Estimate vigilance level in driving simulation based on sparse representation

摘要

Avoiding fatal accidents caused by low vigilance level in driving is very important in our daily lives. Electroen-cephalography(EEG) has been proved very effective for measuring the level of vigilance. In this paper, we distin­guish vigilance level into three classes which are ''alert'', ''fatigue'' and ''sleeping'' by using sparse representation classiflcation(SRC). Six features from each frequency band are got from samples of EEG data. Random fea­ture is used to reduce the dimension of features. Actu­ally there is almost no training process before the clas­sification. The accuracy in classification of three classes reaches about 90% on average.