Research on fatigue driving detection using forehead EEG based on adaptive multi-scale entropy. (May 2019)

• Record Type: Journal Article
• Authors: Luo, Haowen; Qiu, Taorong; Liu, Chao; Huang, Peifan
• Is Part Of: Biomedical signal processing and control. Volume 51(2019)
• Page Start: 50
• Page End: 58
• Publication Date: 2019-05
• Subjects: Driving fatigue -- Forehead EEG signal -- Adaptive scale -- Multi-scale entropy; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.02.005
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: An adaptive scaling factor method based on k -means algorithm is proposed. Different genders have an impact on fatigue driving detection. Adaptive multi-scale entropy has higher accuracy than single-scale entropy. The accuracy of fatigue driving detection based on the forehead reached 95.37%. The effectiveness of the method was verified by the epileptic dataset. Abstract: Fatigue driving is one of the main factors that causes traffic accidents. In the current non-linear analysis methods, the entropy feature extraction methods can be well applied to detection of driving fatigue. However, all of these methods analyzed the EEG data on a single scale signal and there is also no effective way to determine the signal multi-scale information. In addition, most of the current researches choose all the electrodes, which is not conducive to practical application. Based on the forehead EEG data, an adaptive multi-scale entropy feature extraction algorithm is proposed by combining with an adaptive scaling factor (ASF) obtaining algorithm and entropy feature extraction method. Firstly, ASF algorithm is used to extract the scale factor of the signal. Secondly, this factor is used to reconstruct the signal to get new signal data. Finally, the entropy features are extracted for classification. The experimental results show that the proposed adaptive multi-scale entropy feature algorithm is effective in the detection of fatigue driving based on using forehead EEG data. So the effectiveness of this feature extraction algorithm is proved.