Emerging Trends in Knowledge Discovery and Data Mining : PAKDD 2012 International Workshops: DMHM, GeoDoc, 3Clust, and DSDM, Kuala Lumpur, Malaysia, May 29 -- June 1, 2012, Revised Selected Papers

This book constitutes the thoroughly refereed proceedings of the PAKDD 2012 International Workshops: Third Workshop on Data Mining for Healthcare Management (DMHM 2012), First Workshop on Geospatial Information and Documents (GeoDoc 2012), First Workshop on Multi-view data, High-dimensionality, External Knowledge: Striving for a Unified Approach to Clustering (3Clust 2012), and the Second Doctoral Symposium on Data Mining (DSDM 2012); held in conjunction with the 16th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2012), in Kuala Lumpur, Malaysia, May/June 2012. The 12 revised papers presented were carefully reviewed and selected from numerous submissions. DMHM 2012 aimed at providing a common platform for the discussion of challenging issues and potential techniques in this emerging field of data mining for health care management; 3Clust 2012 focused on solving emerging problems such as clustering ensembles, semi-supervised clustering, subspace/projective clustering, co-clustering, and multi-view clustering; GeoDoc 2012 highlighted the formalization of geospatial concepts and relationships with a focus on the extraction of geospatial relations in free text datasets to offer to the database community a unified framework for geodata discovery; and DSDM 2012 provided the opportunity for Ph.D. students and junior researchers to discuss their work on data mining foundations, techniques and applications. This book constitutes the thoroughly refereed proceedings of the PAKDD 2012 International Workshops: Third Workshop on Data Mining for Healthcare Management (DMHM 2012), First Workshop on Geospatial Information and Documents (GeoDoc 2012), First Workshop on Multi-view data, High-dimensionality, External Knowledge: Striving for a Unified Approach to Clustering (3Clust 2012), and the Second Doctoral Symposium on Data Mining (DSDM 2012); held in conjunction with the 16th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2012), in Kuala Lumpur, Malaysia, May/June 2012. The 12 revised papers presented were carefully reviewed and selected from numerous submissions. DMHM 2012 aimed at providing a common platform for the discussion of challenging issues and potential techniques in this emerging field of data mining for health care management; 3Clust 2012 focused on solving emerging problems such as clustering ensembles, semi-supervised clustering, subspace/projective clustering, co-clustering, and multi-view clustering; GeoDoc 2012 highlighted the formalization of geospatial concepts and relationships with a focus on the extraction of geospatial relations in free text datasets to offer to the database community a unified framework for geodata discovery; and DSDM 2012 provided the opportunity for Ph. D. students and junior researchers to discuss their work on data mining foundations, techniques and applications Front Matter....Pages - Modality Classification for Medical Images Using Sparse Coded Affine-Invariant Descriptors....Pages 1-10 Mining Web Data for Epidemiological Surveillance....Pages 11-21 Getting a Grasp on Clinical Pathway Data: An Approach Based on Process Mining....Pages 22-35 ALIVE: A Multi-relational Link Prediction Environment for the Healthcare Domain....Pages 36-46 The Relevance of Spatial Relation Terms and Geographical Feature Types....Pages 47-56 Applying NLP Techniques for Query Reformulation to Information Retrieval with Geographical References....Pages 57-69 Adaptive Evidence Accumulation Clustering Using the Confidence of the Objects’ Assignments....Pages 70-87 An Explicit Description of the Extended Gaussian Kernel....Pages 88-99 An Improved Genetic Clustering Algorithm for Categorical Data....Pages 100-111 Instance-Ranking: A New Perspective to Consider the Instance Dependency for Classification....Pages 112-123 Triangular Kernel Nearest-Neighbor-Based Clustering Algorithm for Discovering True Clusters....Pages 124-140 DisClose : Dis covering Colossal Close d Itemsets via a Memory Efficient Compact Row-Tree....Pages 141-156 Back Matter....Pages -