Binary social impact theory based optimization and its applications in pattern recognition

The human opinion formation can be understood as a social approach to optimization. In the real world, the opinions on different issues encode a “candidate solution”, which is evaluated by a complex and unknown fitness function. The computer models of such processes can be easily modified by introducing a fitness value, which leads to novel family of optimization techniques. This paper demonstrates how the novel algorithms can be derived from opinion formation models and empirically demonstrates their usability in the area of binary optimization. Particularly, it introduces a general SITO algorithmic framework and describes four algorithms based on this general framework. Recent applications of these algorithms to pattern recognition in electronic nose, electronic tongue, new born EEG and ICU patient mortality prediction are discussed. Finally, an open source SITO library for MATLAB and JAVA is introduced.