Advances in Knowledge Discovery and Data Mining, Part I

14th Pacific-Asia Conference, PAKDD 2010, Hyderabat, India, June 21-24, 2010, Proceedings
Buch | Softcover
506 Seiten
2010 | 2010
Springer Berlin (Verlag)
978-3-642-13656-6 (ISBN)
112,34 inkl. MwSt
The14thPaci?c-AsiaConferenceonKnowledgeDiscoveryandData Mining was held in Hyderabad, India during June 21 24, 2010; this was the ?rst time the conference was held in India. PAKDDisamajorinternationalconferenceintheareasofdatamining (DM) and knowledge discovery in databases (KDD). It provides an international - rum for researchers and industry practitioners to share their 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 and automatic scienti?c discovery, data visu- ization, causal induction and knowledge-based systems. PAKDD-2010 received 412 research papers from over 34 countries incl- ing: Australia,Austria,Belgium, Canada,China, Cuba, Egypt,Finland, France, Germany, Greece, Hong Kong, India, Iran, Italy, Japan, S. Korea, Malaysia, Mexico,TheNetherlands,NewCaledonia,NewZealand,SanMarino,Singapore, Slovenia,Spain, Switzerland, Taiwan, Thailand, Tunisia, Turkey, UK, USA, and Vietnam. This clearly re?ects the truly international stature of the PAKDD conference. AfteraninitialscreeningofthepapersbytheProgramCommitteeChairs,for papers that did not conform to the submission guidelines or that were deemed not worthy of further reviews, 60 papers were rejected with a brief expla- tion for the decision. The remaining 352 papers were rigorously reviewed by at least three reviewers. The initial results were discussed among the reviewers and ?nally judged by the Program Committee Chairs. In some cases of c- ?ict additional reviews were sought. As a result of the deliberation process, only 42 papers (10.2%) were accepted as long presentations (25 mins), and an ad- tional 55 papers (13.3%) were accepted as short presentations (15 mins). The total acceptance rate was thus about 23.5% across both categories.

Keynote Speeches.- Empower People with Knowledge: The Next Frontier for Web Search.- Discovery of Patterns in Global Earth Science Data Using Data Mining.- Game Theoretic Approaches to Knowledge Discovery and Data Mining.- Session 1A. Clustering I.- A Set Correlation Model for Partitional Clustering.- iVAT and aVAT: Enhanced Visual Analysis for Cluster Tendency Assessment.- A Robust Seedless Algorithm for Correlation Clustering.- Integrative Parameter-Free Clustering of Data with Mixed Type Attributes.- Data Transformation for Sum Squared Residue.- Session 1B. Social Networks.- A Better Strategy of Discovering Link-Pattern Based Communities by Classical Clustering Methods.- Mining Antagonistic Communities from Social Networks.- As Time Goes by: Discovering Eras in Evolving Social Networks.- Online Sampling of High Centrality Individuals in Social Networks.- Estimate on Expectation for Influence Maximization in Social Networks.- Session 1C. Classification I.- A Novel Scalable Multi-class ROC for Effective Visualization and Computation.- Efficiently Finding the Best Parameter for the Emerging Pattern-Based Classifier PCL.- Rough Margin Based Core Vector Machine.- BoostML: An Adaptive Metric Learning for Nearest Neighbor Classification.- A New Emerging Pattern Mining Algorithm and Its Application in Supervised Classification.- Session 2A. Privacy.- Hiding Emerging Patterns with Local Recoding Generalization.- Anonymizing Transaction Data by Integrating Suppression and Generalization.- Satisfying Privacy Requirements: One Step before Anonymization.- Computation of Ratios of Secure Summations in Multi-party Privacy-Preserving Latent Dirichlet Allocation.- Privacy-Preserving Network Aggregation.- Multivariate Equi-width Data Swapping for Private Data Publication.- Session 2B.Spatio-Temporal Mining.- Correspondence Clustering: An Approach to Cluster Multiple Related Spatial Datasets.- Mining Trajectory Corridors Using Fréchet Distance and Meshing Grids.- Subseries Join: A Similarity-Based Time Series Match Approach.- TWave: High-Order Analysis of Spatiotemporal Data.- Spatial Clustering with Obstacles Constraints by Dynamic Piecewise-Mapped and Nonlinear Inertia Weights PSO.- Session 3A. Pattern Mining.- An Efficient GA-Based Algorithm for Mining Negative Sequential Patterns.- Valency Based Weighted Association Rule Mining.- Ranking Sequential Patterns with Respect to Significance.- Mining Association Rules in Long Sequences.- Mining Closed Episodes from Event Sequences Efficiently.- Most Significant Substring Mining Based on Chi-square Measure.- Session 3B. Recommendations/Answers.- Probabilistic User Modeling in the Presence of Drifting Concepts.- Using Association Rules to Solve the Cold-Start Problem in Recommender Systems.- Semi-supervised Tag Recommendation - Using Untagged Resources to Mitigate Cold-Start Problems.- Cost-Sensitive Listwise Ranking Approach.- Mining Wikipedia and Yahoo! Answers for Question Expansion in Opinion QA.- Answer Diversification for Complex Question Answering on the Web.- Vocabulary Filtering for Term Weighting in Archived Question Search.- Session 3C. Topic Modeling/Information Extraction.- On Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations.- Supervising Latent Topic Model for Maximum-Margin Text Classification and Regression.- Resource-Bounded Information Extraction: Acquiring Missing Feature Values on Demand.- Efficient Deep Web Crawling Using Reinforcement Learning.- Topic Decomposition and Summarization.- Session 4A. Skylines/Uncertainty.- UNN: A Neural Networkfor Uncertain Data Classification.- SkyDist: Data Mining on Skyline Objects.- Multi-Source Skyline Queries Processing in Multi-Dimensional Space.- Efficient Pattern Mining of Uncertain Data with Sampling.- Classifier Ensemble for Uncertain Data Stream Classification.

Erscheint lt. Verlag 1.6.2010
Reihe/Serie Lecture Notes in Artificial Intelligence
Lecture Notes in Computer Science
Zusatzinfo 506 p. 167 illus.
Verlagsort Berlin
Sprache englisch
Themenwelt Informatik Datenbanken Data Warehouse / Data Mining
Schlagworte Algorithm analysis and problem complexity • Bioinformatics • classification • Clustering • Data Mining • Distributed data mining • fractal representation • graph analysis • Knowledge Discovery
ISBN-10 3-642-13656-7 / 3642136567
ISBN-13 978-3-642-13656-6 / 9783642136566
Zustand Neuware
Haben Sie eine Frage zum Produkt?
Mehr entdecken
aus dem Bereich
Datenanalyse für Künstliche Intelligenz

von Jürgen Cleve; Uwe Lämmel

Buch | Softcover (2024)
De Gruyter Oldenbourg (Verlag)
74,95
Auswertung von Daten mit pandas, NumPy und IPython

von Wes McKinney

Buch | Softcover (2023)
O'Reilly (Verlag)
44,90