EEG feature extraction and analysis under drowsy state based on energy and sample entropy

Abstract

In order to explore the effect of drowsiness on Electroencephalogram (EEG), EEG signals with bipolar lead C4-P4 are collected from 15 healthy subjects. There are six energy features and six sample entropy features of EEG signals under conscious and drowsy states extracted respectively. The study results show that the energy under drowsy state increase obviously while the sample entropy under drowsy state decrease obviously compare with those under conscious state (p<;0.05), it offers a new method for drowsiness detection based on EEG.