Discovery Science [electronic resource] : 5th International Conference, DS 2002, Lubeck, Germany, November 24-26, 2002, Proceedings /

Invited Talks -- Mathematics Based on Learning -- Data Mining with Graphical Models -- On the Eigenspectrum of the Gram Matrix and Its Relationship to the Operator Eigenspectrum -- In Search of the Horowitz Factor: Interim Report on a Musical Discovery Project -- Learning Structure from Sequences, with Applications in a Digital Library -- Regular Papers -- Discovering Frequent Structured Patterns from String Databases: An Application to Biological Sequences -- Discovery in Hydrating Plaster Using Machine Learning Methods -- Revising Qualitative Models of Gene Regulation -- SEuS: Structure Extraction Using Summaries -- Discovering Best Variable-Length-Don’t-Care Patterns -- A Study on the Effiect of Class Distribution Using Cost-Sensitive Learning -- Model Complexity and Algorithm Selection in Classification -- Experiments with Projection Learning -- Improved Dataset Characterisation for Meta-learning -- Racing Committees for Large Datasets -- From Ensemble Methods to Comprehensible Models -- Learning the Causal Structure of Overlapping Variable Sets -- Extraction of Logical Rules from Data by Means of Piecewise-Linear Neural Networks -- Structuring Neural Networks through Bidirectional Clustering of Weights -- Toward Drawing an Atlas of Hypothesis Classes: Approximating a Hypothesis via Another Hypothesis Model -- Datascape Survey Using the Cascade Model -- Learning Hierarchical Skills from Observation -- Poster Papers -- Image Analysis for Detecting Faulty Spots from Microarray Images -- Inferring Gene Regulatory Networks from Time-Ordered Gene Expression Data Using Differential Equations -- DNA-Tract Curvature Profile Reconstruction: A Fragment Flipping Algorithm -- Evolution Map: Modeling State Transition of Typhoon Image Sequences by Spatio-Temporal Clustering -- Structure-SweetnessRelationships of Aspartame Derivatives by GUHA -- A Hybrid Approach for Chinese Named Entity Recognition -- Extraction of Word Senses from Human Factors in Knowledge Discovery -- Event Pattern Discovery from the Stock Market Bulletin -- Email Categorization Using Fast Machine Learning Algorithms -- Discovery of Maximal Analogies between Stories -- Automatic Wrapper Generation for Multilingual Web Resources -- Combining Multiple K-Nearest Neighbor Classifiers for Text Classification by Reducts -- ARISTA Causal Knowledge Discovery from Texts -- Knowledge Discovery as Applied to Music: Will Music Web Retrieval Revolutionize Musicology? -- Process Mining: Discovering Direct Successors in Process Logs -- The Emergence of Artificial Creole by the EM Algorithm -- Generalized Musical Pattern Discovery by Analogy from Local Viewpoints -- Using Genetic Algorithms-Based Approach for Better Decision Trees: A Computational Study -- Handling Feature Ambiguity in Knowledge Discovery from Time Series -- A Compositional Framework for Mining Longest Ranges -- Post-processing Operators for Browsing Large Sets of Association Rules -- Mining Patterns from Structured Data by Beam-Wise Graph-Based Induction -- Feature Selection for Propositionalization -- Subspace Clustering Based on Compressibility -- The Extra-Theoretical Dimension of Discovery Extracting Knowledge by Abduction -- Discovery Process on the WWW: Analysis Based on a Theory of Scientific Discovery -- Invention vs. Discovery A Critical Discussion.