Genetic learning of fuzzy integrals accumulating human-reported environmental stress
Parameter adjustment of a fusion system for 3D image interpretation is often a difficult task that is emphasized by the non understandability of the parameters by the end-users. Moreover, such fusion systems are complex because they involve a complete information treatment chain (from the information extraction to the decision). The sub-parts of the system concern also different scientific areas which add some additional difficulties. Some parameters cannot be easily set empirically and their adjustments are made by trials and errors. This paper studies an optimization of a generalized Choquet Integral parameters by means of genetic algorithms. Fuzzy measures are first learnt thanks to the reference data given by experts and then the best importance coefficients are searched around the initial ones. The approach is illustrated on a cooperative fusion system based on Choquet Integral and devoted to 3D image interpretation.