Methodologies for Knowledge Discovery and Data Mining

This volume contains the papers selected for presentation at the Third Paci?c- Asia Conference on Knowledge Discovery and Data Mining (PAKDD-99)held in the Xiangshan Hotel, Beijing, China, April 26-28, 1999. The conference was sp- sored by Tsinghua University, National Science Foundation of China, Chinese Computer Federation, Toshiba Corporation, and NEC Software Chugoku, Ltd. PAKDD-99 provided an international forum for the sharing of original research results and practical development experiences among researchers and application developers from di?erent KDD-related areas such as machine lea- ing, databases, statistics, knowledge acquisition, data visualization, knowled- based systems, soft computing, and high performance computing. It followed the success of PAKDD-97 held in Singapore in 1997 and PAKDD-98 held in A- tralia in 1998 by bringing together participants from universities, industry, and government. PAKDD-99 encouraged both new theory/methodologies and real world - plications, and covered broad and diverse topics in data mining and knowledge discovery. The technical sessions included: Association Rules Mining; Feature Selection and Generation; Mining in Semi, Un-structured Data; Interestingness, Surprisingness, and Exceptions; Rough Sets, Fuzzy Logic, and Neural Networks; Induction, Classi?cation, and Clustering; Causal Model and Graph-Based Me- ods; Visualization; Agent-Based, and Distributed Data Mining; Advanced Topics and New Methodologies. Of the 158 submissions, we accepted 29 regular papers and 37 short papers for presentation at the conference and for publication in this volume. In addition, over 20 papers were accepted for poster presentation.

Includes supplementary material: sn.pub/extras

Auteur
Ning Zhong is currently head of Knowledge Information Systems Laboratory, and a professor in Department of Systems and Information Engineering, Graduate School, Maebashi Institute of Technology, Japan. He is also CEO of Web Intelligence Laboratory, Inc., a new type of venture intelligent IT business company. Before moving to Maebashi Institute of Technology, he was an associate professor in Department of Computer Science and Systems Engineering, Yamaguchi University, Japan. He is also a guest professor of Beijing University of Technology since 1998. He is the co-founder and co-chair of Web Intelligence Consortium (WIC), vice chair of the executive committee of the IEEE Computer Society Technical Committee on Computational Intelligence (TCCI), the advisory board of ACM SIGART, steering committee of IEEE International Conferences on Data Mining (ICDM), the advisory board of International Rough Set Society, steering committee of Pacific-Asia Conferences on Knowledge Discovery and Data Mining (PAKDD), coordinator and member of advisory board of a Special Interest Group on Granular Computing in Berkeley Initiative in Soft Computing (BISC/SIG-GrC).

