PKDD'97 -- 1st European Symposium on Principles of Data Mining and Knowledge Discovery Trondheim, Norway June 25-27, 1997 NB: NEW DEADLINE FOR PAPER SUBMISSIONS: February 17, 1997 Contents * Program committee * Introduction * Topics * Submission details o Important dates o Proceedings (Springer Verlag) * Program co-chairs Program Committee * Pieter Adriaans * Attilio Giordana * David Hand * Bob Henery * Mikhail Kiselev * Willi Kloesgen * Yves Kodratoff * Jan Komorowski, co-chair * Heikki Mannila * Marjorie Moulet * Steve Muggleton * Zdzislaw Pawlak * Gregory Piatetsky-Shapiro * Zbigniew Ras * Lorenza Saitta * Erik Sandewall * Wei-Min Shen * Arno Siebes * Andrzej Skowron * Derek Sleeman * Shusaku Tsumoto * Raul Valdes-Perez * Rudiger Wirth * Stefan Wrobel * Wojtek Ziarko * Jan Zytkow, co-chair Introduction Data Mining and Knowledge Discovery (KDD) have recently emerged from a combination of many research areas: databases, statistics, machine learning, automated scientific discovery, inductive programming, artificial intelligence, visualization, decision science, and high performance computing. While each of these areas can contribute in specific ways, KDD focuses on the value that is added by creative combination of the contributing areas. The goal of PKDD'97 is to provide a European-based forum for interaction among all theoreticians and practitioners interested in data mining. Fostering an interdisciplinary collaboration is one desired outcome, but the main long-term focus is on theoretical principles for the emerging discipline of KDD, especially those new principles that go beyond each of the contributing areas. To promote these goals, PKDD'97 will be organized into tracks around the key areas contributing to KDD. For each area an ideal paper should focus on how its methods advance KDD's goals and principles. Both theoretical and applied submissions are sought. Reviewers will assess the contribution towards the main goals of PKDD'97, in addition to the usual requirements of novelty, clarity and significance. Applied papers should go beyond an individual application, presenting an explicit method that promises a degree of generality within some stage of the discovery process, such as preprocessing, mining, visualization, use of prior knowledge, knowledge refinement, and evaluation. Theoretical papers should demonstrate how they advance the process of data mining and knowledge discovery. Topics The following non-exclusive list exemplifies topics of interest: * Data and knowledge representation for data mining o Beyond relational databases: new forms of data organization o Data reduction o Prior domain knowledge and use of discovered knowledge o Combining query systems with discovery capabilities * Statistics and probability in data mining o Discovery of probabilistic networks o Modeling data and knowledge uncertainty o Discovery of exceptions and deviations o Statistical significance in large-scale search o The problems of over-fit * Logic-based perspective on data mining o Inferring knowledge from data o Exploring different subspaces of first order logic o Rough sets in data mining o Fuzzy sets in data mining o Boolean approaches to data mining o Inductive Logic Programming for mining real databases o Pattern-recognition for data mining o Clustering analysis o Tolerance (similarity) relations o KDD-motivated discretization of data * Man-Machine interaction in data mining o Visualization of data o Visualization of results o Interface design o Interactive data mining: human and computer contributions * Artificial Intelligence contributions to KDD o Representing knowledge and hypotheses spaces o Search for knowledge and its complexities o Combining many methods in one system * High performance computing for data mining o Hardware dedicated to discovery applications o Parallel discovery algorithms and complexity o Distributed data mining o Scalability in high dimensional datasets * From machine learning to KDD o From concept learning to concept discovery o Expanding the autonomy of machine learners o Embedding learning methods in KDD systems o Conceptual clustering in knowledge discovery * From automated scientific discovery to KDD o Applications of scientific discovery systems to databases o Experience with hypothesis evaluation that transfers to KDD o Hypothesis spaces of scientific discovery applied in KDD o Differences between the data handled in both fields o Scientific discovery techniques relevant in KDD * Quality assessment of data mining results o Multi-criteria knowledge evaluation o Benchmarks and metrics for system evaluation o Statistical tests in KDD applications o Usefulness and risk assessment in decision-making * Applications of data mining and knowledge discovery o Medicine: diagnosis and prognosis o Control theory: predictive and adaptive control, model identification o Engineering: diagnosis of mechanisms and processes o Public administration o Marketing and finance o Data mining on the web in text and heterogeneous data o Natural and social science Submission details Submissions are by email (preferred) to pkdd97@idt.ntnu.no or by airmail to Jan Komorowski (see address below). Papers should be in English and not exceed ten single-spaced pages of 12pt font. The first page should begin with title, authors, affiliations, surface and e-mail addresses, and an abstract of about 200 words. Proceedings The proceedings of the Symposium will be published in the Springer Verlag Lecture Notes AI Series ( www.springer.de/comp/comp.html) and available at PKDD97, June 25-27. Important dates * Submission deadline: February 17th, 1997 * Notice of acceptance: March 17th * Camera ready papers: April 4th PANEL DISCUSSIONS: proposals are sought for panels that stimulate interaction between the communities contributing to KDD. Include title. Submit prospective participants and a summary of the topics to be discussed. Submission to zytkow@cs.twsu.edu by March 14th. Notice of acceptance by March 21th. POSTER SESSION: informative descriptions of successful applications of data mining and knowledge discovery techniques in processing new data sets may be submitted for presentation at the poster session. Send an extended abstract, not exceeding two pages of 12pt, single spaced text to pkdd97@idt.ntnu.no by March 14th. Notice of acceptance by March 21st. TUTORIALS: proposals are solicited for tutorials that: (1) transfer know-how and provide hands-on experience, (2) combine two or more areas (e.g. rough sets and statistics, high-performance computing and databases, etc), or (3) cover application domains such as finance, medicine, or automatic control. Submission to pkdd97@idt.ntnu.no by February 19th. Notice of acceptance by March 10th. DEMONSTRATIONS OF SOFTWARE for data mining and knowledge discovery are invited. This includes professional and experimental systems. Send descriptions to pkdd97@idt.ntnu.no by June 2nd. Program co-chairs Jan Komorowski, Trondheim, Norway Jan Zytkow, Wichita, USA Jan.Komorowski@idt.ntnu.no zytkow@cs.twsu.edu Department of Computer Systems Norwegian University of Science and Technology 7034 Trondheim, Norway. Details regarding the conference will be forthcoming. Watch the PKDD'97 WWW page for details (http://www.idt.ntnu.no/pkdd97). ---------------------------------------------------------------------------- [NTNU][NTNU] [Norge] [Norge] ---------------------------------------------------------------------------- Jan.Komorowski@idt.ntnu.no Last modified: Mon Feb 10 17:56:07 MET 1997