Application of genetic programming and genetic algorithm in evolving emotion recognition module

This paper will discuss about implementation of a voting system and weighted credibility to augment evolution process of an emotion recognition module. The evolution process of the emotion recognition module is one part of ongoing research on designing an intelligent agent capable of emotion recognition, interaction, and expression. Genetic programming evolves the classifiers, while genetic algorithm evolves the weighted credibility as a modification of parallel voting systems. The experimental results suggest that the implementation of weighted credibility evolution improves the performance of training, in the form of significantly reduced training time needed.