Contenu
Invited Talks.- KDD as an Enterprise IT Tool: Reality and Agenda.- Computer Assisted Discovery of First Principle Equations from Numeric Data.- Emerging KDD Technology.- Data Mining a Rough Set Perspective.- Data Mining Techniques for Associations, Clustering and Classification.- Data Mining: Granular Computing Approach.- Rule Extraction from Prediction Models.- Association Rules.- Mining Association Rules on Related Numeric Attributes.- LGen A Lattice-Based Candidate Set Generation Algorithm for I/O Efficient Association Rule Mining.- Extending the Applicability of Association Rules.- An Efficient Approach for Incremental Association Rule Mining.- Association Rules in Incomplete Databases.- Parallel SQL Based Association Rule Mining on Large Scale PC Cluster: Performance Comparison with Directly Coded C Implementation.- H-Rule Mining in Heterogeneous Databases.- An Improved Definition of Multidimensional Inter-transaction Association Rule.- Incremental Discovering Association Rules: A Concept Lattice Approach.- Feature Selection and Generation.- Induction as Pre-processing.- Stochastic Attribute Selection Committees with Multiple Boosting: Learning More Accurate and More Stable Classifier Committees.- On Information-Theoretic Measures of Attribute Importance.- A Technique of Dynamic Feature Selection Using the Feature Group Mutual Information.- A Data Pre-processing Method Using Association Rules of Attributes for Improving Decision Tree.- Mining in Semi, Un-structured Data.- An Algorithm for Constrained Association Rule Mining in Semi-structured Data.- Incremental Mining of Schema for Semistructured Data.- Discovering Structure from Document Databases.- Combining Forecasts from Multiple Textual Data Sources.- Domain Knowledge Extracting in a Chinese NaturalLanguage Interface to Databases: NChiql.- Interestingness, Surprisingness, and Exceptions.- Evolutionary Hot Spots Data Mining.- Efficient Search of Reliable Exceptions.- Heuristics for Ranking the Interestingness of Discovered Knowledge.- Rough Sets, Fuzzy Logic, and Neural Networks.- Automated Discovery of Plausible Rules Based on Rough Sets and Rough Inclusion.- Discernibility System in Rough Sets.- Automatic Labeling of Self-Organizing Maps: Making a Treasure-Map Reveal Its Secrets.- Neural Network Based Classifiers for a Vast Amount of Data.- Accuracy Tuning on Combinatorial Neural Model.- A Situated Information Articulation Neural Network: VSF Network.- Neural Method for Detection of Complex Patterns in Databases.- Preserve Discovered Linguistic Patterns Valid in Volatility Data Environment.- An Induction Algorithm Based on Fuzzy Logic Programming.- Rule Discovery in Databases with Missing Values Based on Rough Set Model.- Sustainability Knowledge Mining from Human Development Database.- Induction, Classification, and Clustering.- Characterization of Default Knowledge in Ripple Down Rules Method.- Improving the Performance of Boosting for Naive Bayesian Classification.- Convex Hulls in Concept Induction.- Mining Classification Knowledge Based on Cloud Models.- Robust Clusterin of Large Geo-referenced Data Sets.- A Fast Algorithm for Density-Based Clustering in Large Database.- A Lazy Model-Based Algorithm for On-Line Classification.- An Efficient Space-Partitioning Based Algorithm for the K-Means Clustering.- A Fast Clustering Process for Outliers and Remainder Clusters.- Optimising the Distance Metric in the Nearest Neighbour Algorithm on a Real-World Patient Classification Problem.- Classifying Unseen Cases with Many Missing Values.- Study of a Mixed SimilarityMeasure for Classification and Clustering.- Visualization.- Visually Aided Exploration of Interesting Association Rules.- DVIZ: A System for Visualizing Data Mining.- Causal Model and Graph-Based Methods.- A Minimal Causal Model Learner.- Efficient Graph-Based Algorithm for Discovering and Maintaining Knowledge in Large Databases.- Basket Analysis for Graph Structured Data.- The Evolution of Causal Models: A Comparison of Bayesian Metrics and Structure Priors.- KD-FGS: A Knowledge Discovery System from Graph Data Using Formal Graph System.- Agent-Based, and Distributed Data Mining.- Probing Knowledge in Distributed Data Mining.- Discovery of Equations and the Shared Operational Semantics in Distributed Autonomous Databases.- The Data-Mining and the Technology of Agents to Fight the Illicit Electronic Messages.- Knowledge Discovery in SportsFinder: An Agent to Extract Sports Results from the Web.- Event Mining with Event Processing Networks.- Advanced Topics and New Methodologies.- An Analysis of Quantitative Measures Associated with Rules.- A Strong Relevant Logic Model of Epistemic Processes in Scientific Discovery.- Discovering Conceptual Differences among Different People via Diverse Structures.- Ordered Estimation of Missing Values.- Prediction Rule Discovery Based on Dynamic Bias Selection.- Discretization of Continuous Attributes for Learning Classification Rules.- BRRA: A Based Relevant Rectangles Algorithm for Mining Relationships in D…