A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEG

TL;DR

This paper introduces a compact, interpretable CNN model for cross-subject driver drowsiness detection using single-channel EEG, achieving higher accuracy and biologically meaningful feature localization.

Contribution

The study presents a novel CNN architecture with GAP and CAM for shared EEG feature extraction across subjects, enhancing interpretability and accuracy in drowsiness detection.

Findings

Achieved 73.22% accuracy on 11 subjects for cross-subject classification.

Model learned biologically explainable features like Alpha spindles and Theta bursts.

Utilized artifacts such as muscle activity for alert state recognition.

Abstract

Driver drowsiness is one of 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.