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 the 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.

翻译：驾驶员嗜睡是导致道路交通事故的主要原因之一。脑电图（EEG）极易受嗜睡状态影响，因此基于EEG的方法对嗜睡检测具有最高的准确率。干电极及头戴设备制造技术的进步使EEG记录更为便捷。用于检测嗜睡的车载特征虽易于采集，但并非最优性能。本文研究了使用商用头戴设备通过4通道记录EEG信号与车载技术在嗜睡检测中的性能表现。我们利用商用设备记录了50名志愿者在模拟驾驶中嗜睡与清醒状态下的EEG信号，采用观察者嗜睡等级评定法确定受试者嗜睡程度。针对模拟器记录的车载特征与EEG特征在嗜睡与清醒两种状态下的显著分离性进行了研究。比较结果表明，EEG特征在两种状态下的p值显著低于车载特征。由此得出结论：相较于车载方法，EEG头戴设备在嗜睡检测中具有更优性能，可作为可行的替代方案。