뇌파 분류에 유용한 주성분 특징

EEG-based brain computer interface(BCI) provides a new communication channel between human brain and computer. EEG data is a multivariate time series so that hidden Markov model (HMM) might be a good choice for classification. However EEG is very noisy data and contains artifacts, so useful features are expected to improve the performance of HMM. In this paper we addresses the usefulness of principal component features with hidden Markov model (HMM). We show that some selected principal component features can suppress small noises and artifacts, hence improves classfication performance. Experimental study for the classification of EEG data during imagination of a left, right, up or down hand movement confirms the validity of our proposed method.