1. A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG
- Author
-
Olga Sourina, Jian Cui, Fan Li, Yisi Liu, Ruilin Li, Zirui Lan, Wolfgang Müller-Wittig, Fraunhofer Singapore, and Publica
- Subjects
Signal Processing (eess.SP) ,FOS: Computer and information sciences ,Computer Science - Machine Learning ,Single-Channel EEG ,Channel (digital image) ,Computer science ,Pooling ,Computer Science - Human-Computer Interaction ,Convolutional Neural Network ,Electroencephalography ,Convolutional neural network ,Signal ,General Biochemistry, Genetics and Molecular Biology ,Human-Computer Interaction (cs.HC) ,Machine Learning (cs.LG) ,Machine Learning ,03 medical and health sciences ,FOS: Electrical engineering, electronic engineering, information engineering ,medicine ,Humans ,Neural and Evolutionary Computing (cs.NE) ,Electrical Engineering and Systems Science - Signal Processing ,Electroencephalography (EEG) ,Wakefulness ,Molecular Biology ,030304 developmental biology ,0303 health sciences ,medicine.diagnostic_test ,business.industry ,Deep learning ,030302 biochemistry & molecular biology ,network visualization ,Biological sciences::Human anatomy and physiology [Science] ,Computer Science - Neural and Evolutionary Computing ,Pattern recognition ,Driver Drowsiness Detection ,Neurophysiology ,Visualization ,Convolutional Neural Networks (CNN) ,Computer science and engineering [Engineering] ,Neural Networks, Computer ,Artificial intelligence ,Artifacts ,business - Abstract
Driver drowsiness is one of the main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been considered as one of the best physiological signals to detect drivers' drowsy states, since it directly measures neurophysiological activities in the brain. However, designing a calibration-free system for driver drowsiness detection with EEG is still a challenging task, as EEG suffers from serious mental and physical drifts across different subjects. In this paper, we propose a compact and interpretable Convolutional Neural Network (CNN) to discover shared EEG features across different subjects for driver drowsiness detection. We incorporate the Global Average Pooling (GAP) layer in the model structure, allowing the Class Activation Map (CAM) method to be used for localizing regions of the input signal that contribute most for classification. Results show that the proposed model can achieve an average accuracy of 73.22% on 11 subjects for 2-class cross-subject EEG signal classification, which is higher than conventional machine learning methods and other state-of-art deep learning methods. It is revealed by the visualization technique that the model has learned biologically explainable features, e.g., Alpha spindles and Theta burst, as evidence for the drowsy state. It is also interesting to see that the model uses artifacts that usually dominate the wakeful EEG, e.g., muscle artifacts and sensor drifts, to recognize the alert state. The proposed model illustrates a potential direction to use CNN models as a powerful tool to discover shared features related to different mental states across different subjects from EEG signals. National Research Foundation (NRF) Submitted/Accepted version This research is supported by the National Research Foundation, Singapore under its International Research Centres in Singapore Funding Initiative.
- Published
- 2022