EEG-Based Spatio-Temporal Convolutional Neural Network for Driver Fatigue Evaluation

• Published in: IEEE transaction on neural networks and learning systems Vol. 30; no. 9; pp. 2755 - 2763
• Main Authors: Gao, Zhongke, Wang, Xinmin, Yang, Yuxuan, Mu, Chaoxu, Cai, Qing, Dang, Weidong, Zuo, Siyang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Brain; Brain modeling; Brain–computer interface (BCI); Classification; Computational neuroscience; Convolution; convolutional neural network (CNN); deep learning (DL); Driver fatigue; EEG; electroencephalogram (EEG); Electroencephalography; Evaluation; Fatigue; fatigue driving; Feature extraction; Learning algorithms; Machine learning; Multichannel communication; Neural networks; On-line systems; Physiology; spatio–temporal data; Task analysis; Traffic accidents & safety; Traffic safety
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2018.2886414

Driver fatigue evaluation is of great importance for traffic safety and many intricate factors would exacerbate the difficulty. In this paper, based on the spatial-temporal structure of multichannel electroencephalogram (EEG) signals, we develop a novel EEG-based spatial-temporal convolutional neural network (ESTCNN) to detect driver fatigue. First, we introduce the core block to extract temporal dependencies from EEG signals. Then, we employ dense layers to fuse spatial features and realize classification. The developed network could automatically learn valid features from EEG signals, which outperforms the classical two-step machine learning algorithms. Importantly, we carry out fatigue driving experiments to collect EEG signals from eight subjects being alert and fatigue states. Using 2800 samples under within-subject splitting, we compare the effectiveness of ESTCNN with eight competitive methods. The results indicate that ESTCNN fulfills a better classification accuracy of 97.37% than these compared methods. Furthermore, the spatial-temporal structure of this framework advantages in computational efficiency and reference time, which allows further implementations in the brain-computer interface online systems.