## Advances in Knowledge Discovery and Data Mining: 5th Pacific-Asia Conference, PAKDD 2001 Hong Kong, China, April 16-18, 2001. ProceedingsDavid Cheung, Graham J. Williams, Qing Li This book constitutes the refereed proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001, held in Hong Kong, China in April 2001. The 38 revised full papers and 22 short papers presented were carefully reviewed and selected from a total of 152 submissions. The book offers topical sections on Web mining, text mining, applications and tools, concept hierarchies, feature selection, interestingness, sequence mining, spatial and temporal mining, association mining, classification and rule induction, clustering, and advanced topics and new methods. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

Incompleteness in Data Mining | 1 |

The Good the Bad and the Ugly | 2 |

Seamless Integration of Data Mining with DBMS and Applications | 3 |

Applying Pattern Mining to Web Information Extraction | 4 |

Empirical Study of Recommender Systems Using Linear Classifiers | 16 |

iJADE eMiner A WebBased Mining Agent Based on Intelligent Java Agent Development Environment iJADE on Internet Shopping | 28 |

A Characterized Rating Recommend System | 41 |

Discovery of Frequent Tree Structured Patterns in Semistructured Web Documents | 47 |

An Index Structure for Subsequence Matching of Spatial Objects | 312 |

Temporal Data Mining Using Hidden MarkovLocal Polynomial Models | 324 |

Patterns Discovery Based on TimeSeries Decomposition | 336 |

Criteria on Proximity Graphs for Boundary Extraction and Spatial Clustering | 348 |

Micro Similarity Queries in Time Series Database | 358 |

Mining Optimal Class Association Rule Set | 364 |

Generating Frequent Patterns with the Frequent Pattern List | 376 |

UserDefined Association Mining | 387 |

Text Categorization Using Weight Adjusted kNearest Neighbor Classification | 53 |

Predictive SelfOrganizing Networks for Text Categorization | 66 |

Metalearning Models for Automatic Textual Document Categorization | 78 |

Efficient Algorithms for Concept Space Construction | 90 |

Topic Detection Tracking and Trend Analysis Using SelfOrganizing Neural Networks | 102 |

Automatic Hypertext Construction through a Text Mining Approach by SelfOrganizing Maps | 108 |

A Study on Hong Kong Stock Movement Analysis | 114 |

A Toolbox Approach to Flexible and Efficient Data Mining | 124 |

Determining Progression in Glaucoma Using Visual Fields | 136 |

Seabreeze Prediction Using Bayesian Networks | 148 |

Semisupervised Learning in Medical Image Database | 154 |

On Application of Rough Data Mining Methods to Automatic Construction of Student Models | 161 |

Concept Approximation in Concept Lattice | 167 |

Mining Additional Semantics in Relational Data | 174 |

Representing Large Concept Hierarchies Using Lattice Data Structure | 186 |

Feature Selection for Temporal Health Records | 198 |

Boosting the Performance of Nearest Neighbour Methods with Feature Selection | 210 |

Feature Selection for Metalearning | 222 |

Efficient Mining of Niches and Set Routines | 234 |

Evaluation of Interestingness Measures for Ranking Discovered Knowledge | 247 |

Peculiarity Oriented Mining and Its Application for Knowledge Discovery in AminoAcid Data | 260 |

Mining Sequence Patterns from Wind Tunnel Experimental Data for Flight Control | 270 |

Scalable Hierarchical Clustering Method for Sequences of Categorical Values | 282 |

FFS An IOEfficient Algorithm for Mining Frequent Sequences | 294 |

Sequential Index Structure for ContentBased Retrieval | 306 |

Direct and Incremental Computing of Maximal Covering Rules | 400 |

Towards Efficient Data Remining DRM | 406 |

Data Allocation Algorithm for Parallel Association Rule Discovery | 413 |

Direct Domain Knowledge Inclusion in the PA3 Rule Induction Algorithm | 421 |

Hierarchical Classification of Documents with Error Control | 433 |

An Efficient Data Compression Approach to the Classification Task | 444 |

Combining the Strength of Pattern Frequency and Distance for Classification | 455 |

A Scalable Algorithm for Rule Postpruning of Large Decision Trees | 467 |

Optimizing the Induction of Alternating Decision Trees | 477 |

Building Behaviour Knowledge Space to Make Classification Decision | 488 |

Efficient Hierarchical Clustering Algorithms Using Partially Overlapping Partitions | 495 |

A Rough SetBased Clustering Method with Modification of Equivalence Relations | 507 |

Importance of Individual Variables in the kMeans Algorithm | 513 |

A Hybrid Approach to Clustering in Very Large Databases | 519 |

A Similarity Indexing Method for the Data Warehousing BitWise Indexing Method | 525 |

Rule Reduction over Numerical Attributes in Decision Tree Using Multilayer Perceptron | 538 |

Knowledge Acquisition from Both Human Expert and Data | 550 |

Neighborhood Dependencies for Prediction | 562 |

Learning Bayesian Networks with Hidden Variables Using the Combination of EM and Evolutionary Algorithms | 568 |

Interactive Construction of Decision Trees | 575 |

An Improved Learning Algorithm for Augmented Naive Bayes | 581 |

Generalised RBF Networks Trained Using an IBL Algorithm for Mining Symbolic Data | 587 |

594 | |

### Other editions - View all

### Common terms and phrases

analysis applied approach association rule set attributes average Bayesian Bayesian networks Berlin Heidelberg 2001 binary binary relation bit-wise Cheung class association rule classification Computer concept hierarchies concept lattice data mining data sequence data sets database decision tree defined denoted distance document domain efficient encoding equivalence relations error evaluation example experiments extraction feature frequent patterns frequent sequences function G.J. Williams glaucoma graph Hong Kong input Item node itemsets iteration k-NN Knowledge Discovery labeled lattice linear classifiers LNAI Machine Learning matrix maximal measures meta-learning meta-model method neural network optimal PAKDD paper parameter partition performance periodic patterns problem Proc proposed pruning query relation represent retrieval sample Section selection semantic similar similarity matrix spatial Springer-Verlag Berlin Heidelberg structure subset suffix tree support vector machines Table techniques threshold time-series training data transaction tuples values variables vector weight