Progress in discovery science : final report of the Japanese Dicsovery [sic] Science project : proceedings

Annotation This book documents the scientific outcome and constitutes the final report of the Japanese research project on discovery science. During three years more than 60 scientists participated in the project and developed a wealth of new methods for knowledge discovery and data mining. The 52 revised full papers presented were carefully reviewed and span the whole range of knowledge discovery from logical foundations and inductive reasoning to statistical inference and computational learning. A broad variety of advanced applications are presented including knowledge discovery and data mining in very large databases, knowledge discovery in network environments, text mining, information extraction, rule mining, Web mining, image processing, and pattern recognition Searching for Mutual Exclusion Algorithms Using BDDs....Pages 1-18 Reducing Search Space in Solving Higher-Order Equations....Pages 19-30 The Structure of Scientific Discovery: From a Philosophical Point of View....Pages 31-39 Ideal Concepts, Intuitions, and Mathematical Knowledge Acquisitions in Husserl and Hilbert....Pages 40-77 Theory of Judgments and Derivations....Pages 78-122 Efficient Data Mining from Large Text Databases....Pages 123-139 A Computational Model for Children’s Language Acquisition Using Inductive Logic Programming....Pages 140-155 Some Criterions for Selecting the Best Data Abstractions....Pages 156-167 Discovery of Chances Underlying Real Data....Pages 168-177 Towards the Integration of Inductive and Nonmonotonic Logic Programming....Pages 178-188 EM Learning for Symbolic-Statistical Models in Statistical Abduction....Pages 189-200 Refutable/Inductive Learning from Neighbor Examples and Its Application to Decision Trees over Patterns....Pages 201-213 Constructing a Critical Casebase to Represent a Lattice-Based Relation....Pages 214-223 On Dimension Reduction Mappings for Approximate Retrieval of Multi-dimensional Data....Pages 224-231 Rule Discovery from fMRI Brain Images by Logical Regression Analysis....Pages 232-245 A Theory of Hypothesis Finding in Clausal Logic....Pages 246-257 Efficient Data Mining by Active Learning....Pages 258-267 Data Compression Method Combining Properties of PPM and CTW....Pages 268-283 Discovery of Definition Patterns by Compressing Dictionary Sentences....Pages 284-295 On-Line Algorithm to Predict Nearly as Well as the Best Pruning of a Decision Tree....Pages 296-306 Finding Best Patterns Practically....Pages 307-317 Classification of Object Sequences Using Syntactical Structure....Pages 318-326 Top-Down Decision Tree Boosting and Its Applications....Pages 327-337 Extraction of Primitive Motion and Discovery of Association Rules from Human Motion Data....Pages 338-348 Algorithmic Aspects of Boosting....Pages 349-359 Automatic Detection of Geomagnetic Jerks by Applying a Statistical Time Series Model to Geomagnetic Monthly Means....Pages 360-371 Application of Multivariate Maxwellian Mixture Model to Plasma Velocity Distribution....Pages 372-383 Inductive Thermodynamics from Time Series Data Analysis....Pages 384-394 Mining of Topographic Feature from Heterogeneous Imagery and Its Application to Lunar Craters....Pages 395-407 Application of Neural Network Technique to Combustion Spray Dynamics Analysis....Pages 408-425 Computational Analysis of Plasma Waves and Particles in the Auroral Region Observed by Scientific Satellite....Pages 426-437 A Flexible Modeling of Global Plasma Profile Deduced from Wave Data....Pages 438-448 Extraction of Signal from High Dimensional Time Series: Analysis of Ocean Bottom Seismograph Data....Pages 449-458 Foundations of Designing Computational Knowledge Discovery Processes....Pages 459-470 Computing Optimal Hypotheses Efficiently for Boosting....Pages 471-481 Discovering Polynomials to Fit Multivariate Data Having Numeric and Nominal Variables....Pages 482-493 Finding of Signal and Image by Integer-Type Haar Lifting Wavelet Transform....Pages 494-503 In Pursuit of Interesting Patterns with Undirected Discovery of Exception Rules....Pages 504-517 Mining from Literary Texts: Pattern Discovery and Similarity Computation....Pages 518-531 Second Difference Method Reinforced by Grouping: A New Tool for Assistance in Assignment of ComplexMolecular Spectra....Pages 532-542 Discovery of Positive and Negative Knowledge in Medical Databases Using Rough Sets....Pages 543-552 Toward the Discovery of First Principle Based Scientific Law Equations....Pages 553-564 A Machine Learning Algorithm for Analyzing String Patterns Helps to Discover Simple and Interpretable Business Rules from Purchase History....Pages 565-575 Constructing Inductive Applications by Meta-Learning with Method Repositories....Pages 576-585 Knowledge Discovery from Semistructured Texts....Pages 586-599 Packet Analysis in Congested Networks....Pages 600-615 Visualization and Analysis of Web Graphs....Pages 616-627 Knowledge Discovery in Auto-tuning Parallel Numerical Library....Pages 628-639 Extended Association Algorithm Based on ROC Analysis for Visual Information Navigator....Pages 640-649 WWW Visualization Tools for Discovering Interesting Web Pages....Pages 650-660 Scalable and Comprehensible Visualization for Discovery of Knowledge from the Internet....Pages 661-671 Meme Media for Re-editing and Redistributing Intellectual Assets and Their Application to Interactive Virtual Information Materialization....Pages 672-681 This volume contains the research reports of the Discovery Science pro ject in Japan (No. 10143106), in which more than 60 scientists participated. It was a three-year pro ject sponsored by Grant-in-Aid for Scienti?c Research on Priority Areas from the Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan. This pro ject mainly aimed to (1) develop new methods for knowledge discovery, (2) install network environments for knowledge discovery, and (3) establish Discovery Science as a new area of study in Computer Science / Arti?cial Intelligence. In order to attain these aims we set up?ve groups for studying the following research areas: (A) Logic for/of Knowledge Discovery (B) Knowledge Discovery by Inference/Reasoning (C) Knowledge Discovery Based on Computational Learning Theory (D) Knowledge Discovery in Huge Databases and Data Mining (E) Knowledge Discovery in Network Environments These research areas and related topics can be regarded as a preliminary d- inition of Discovery Science by enumeration. Thus Discovery Science ranges over philosophy, logic, reasoning, computational learning, and system developments. In addition to these?ve research groups we organized a steering group for planning, adjustment, and evaluation of the project. The steering group, chaired by the principal investigator of the project, consists of leaders of the?ve research groups and their subgroups as well as advisors from outside of the pro ject. We invited three scientists to consider Discovery Science and the?ve above m- tioned research areas from viewpoints of knowledge science, natural language processing, and image processi ng, respectively