DREAM European project : Optimisation of food models
Participant : Evelyne Lutton.
In collaboration with Alberto Tonda and Romain Reuillon, ISC-PIF
The overall goal of DREAM (Design and development of REAlistic food Models with well-characterised micro- and macro-structure and composition) is to develop realistic, physical and mathematical models to be used as standards that can be exploited across all major food categories to facilitate development of common approaches to risk assessment and nutritional quality for food research and industry.
The partnership involves 18 partners from 9 european countries, among which two multinationals. The project is lead by INRA, CEPIA department, and INRIA participation is managed by delegation by the ISC-PIF (CNRS-CREA, UMR 7656).
Our contribution to this project is focussed on the evolutionary optimisation of Bayesian Networks models, on the development of efficient cooperative-co-evolution schemes to solve some food modeling problems (milk gel, cheese ripening), and on the efficient visualisation of output data of these algorithms.
Publications:
- Salma Mesmoudi, Nathalie Perrot, Romain Reuillon, Paul Bourgine, and Evelyne Lutton. Optimal viable path search for a cheese ripening process using a multi-objective ea. In ICEC 2010, International Conference on Evolutionary Computation, October 2010. 24-26 oct, Valencia, Spain. pdf
- Olivier Barrière, Evelyne Lutton, and Pierre-Henri Wuillemin. Bayesian network structure learning using cooperative coevolution. In Genetic and Evolutionary Computation Conference (GECCO 2009), 2009. pdf
- Olivier Barrière and Evelyne Lutton. Experimental analysis of a variable size mono-population cooperative-coevolution strategy. In NICSO 2008, International Workshop on Nature Inspired Cooperative Strategies for Optimization,, 2008. Puerto de La Cruz, Tenerife, 12-14 November. pdf