Advances in Knowledge Discovery and Management

<div>Part I: Online learning of a weighted selective naive Bayes classifier with&nbsp;non-convex optimization.- On making skyline queries resistant to outliers.- Adaptive Down-Sampling and Dimension Reduction in Time Elastic Kernel Machines for Efficient Recognition of Isolated Gestures.- Exact and Approximate Minimal Pattern Mining.- Part II: Comparison of proximity measures for a topological discrimination.- Comparison of linear modularization criteria using the relational formalism, an approach to easily identify resolution limit.- A novel approach to feature selection based on quality estimation metrics.- Ultrametricity of Dissimilarity Spaces and Its Significance for Data Mining.- Part III: SMERA: Semantic Mixed Approach for Web Query Expansion and Reformulation.- Multi-layer ontologies for integrated 3D shape segmentation and annotation.- Ontology Alignment Using Web Linked Ontologies as Background Knowledge.- LIAISON: reconciLIAtion of Individuals profiles across SOcial&nbsp;Networks.- Clustering of Links and Clustering of Nodes: Fusion of Knowledge in&nbsp;Social Networks</div>