Classifying neuro-biological signals by evolutionary fuzzy classifier construction
Min-Soeng Kim, Chang-Hyun Kim, Ju-Jang Lee · Society of Instrument and Control Engineers of Japan · 2004
In this research, EOG (electrooculogram) signal was analyzed to predict a subject's intention using a fuzzy classifier. The fuzzy classifier was built automatically based on EOG data by evolutionary algorithm. For automatic fuzzy classifier construction without any experts' knowledge, a new evolutionary algorithm is proposed. A new representation scheme, a new fitness function and adequate evolutionary operators were designed for the proposed evolutionary algorithm. The proposed evolutionary algorithm can optimize the number of fuzzy rules, the number of fuzzy membership functions, parameter values for the each membership functions, and parameter values for the consequent parts, simultaneously. It is shown that the fuzzy classifier built by the proposed algorithm can classify the given EOG data efficiently. As consequence, the fuzzy classifier can recognize the intention of a human subject.