EEG Channel Selection Using A Modified Grey Wolf Optimizer

Consider an increasingly growing field of research, Brain-Computer Interface (BCI) is to form a direct channel communication between computer and the brain. However, extracting features random time-varying EEG signals their classification major challenge that faces current BCI. This paper proposes modified grey wolf optimizer (MGWO) can select optimal channels be used in (BCIs), way identifies main immaterial ones from dataset complexity removed. allows opt for as well helping machine learning its tasks when doing training classifier with dataset. (MGWO), which imitates wolves leadership hunting manner nature consider metaheuristics swarm intelligence algorithms, integration two modification achieve balance exploration exploitation first applies exponential change number iterations increase search space accordingly exploitation, second crossover operation diversity population enhance capability. Experimental results use four different datasets BCI Competition IV- 2a, data set III, II Eye State UCI Machine Learning Repository evaluate quality effectiveness (MGWO). A cross-validation method measure stability