Advances in Knowledge Discovery and Data Mining: 12th Pacific-Asia Conference, Pakdd 2008 Osaka, Japan, May 20-23, 2008 Proceedings

ISBN-13: 9783540681243 / Angielski / Miękka / 2008 / 1102 str.

Takashi Washio

Opis

ThePaci?c-AsiaConferenceonKnowledgeDiscoveryandDataMining(PAKDD) has been held every year since 1997. PAKDD 2008, the 12th in the series, was heldatOsaka, JapanduringMay20-23,2008.PAKDDisaleadinginternational conference in the area of data mining. It provides an international forum for - searchers and industry practitioners to share their new ideas, original research results, and practical development experiences from all KDD-related areas - cluding data mining, data warehousing, machine learning, databases, statistics, knowledge acquisition, automatic scienti?c discovery, data visualization, causal induction, and knowledge-based systems. This year we received a total of 312 research papers from 34 countries and regions in Asia, Australia, North America, South America, Europe, and Africa. Every submitted paper was rigorously reviewed by two or three reviewers, d- cussed by the reviewers under the supervision of an Area Chair, and judged by the Program Committee Chairs. When there was a disagreement, the Area Chair and/or the Program Committee Chairs provided an additional review. Thus, many submissions were reviewed by four experts. The Program Comm- tee members were deeply involved in a highly selective process. As a result, only approximately11.9%ofthe312submissionswereacceptedaslongpapers,12.8% of them were accepted as regular papers, and 11.5% of them were accepted as short papers.

