Optimal imaging of multi-channel EEG features based on a novel clustering technique for driver fatigue detection. (September 2020)

• Record Type: Journal Article
• Authors: Zhang, Chi; Sun, Lina; Cong, Fengyu; Kujala, Tuomo; Ristaniemi, Tapani; Parviainen, Tiina
• Is Part Of: Biomedical signal processing and control. Volume 62(2020)
• Publication Date: 2020-09
• Subjects: Fatigue detection -- EEG -- Signal processing -- Brain network -- Clustering; 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.2020.102103
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A driver fatigue detection method based on brain network clustering is proposed. System performance is improved while considering effective spatial information. EEG data with fatigue and accidents are used to evaluate the proposed method. Most Fatigue was detected before accidents and subjective feelings of fatigue. Abstract: Fatigue may cause a decrease in mental and physical performance capacity, which is a serious safety risk for the drivers in the transportation system. Recently, various studies have demonstrated the deviations of electroencephalogram (EEG) indicators from normal vigilant state during fatigue in time and frequency domains. However, when considering spatial information, these feature descriptors are not satisfying the demand for reliable detection due to the well-known challenge of signal mixing. In this paper, we propose a novel approach based on clustering on brain networks (CBNs) to alleviate the problem to improve the performance of driver fatigue detection. The clustering algorithm was employed to extract the spatial nodes with distinct connectivity attributes throughout the EEG-based brain networks. Then, the temporal features of wavelet entropy from the extracted nodes were transformed to spatio-temporal images so that the image edge detection method (pulse-coupled neural networks) to distinguish different stages of fatigue can be used. The experimental results demonstrated the temporal features from the extracted nodes reduced signal mixing and showed clearer deviations. The detected fatigue based on the imaging method was to an extent consistent with self-reported subjective feelings and most of the critical fatigue was detected before the subjective feelings of fatigue. For all the subjects, 21 of 29 accidents happened after detected fatigue in the simulated driving task. Therefore, the proposed method owns potential value for early warning and avoidance of traffic accidents caused by driver fatigue.