Research and Development in Knowledge Discovery and Data Mining de Xindong Wu

Research and Development in Knowledge Discovery and Data Mining

Xindong Wu

Ramamohanarao Kotagiri

Kevin B. Korb

This book constitutes the refereed proceedings of the Second Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD-98, held in Melbourne, Australia, in April 1998. The book presents 30 revised full papers selected from a total of 110 submissions; also included are 20 poster presentations. The papers contribute new results to all current aspects in knowledge discovery and data mining on the research level as well as on the level of systems development. Among the areas covered are machine learning, information systems, the Internet, statistics, knowledge acquisition, data visualization, software reengineering, and knowledge based systems.

Citește tot Restrânge

Cuprins

Knowledge acquisition for goal prediction in a multi-user adventure game.- Hybrid data mining systems: The next generation.- Discovering case knowledge using data mining.- Discovery of association rules over ordinal data: A new and faster algorithm and its application to basket analysis.- Effect of data skewness in parallel mining of association rules.- Trend directed learning: A case study.- Interestingness of discovered association rules in terms of neighborhood-based unexpectedness.- Point estimation using the Kullback-Leibler loss function and MML.- Single factor analysis in MML mixture modelling.- Discovering associations in spatial data — An efficient medoid based approach.- Data mining using dynamically constructed recurrent fuzzy neural networks.- CCAIIA: Clustering categorical attributes into interesting association rules.- Selective materialization: An efficient method for spatial data cube construction.- Mining market basket data using share measures and characterized itemsets.- Automatic visualization method for visual data mining.- Rough-set inspired approach to knowledge discovery in business databases.- Representative association rules.- Identifying relevant databases for multidatabase mining.- Minimum message length segmentation.- Bayesian classification trees with overlapping leaves applied to credit-scoring.- Contextual text representation for unsupervised knowledge discovery in texts.- Treatment of missing values for association rules.- Mining regression rules and regression trees.- Mining algorithms for sequential patterns in parallel : Hash based approach.- Wavelet transform in similarity paradigm.- Improved rule discovery performance on uncertainty.- Feature mining and mapping of collinear data.- Knowledge discovery in discretionary legaldomains.- Scaling up the rule generation of C4.5.- Data mining based on the generalization distribution table and rough sets.- Constructing personalized information agents.- Towards real time discovery from distributed information sources.- Constructing conceptual scales in formal concept analysis.- The hunter and the hunted — Modelling the relationship between web pages and search engines.- An efficient global discretization method.- Learning user preferences on the WEB.- Using rough sets for knowledge discovery in the development of a decision support system for issuing smog alerts.- Empirical results on data dimensionality reduction using the divided self-organizing map.- Mining association rules with linguistic cloud models.- A data mining approach for query refinement.- CFMD: A conflict-free multivariate discretization algorithm.- Characteristic rule induction algorithm for data mining.- Data-mining massive time series astronomical data sets — A case study.- Multiple databases, partial reasoning, and knowledge discovery.- Design recovery with data mining techniques.- The CLARET algorithm.- LRTree: A hybrid technique for classifying myocardial infarction data containing unknown attribute values.- Modelling decision tables from data.- A classification and relationship extraction scheme for relational databases based on fuzzy logic.- Mining association rules for estimation and prediction.- Rule generalization by condition combination.