Spis treści

Keynote Speech.- Graph Mining: Laws, Generators and Tools.- Invited Speeches.- Efficient Algorithms for Mining Frequent and Closed Patterns from Semi-structured Data.- Supporting Creativity: Towards Associative Discovery of New Insights.- Cost-Sensitive Classifier Evaluation Using Cost Curves.- Prospective Scientific Methodology in Knowledge Society.- Long Papers.- SubClass: Classification of Multidimensional Noisy Data Using Subspace Clusters.- Mining Quality-Aware Subspace Clusters.- A Decremental Approach for Mining Frequent Itemsets from Uncertain Data.- Multi-class Named Entity Recognition Via Bootstrapping with Dependency Tree-Based Patterns.- Towards Region Discovery in Spatial Datasets.- Accurate and Efficient Retrieval of Multimedia Time Series Data Under Uniform Scaling and Time Warping.- Feature Construction Based on Closedness Properties Is Not That Simple.- On Addressing Accuracy Concerns in Privacy Preserving Association Rule Mining.- Privacy-Preserving Linear Fisher Discriminant Analysis.- Unsupervised Change Analysis Using Supervised Learning.- ANEMI: An Adaptive Neighborhood Expectation-Maximization Algorithm with Spatial Augmented Initialization.- Minimum Variance Associations — Discovering Relationships in Numerical Data.- An Efficient Unordered Tree Kernel and Its Application to Glycan Classification.- Generation of Globally Relevant Continuous Features for Classification.- Mining Bulletin Board Systems Using Community Generation.- Extreme Support Vector Machine Classifier.- LCM over ZBDDs: Fast Generation of Very Large-Scale Frequent Itemsets Using a Compact Graph-Based Representation.- Unusual Pattern Detection in High Dimensions.- Person Name Disambiguation in Web Pages Using Social Network, Compound Words and Latent Topics.- Mining Correlated Subgraphs in Graph Databases.- A Minimal Description Length Scheme for Polynomial Regression.- Handling Numeric Attributes in Hoeffding Trees.- Scaling Record Linkage to Non-uniform Distributed Class Sizes.- Large-Scale k-Means Clustering with User-Centric Privacy Preservation.- Semi-Supervised Local Fisher Discriminant Analysis for Dimensionality Reduction.- An Efficient Algorithm for Finding Similar Short Substrings from Large Scale String Data.- Ambiguous Frequent Itemset Mining and Polynomial Delay Enumeration.- Characteristic-Based Descriptors for Motion Sequence Recognition.- Protecting Privacy in Incremental Maintenance for Distributed Association Rule Mining.- SEM: Mining Spatial Events from the Web.- BOAI: Fast Alternating Decision Tree Induction Based on Bottom-Up Evaluation.- Feature Selection by Nonparametric Bayes Error Minimization.- A Framework for Modeling Positive Class Expansion with Single Snapshot.- A Decomposition Algorithm for Learning Bayesian Network Structures from Data.- Learning Classification Rules for Multiple Target Attributes.- A Mixture Model for Expert Finding.- On Privacy in Time Series Data Mining.- Regular Papers.- Exploiting Propositionalization Based on Random Relational Rules for Semi-supervised Learning.- On Discrete Data Clustering.- Automatic Training Example Selection for Scalable Unsupervised Record Linkage.- Analyzing PETs on Imbalanced Datasets When Training and Testing Class Distributions Differ.- Improving the Robustness to Outliers of Mixtures of Probabilistic PCAs.- Exploratory Hot Spot Profile Analysis Using Interactive Visual Drill-Down Self-Organizing Maps.- Maintaining Optimal Multi-way Splits for Numerical Attributes in Data Streams.- Efficient Mining of High Utility Itemsets from Large Datasets.- Tradeoff Analysis of Different Markov Blanket Local Learning Approaches.- Forecasting Urban Air Pollution Using HMM-Fuzzy Model.- Relational Pattern Mining Based on Equivalent Classes of Properties Extracted from Samples.- Evaluating Standard Techniques for Implicit Diversity.- A Simple Characterization on Serially Constructible Episodes.- Bootstrap Based Pattern Selection for Support Vector Regression.- Tracking Topic Evolution in On-Line Postings: 2006 IBM Innovation Jam Data.- PAID: Packet Analysis for Anomaly Intrusion Detection.- A Comparison of Different Off-Centered Entropies to Deal with Class Imbalance for Decision Trees.- FIsViz: A Frequent Itemset Visualizer.- A Tree-Based Approach for Frequent Pattern Mining from Uncertain Data.- Connectivity Based Stream Clustering Using Localised Density Exemplars.- Learning User Purchase Intent from User-Centric Data.- Query Expansion for the Language Modelling Framework Using the Naïve Bayes Assumption.- Fast Online Estimation of the Joint Probability Distribution.- Fast k Most Similar Neighbor Classifier for Mixed Data Based on Approximating and Eliminating.- Entity Network Prediction Using Multitype Topic Models.- Using Supervised and Unsupervised Techniques to Determine Groups of Patients with Different Doctor-Patient Stability.- Local Projection in Jumping Emerging Patterns Discovery in Transaction Databases.- Applying Latent Semantic Indexing in Frequent Itemset Mining for Document Relation Discovery.- G-TREACLE: A New Grid-Based and Tree-Alike Pattern Clustering Technique for Large Databases.- A Clustering-Oriented Star Coordinate Translation Method for Reliable Clustering Parameterization.- Constrained Clustering for Gene Expression Data Mining.- Concept Lattice–Based Mutation Control for Reactive Motifs Discovery.- Mining a Complete Set of Both Positive and Negative Association Rules from Large Databases.- Designing a System for a Process Parameter Determined through Modified PSO and Fuzzy Neural Network.- Data-Aware Clustering Hierarchy for Wireless Sensor Networks.- A More Topologically Stable Locally Linear Embedding Algorithm Based on R*-Tree.- Sparse Kernel-Based Feature Weighting.- Term Committee Based Event Identification within News Topics.- Locally Linear Online Mapping for Mining Low-Dimensional Data Manifolds.- A Creditable Subspace Labeling Method Based on D-S Evidence Theory.- Short Papers.- Discovering New Orders of the Chemical Elements through Genetic Algorithms.- What Is Frequent in a Single Graph?.- A Cluster-Based Genetic-Fuzzy Mining Approach for Items with Multiple Minimum Supports.- A Selective Classifier for Incomplete Data.- Detecting Near-Duplicates in Large-Scale Short Text Databases.- Customer Churn Time Prediction in Mobile Telecommunication Industry Using Ordinal Regression.- Rule Extraction with Rough-Fuzzy Hybridization Method.- I/O Scalable Bregman Co-clustering.- Jumping Emerging Patterns with Occurrence Count in Image Classification.- Mining Non-coincidental Rules without a User Defined Support Threshold.- Transaction Clustering Using a Seeds Based Approach.- Using Ontology-Based User Preferences to Aggregate Rank Lists in Web Search.- The Application of Echo State Network in Stock Data Mining.- Text Categorization of Multilingual Web Pages in Specific Domain.- Efficient Joint Clustering Algorithms in Optimization and Geography Domains.- Active Learning with Misclassification Sampling Using Diverse Ensembles Enhanced by Unlabeled Instances.- A New Model for Image Annotation.- Unmixed Spectrum Clustering for Template Composition in Lung Sound Classification.- Forward Semi-supervised Feature Selection.- Automatic Extraction of Basis Expressions That Indicate Economic Trends.- A New Framework for Taxonomy Discovery from Text.- R-Map: Mapping Categorical Data for Clustering and Visualization Based on Reference Sets.- Mining Changes in Patent Trends for Competitive Intelligence.- Seeing Several Stars: A Rating Inference Task for a Document Containing Several Evaluation Criteria.- Structure-Based Hierarchical Transformations for Interactive Visual Exploration of Social Networks.- CP-Tree: A Tree Structure for Single-Pass Frequent Pattern Mining.- Combining Context and Existing Knowledge When Recognizing Biological Entities – Early Results.- Semantic Video Annotation by Mining Association Patterns from Visual and Speech Features.- Cell-Based Outlier Detection Algorithm: A Fast Outlier Detection Algorithm for Large Datasets.- Fighting WebSpam: Detecting Spam on the Graph Via Content and Link Features.- A Framework for Discovering Spatio-temporal Cohesive Networks.- Efficient Mining of Minimal Distinguishing Subgraph Patterns from Graph Databases.- Combined Association Rule Mining.- Enriching WordNet with Folksonomies.- A New Credit Scoring Method Based on Rough Sets and Decision Tree.- Analyzing the Propagation of Influence and Concept Evolution in Enterprise Social Networks through Centrality and Latent Semantic Analysis.

Blurb

This book constitutes the refereed proceedings of the 12th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2008, held in Osaka, Japan, in May 2008.

The 37 revised long papers, 40 revised full papers, and 36 revised short papers presented together with 1 keynote talk and 4 invited lectures were carefully reviewed and selected from 312 submissions. The papers present new ideas, original research results, and practical development experiences from all KDD-related areas including data mining, data warehousing, machine learning, databases, statistics, knowledge acquisition, automatic scientific discovery, data visualization, causal induction, and knowledge-based systems.