Ebook: Advanced Data Mining and Applications: Third International Conference, ADMA 2007 Harbin, China, August 6-8, 2007. Proceedings

The Third International Conference on Advanced Data Mining and Applications (ADMA) organized in Harbin, China continued the tradition already established by the first two ADMA conferences in Wuhan in 2005 and Xi’an in 2006. One major goal of ADMA is to create a respectable identity in the data mining research com- nity. This feat has been partially achieved in a very short time despite the young age of the conference, thanks to the rigorous review process insisted upon, the outstanding list of internationally renowned keynote speakers and the excellent program each year. The impact of a conference is measured by the citations the conference papers receive. Some have used this measure to rank conferences. For example, the independent source cs-conference-ranking.org ranks ADMA (0.65) higher than PAKDD (0.64) and PKDD (0.62) as of June 2007, which are well established conferences in data mining. While the ranking itself is questionable because the exact procedure is not disclosed, it is nevertheless an encouraging indicator of recognition for a very young conference such as ADMA.

---

This book constitutes the refereed proceedings of the Third International Conference on Advanced Data Mining and Applications, ADMA 2007, held in Harbin, China in August 2007.

The 44 revised full papers and 15 revised short papers presented together with the abstract of one invited lecture were carefully reviewed and selected from about 200 submissions. The papers focus on advancements in data mining and peculiarities and challenges of real world applications using data mining. The major theme of the conference encompasses the innovative applications of data mining approaches to real-world problems that involve large data sets, incomplete and noisy data, or demand optimal solutions.

---

This book constitutes the refereed proceedings of the Third International Conference on Advanced Data Mining and Applications, ADMA 2007, held in Harbin, China in August 2007.

The 44 revised full papers and 15 revised short papers presented together with the abstract of one invited lecture were carefully reviewed and selected from about 200 submissions. The papers focus on advancements in data mining and peculiarities and challenges of real world applications using data mining. The major theme of the conference encompasses the innovative applications of data mining approaches to real-world problems that involve large data sets, incomplete and noisy data, or demand optimal solutions.

Content:
Front Matter....Pages -
Mining Ambiguous Data with Multi-instance Multi-label Representation....Pages 1-1
Exploring Content and Linkage Structures for Searching Relevant Web Pages....Pages 2-14
CLBCRA-Approach for Combination of Content-Based and Link-Based Ranking in Web Search....Pages 15-22
Rough Sets in Hybrid Soft Computing Systems....Pages 23-34
Discovering Novel Multistage Attack Strategies....Pages 35-44
Privacy Preserving DBSCAN Algorithm for Clustering....Pages 45-56
A New Multi-level Algorithm Based on Particle Swarm Optimization for Bisecting Graph....Pages 57-68
A Supervised Subspace Learning Algorithm: Supervised Neighborhood Preserving Embedding....Pages 69-80
A k-Anonymity Clustering Method for Effective Data Privacy Preservation....Pages 81-88
LSSVM with Fuzzy Pre-processing Model Based Aero Engine Data Mining Technology....Pages 89-99
A Coding Hierarchy Computing Based Clustering Algorithm....Pages 100-109
Mining Both Positive and Negative Association Rules from Frequent and Infrequent Itemsets....Pages 110-121
Survey of Improving Naive Bayes for Classification....Pages 122-133
Privacy Preserving BIRCH Algorithm for Clustering over Arbitrarily Partitioned Databases....Pages 134-145
Unsupervised Outlier Detection in Sensor Networks Using Aggregation Tree....Pages 146-157
Separator: Sifting Hierarchical Heavy Hitters Accurately from Data Streams....Pages 158-169
Spatial Fuzzy Clustering Using Varying Coefficients....Pages 170-182
Collaborative Target Classification for Image Recognition in Wireless Sensor Networks....Pages 183-190
Dimensionality Reduction for Mass Spectrometry Data....Pages 191-202
The Study of Dynamic Aggregation of Relational Attributes on Relational Data Mining....Pages 203-213
Learning Optimal Kernel from Distance Metric in Twin Kernel Embedding for Dimensionality Reduction and Visualization of Fingerprints....Pages 214-226
Efficiently Monitoring Nearest Neighbors to a Moving Object....Pages 227-238
A Novel Text Classification Approach Based on Enhanced Association Rule....Pages 239-251
Inference of Gene Regulatory Network by Bayesian Network Using Metropolis-Hastings Algorithm....Pages 252-263
A Consensus Recommender for Web Users....Pages 264-275
Constructing Classification Rules Based on SVR and Its Derivative Characteristics....Pages 276-286
Hiding Sensitive Associative Classification Rule by Data Reduction....Pages 287-299
AOG-ags Algorithms and Applications....Pages 300-309
A Framework for Titled Document Categorization with Modified Multinomial Naivebayes Classifier....Pages 310-322
Prediction of Protein Subcellular Locations by Combining K-Local Hyperplane Distance Nearest Neighbor....Pages 323-334
A Similarity Retrieval Method in Brain Image Sequence Database....Pages 335-344
A Criterion for Learning the Data-Dependent Kernel for Classification....Pages 345-351
Topic Extraction with AGAPE....Pages 352-364
Clustering Massive Text Data Streams by Semantic Smoothing Model....Pages 365-376
A Novel Greedy Bayesian Network Structure Learning Algorithm for Limited Data....Pages 377-388
Optimum Neural Network Construction Via Linear Programming Minimum Sphere Set Covering....Pages 389-400
How Investigative Data Mining Can Help Intelligence Agencies to Discover Dependence of Nodes in Terrorist Networks....Pages 401-411
Prediction of Enzyme Class by Using Reactive Motifs Generated from Binding and Catalytic Sites....Pages 412-421
Bayesian Network Structure Ensemble Learning....Pages 422-429
Fusion of Palmprint and Iris for Personal Authentication....Pages 430-441
Enhanced Graph Based Genealogical Record Linkage....Pages 442-453
A Fuzzy Comprehensive Clustering Method....Pages 454-465
CACS: A Novel Classification Algorithm Based on Concept Similarity....Pages 466-475
Data Mining in Tourism Demand Analysis: A Retrospective Analysis....Pages 476-487
Chinese Patent Mining Based on Sememe Statistics and Key-Phrase Extraction....Pages 488-499
Classification of Business Travelers Using SVMs Combined with Kernel Principal Component Analysis....Pages 500-507
Research on the Traffic Matrix Based on Sampling Model....Pages 508-515
A Causal Analysis for the Expenditure Data of Business Travelers....Pages 516-523
A Visual and Interactive Data Exploration Method for Large Data Sets and Clustering....Pages 524-532
Explorative Data Mining on Stock Data – Experimental Results and Findings....Pages 533-544
Graph Structural Mining in Terrorist Networks....Pages 545-552
Characterizing Pseudobase and Predicting RNA Secondary Structure with Simple H-Type Pseudoknots Based on Dynamic Programming....Pages 553-561
Locally Discriminant Projection with Kernels for Feature Extraction....Pages 562-569
A GA-Based Feature Subset Selection and Parameter Optimization of Support Vector Machine for Content – Based Image Retrieval....Pages 570-577
E-Stream: Evolution-Based Technique for Stream Clustering....Pages 578-585
H-BayesClust: A New Hierarchical Clustering Based on Bayesian Networks....Pages 586-593
An Improved AdaBoost Algorithm Based on Adaptive Weight Adjusting....Pages 594-604
Back Matter....Pages 605-615
....Pages 616-624