End-to-end fatigue driving EEG signal detection model based on improved temporal-graph convolution network

• Published in: Computers in biology and medicine Vol. 152; p. 106431
• Main Authors: Jia, Huijie, Xiao, Zhongjun, Ji, Peng
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2023; Elsevier Limited
• Subjects: Accidents, Traffic; Accuracy; Algorithms; Artificial neural networks; Automobile Driving; Driver fatigue; EEG; EEG signals; Electrodes; Electroencephalography; End-to-end; Fatigue; Fatigue driving detection; Feature extraction; Humans; Information technology; Internal Medicine; Modules; Multi-scale attention; Neural networks; Other; Physiology; Signal detection; Signal processing; Traffic accidents; Traffic safety; Transformer; Fatigue driving detection; EEG signals; Transformer; Multi-scale attention; End-to-end
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106431

Fatigue driving is one of the leading causes of traffic accidents, so fatigue driving detection technology plays a crucial role in road safety. The physiological information-based fatigue detection methods have the advantage of objectivity and accuracy. Among many physiological signals, EEG signals are considered to be the most direct and promising ones. Most traditional methods are challenging to train and do not meet real-time requirements. To this end, we propose an end-to-end temporal and graph convolution-based (MATCN-GT) fatigue driving detection algorithm. The MATCN-GT model consists of a multi-scale attentional temporal convolutional neural network block (MATCN block) and a graph convolutional-Transformer block (GT block). Among them, the MATCN block extracts features directly from the original EEG signal without a priori information, and the GT block processes the features of EEG signals between different electrodes. In addition, we design a multi-scale attention module to ensure that valuable information on electrode correlations will not be lost. We add a Transformer module to the graph convolutional network, which can better capture the dependencies between long-distance electrodes. We conduct experiments on the public dataset SEED-VIG, and the accuracy of the MATCN-GT model reached 93.67%, outperforming existing algorithms. Furthermore, compared with the traditional graph convolutional neural network, the GT block has improved the accuracy rate by 3.25%. The accuracy of the MATCN block on different subjects is higher than the existing feature extraction methods. [Display omitted] •We propose an EEG signal detection model (MATCN-GT) that can achieve end-to-end fatigue driving detection.•We propose a multi-scale attention temporal convolutional network block (MATCN Block) to extract the raw EEG signal features.•We designed a graph convolution neural network-Transformer block (GT Block) to learn the internal structure information of EEG signals.•We test on the public dataset SEED-VIG and the accuracy of MATCN-GT is higher than that of the state-of-the-art model.