Classification of Cognitive Mental States for Brain Wave based Human-Computer Interface

뇌파기반 휴먼-컴퓨터 인터페이스를 위한 인지적 정신상태의 분별

This paper describes a basic study for the classification of cognitive mental states as a basic research of a human-computer interface technique. To recognize the mental states, we obtained 22 subjects’brain waves in course of two types of experiments. One of the experiments is to choose an answer among yes, no or reject buttons, to underlying questions and the other is to select an icon displayed in a monitor screen. After acquiring the brain wave signals, we construct a feature set with the percent power increase for a given segment with respect to that of the reference period. The linear discriminative algorithm is used to classify the cognitive yes/no mental states.