Drowsiness is the leading cause of many fatal accidents and a substantial financial burden for the economy. Efforts have been made to develop techniques to prevent major accidents while remaining practical for everyday use. The most successful approach discovered thus far involves utilizing physiological techniques that rely on EEG signals. Despite their promising performance, the signal collection process has made them unsuitable for practical implementations. However, the emergence of low-cost commercial EEG headsets has enabled tackling this issue. Our study aimed to assess the effectiveness of machine learning models in identifying drowsiness stages using minimal EEG channels. The study was conducted with fifty sleep-deprived participants driving in a simulator. Based on the Observer Rated Drowsiness method, we divided the stages of drowsiness into three categories: alert, drowsy, and sleepy. Various features were extracted from the EEG signals in time, frequency, and time-frequency domains. Three models were trained in each domain using k-nearest neighbors and ensemble bagged tree classifiers. A majority vote among the three models determined data labels, trained using different combinations of channel data features. Three training strategies were utilized: 1) single channel, 2) temporal channels, frontal channels, left-side channels, and right-side channels separately, and 3) all channels. The results of 10-fold cross-validation showed that the frequency features of temporal channels had the highest accuracy. The best results for nearest neighbors were 97.1% (alert-sleepy), 96.6% (drowsy-sleepy), and 96.7% (alert-drowsy). The highest accuracy of ensemble bagged trees was 100% for all three models.

Driver Drowsiness is one of the leading causes of road accidents. Electroencephalography (EEG) is highly affected by drowsiness; hence, EEG-based methods detect drowsiness with the highest accuracy. Developments in manufacturing dry electrodes and headsets have made recording EEG more convenient. Vehicle-based features used for detecting drowsiness are easy to capture but do not have the best performance. In this paper, we investigated the performance of EEG signals recorded in 4 channels with commercial headsets against the vehicle-based technique in drowsiness detection. We recorded EEG signals of 50 volunteers driving a simulator in drowsy and alert states by commercial devices. The observer rating of drowsiness method was used to determine the drowsiness level of the subjects. The meaningful separation of vehicle-based features, recorded by the simulator, and EEG-based features of the two states of drowsiness and alertness have been investigated. The comparison results indicated that the EEG-based features are separated with lower p-values than the vehicle-based ones in the two states. It is concluded that EEG headsets can be feasible alternatives with better performance compared to vehicle-based methods for detecting drowsiness.