Driver Fatigue Detection System Using Electroencephalography Signals Based on Combined Entropy Features

• DOI: 10.3390/app7020150
• Publication Date: 2017-02-06T16:29:27Z
• Authors: Zhendong Mu; Jianfeng Hu; Jianliang Min
• Keywords: Sample entropy; Approximate entropy

Driver fatigue has become one of the major causes traffic accidents, and is a complicated physiological process. However, there no effective method to detect driving fatigue. Electroencephalography (EEG) signals are complex, unstable, non-linear; non-linear analysis methods, such as entropy, maybe more appropriate. This study evaluates combined entropy-based processing EEG data driver In this paper, 12 subjects were selected take part in an experiment, obeying training virtual environment under instruction operator. Four types enthrones (spectrum approximate sample entropy fuzzy entropy) used extract features for purpose detection. Electrode selection process support vector machine (SVM) classification algorithm also proposed. The average recognition accuracy was 98.75%. Retrospective showed that extracted from electrodes T5, TP7, TP8 FP1 may yield better performance. SVM using radial basis function kernel obtained results. A demonstrates good performance studying