least one of the ISMIS areas listed above); and the preferred address of the contact author, including a telephone number, fax number, and e-mail address (if available). If possible, the title page should be submitted via email (in plain text) to to facilitate submissions processing. IMPORTANT DATES Submission of Papers: October 15, 1995 Acceptance Notification: December 15, 1995 Final Paper: February 15, 1996 * * * * * * * * * * * * * * * * * * * * * * WWW Home Page for ISMIS'96: http://www.ipipan.waw.pl/konferencje/ismis96/ * * * * * * * * * * * * * * * * * * * * * *