Evolutionary Algorithms for Food Science and Technology

5Modeling Human Expertise Using Genetic Programming

Co-operative–co-evolution techniques (CCEAs, also called “Parisian” approaches) actually allow us to represent the searched solution as an aggregation of several individuals (or even as a whole population), as each individual only bears a part of the solution searched. This scheme allows us to use artificial Darwinism principles in a more economic way, and the gain in terms of robustness and efficiency is important. In this chapter, we present two experiments related to the modeling of an industrial agrifood process, where cooperative–co-evolution techniques have proven successful. Experiments have focused on a specific problem: the modeling of a Camembert cheese ripening process. Two related complex optimization problems have been considered:

• – a deterministic modeling problem, the phase prediction problem for which a search for a closed form tree expression has been performed using genetic programming (GP). This part of the study has been performed in collaboration with Olivier Barrière, Cédric Baudrit, Mariette Sicard and Bruno Pinaud;
• – a Bayesian network (BN) structure estimation problem, considered as a two-stage problem, i.e. searching first for an approximation of an independence model (IM) using evolutionary algorithms (EAs), and then deducing, via a deterministic algorithm, a BN that represents the equivalence class of the IM found at the first stage. This part of the study was performed in collaboration with Olivier ...