DREAM Research team
Diagnosing, Recommending Actions and Modelling
- Leader : Marie-Odile Cordier
- Type : Project team
- Research center(s) : Rennes
- Field : Perception, Cognition, Interaction
- Theme : Knowledge and Data Representation and Management
- Université Rennes 1, Institut national des sciences appliquées de Rennes, Institut de recherche en informatique et systèmes aléatoires (IRISA) (UMR6074)
Team presentationThe main research topics of the DREAM project-team are about aiding monitoring and diagnosis of time evolving systems. The main issue is to infer the state of a system from observations provided by sensors in order to detect and characterize potential anomalies or failures within the system. We use a model-based approach relying on normal and faulty behavioral models. These models are temporal qualitative discrete-event models such as temporal communicating automata, temporal causal graphs or sets of chronicles.
- Automatic model acquisition. We investigate symbolic machine learning techniques such as ILP (Inductive Logic Programming).
- Diagnoser algorithm design and implementation.Relying on model inversion and compilation, these techniques aim at computing compact models which link directly observations to faults. More precisely, we focus on a decentralized and generic approach and on the use of model checking techniques.
- Diagnosis and decision interaction in an uncertain context.
- Cardiac monitoring Electrocardiogram on-line analysis, "intelligent" cardiac devices investigation: pacemakers and defibrillators.
- Environmental protection Improvement of land cover classification from remotely sensed images, qualitative modelling of pollutant (pesticides, nitrates) transfer in groundwater.
- Industrial diagnosis Supervision of telecommunication networks and power distribution systems.
International and industrial relations
- Participating in MONET2, the European Network of Excellence in Model-Based and Qualitative Reasoning Systems (BRIDGE working group).
- Collaborating with ANU (the Australian National University, Canberra). Contact: Sylvie Thiébaux.
- Collaborating with INRA (Institut National de la Recherche Agronomique - National Institute for Agricultural Research) in the Phyto project.
- Participating in the IMALAIA working group.
- Participating in the MAGDA2 project (with R&D/France-telecom, Alcatel, Ilog, university Paris-Nord and the SIGMA2 and TRISKELL projects from IRISA). The project aims at implemeting robust correlation and diagnosis algorithms for telecommunication networks.
- Participating in the PISE project (with LTSI-University of Rennes 1, Rennes University Hospital and Ela Medical) on the design of "intelligent" cardiac devices.
- Participating in the "Medical Advisor" project (with Integrative Biocomputing and the Rennes Medical Informatics Laboratory) on the design of an Intelligent Tutoring System for medical diagnosis in cardiology.
- Collaborating with EDF on industrial prognosis for maintenance.
- Participating in the PROCOPE project.
Research teams of the same theme :
- AXIS - Usage-centered design, analysis and improvement of information systems
- DAHU - Verification in databases
- EXMO - Computer mediated exchange of structured knowledge
- GRAPHIK - GRAPHs for Inferences and Knowledge representation
- LINKS - Linking Dynamic Data
- MAGNET - Machine Learning in Information Networks
- MAIA - Autonomous intelligent machine
- OAK - Database optimizations and architectures for complex large data
- ORPAILLEUR - Knowledge representation, reasonning
- SMIS - Secured and Mobile Information Systems
- TYREX - Types and reasoning for the web
- WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
- ZENITH - Scientific Data Management