Title: Bipartite graphs for multimodal/multisource investigation
Speaker: Andrea Marinoni, Univeristy of Pavia, Italy (http://tlclab.unipv.it/sito_tlc/people.do?id=amarinoni)
Abstract:
Nonlinear investigation has recently become an interesting topic in Earth observation data management and analysis, since it can provide important information on hidden interactions and correlations among the considered data records. Although several methods have been proposed and implemented to efficiently extract a proper set of features and deliver accurate image exploration, classification and segmentation, these architectures show drawbacks when the datasets are characterized by complex interactions among the samples. In this presentation, a new approach based on hypergeometric analysis for automatic pattern recognition is introduced for accurate classification of remotely sensed data. Specifically, methods for automatic learning based on information theory, bipartite graph-based data driven discovery, multimodal and multisource investigation, as well as non-Euclidean geometry representation will be presented. Finally, the challenges and opportunities of this data analysis line are discussed.
When and where: wednesday, january 31, 2pm in room Chartreuse, GIPSA-lab/DIS, Grenoble