Smartwatch-Based Wearable EEG System for Driver Drowsiness Detection

Driver drowsiness is a major cause of mortality in traffic accidents worldwide. Many physiological signals have been proposed to detect driver drowsiness. Among these signals, an electroencephalographic (EEG) signal, which reflects the brain activities, is more directly related to drowsiness. Thus, many EEG-based driver drowsiness detection (DDD) models gained more and more attention in recent years. However, one limitation of these studies is that these models merely estimate discrete labels and, thus, did not allow for estimating the relative severity of driver drowsiness. This paper proposes a support vector machine-based posterior probabilistic model (SVMPPM) for DDD, aimed at transforming the drowsiness level to any value of 0 1 instead of discrete labels. A fully wearable EEG system which consists of a Bluetooth-enabled EEG headband and a commercial smartwatch was used to evaluate the proposed model in a real-time way. