Présentation de l'équipe

We address research issues dealing with data processing and management, especially clustering and derived research tracks : summarization, clustering, data integration, indexing and retrieval, querying, ensemble clustering . Specificities of our work : We focus on specific data types or representations : data is represented by parametric models of data sets (specifically fuzzy sets or probabilistic models), or/and spans a high dimension space. Motivations include retrieval of queries (esp. knn) in metric spaces and data clustering strategies for optimizing parallelism data publication and open data, privacy w.r.t. sensitive personal data (k-anonymity, differential privacy), integration of multiple probabilistic models (esp. mixture/mixed-membership models).