Shuli Zou1, Taorong Qiu2, Peifan Huang1, Xiaoming Bai1, Chao Liu1. 1. Department of Computer, Nanchang University, Nanchang, Jiangxi 330029, China. 2. Department of Computer, Nanchang University, Nanchang, Jiangxi 330029, China. Electronic address: qiutaorong@ncu.edu.cn.
Abstract
BACKGROUND: Fatigue is one of the important factors in traffic accidents. Hence, it is necessary to devise methods to detect the fatigue and apply practical fatigue detection solutions for drivers. NEW METHOD: This paper presents a method based on the empirical mode decomposition(EMD) of multi-scale entropy on the recorded forehead Electroencephalogram(EEG) signals. These EEG signals are decomposed to extract intrinsic mode functions(IMFs) by using the EMD technique. Then, the IMFs components are selected out by using the Pearson correlation coefficient and the best scale features on each signal are determined in multiple experiments. RESULTS: Results indicate that the empirical mode decomposition multi-scale fuzzy entropy feature classification recognition rate is up to 87.50%, the highest is 88.74%, which is 23.88% higher than the single-scale fuzzy entropy and 5.56% higher than multi-scale fuzzy entropy. COMPARISON WITH EXISTING METHOD: Three types of entropies measures, permutation entropy(PE), sample entropy(SE), fuzzy entropy(FE), were applied for the analysis of signal and compared by seven classifiers in 10-fold and Leave-One-Out cross-validation experiments. CONCLUSIONS: The proposed method can be effectively applied to the detection of driving fatigue.
BACKGROUND:Fatigue is one of the important factors in traffic accidents. Hence, it is necessary to devise methods to detect the fatigue and apply practical fatigue detection solutions for drivers. NEW METHOD: This paper presents a method based on the empirical mode decomposition(EMD) of multi-scale entropy on the recorded forehead Electroencephalogram(EEG) signals. These EEG signals are decomposed to extract intrinsic mode functions(IMFs) by using the EMD technique. Then, the IMFs components are selected out by using the Pearson correlation coefficient and the best scale features on each signal are determined in multiple experiments. RESULTS: Results indicate that the empirical mode decomposition multi-scale fuzzy entropy feature classification recognition rate is up to 87.50%, the highest is 88.74%, which is 23.88% higher than the single-scale fuzzy entropy and 5.56% higher than multi-scale fuzzy entropy. COMPARISON WITH EXISTING METHOD: Three types of entropies measures, permutation entropy(PE), sample entropy(SE), fuzzy entropy(FE), were applied for the analysis of signal and compared by seven classifiers in 10-fold and Leave-One-Out cross-validation experiments. CONCLUSIONS: The proposed method can be effectively applied to the detection of driving fatigue.