Evolutionary Algorithms for Food Science and Technology

3Model Analysis and Visualization

Obtaining reliable in silico food models is fundamental for a better understanding of these systems. The complex phenomena involved in these real-world processes are reflected in the intricate structure of models, so that thoroughly exploring their behavior and, for example, finding meaningful correlations between variables has become a relevant challenge for the experts. In this chapter, we present a methodology based on visualization and evolutionary computation to assist experts during model exploration. The proposed approach is tested on an established model of milk gel structures, and we show how experts are eventually able to find a correlation between two parameters, previously considered independent. Reverse engineering the final outcome, the emergence of such a pattern is proved by the physical laws underlying the oil–water interface colonization. It is interesting to note that, while the present work is focused on milk gel modeling, the proposed methodology can be straightforwardly generalized to other complex physical phenomena. The work described in this chapter has been done with Sébastien Gaucel, Julie Foucquier and Alain Riaublanc and published in [LUT 14b].

3.1. Introduction

Building in silico models for food processes is an important but difficult task, as there are various known bottlenecks [PER 11]. The process of model design, for instance, often relies on computationally-expensive optimizations to match a theoretical model ...