EEG_DMNet: A Deep Multi-Scale Convolutional Neural Network for Electroencephalography-Based Driver Drowsiness Detection

Abstract

Drowsy driving is one of the major causes of traffic accidents, injuries, and deaths on roads worldwide. One of the best physiological signals that are useful in detecting a driver’s drowsiness is electroencephalography (EEG), a kind of brain signal that directly measures neurophysiological activities in the brain and is widely utilized for brain–computer interfaces (BCIs). However, designing a drowsiness detection method using EEG signals is still challenging because of their non-stationary nature. Deep learning, specifically convolutional neural networks (CNNs), has recently shown promising results in driver’s drowsiness. However, state-of-the-art CNN-based methods extract features sequentially and discard multi-scale spectral-temporal features, which are important in tackling the non-stationarity of EEG signals. This paper proposes a deep multi-scale convolutional neural network (EEG_DMNet) for driver’s drowsiness detection that learns spectral-temporal features. It consists of two main modules. First, the multi-scale spectral-temporal features are extracted from EEG trials using 1D temporal convolutions. Second, the spatial feature representation module calculates spatial patterns from the extracted multi-scale features using 1D spatial convolutions. The experimental results on the public domain benchmark SEED-VIG EEG dataset showed that it learns discriminative features, resulting in an average accuracy of 97.03%, outperforming the state-of-the-art methods that used the same dataset. The findings demonstrate that the proposed method effectively and efficiently detects drivers’ drowsiness based on EEG and can be helpful for safe driving.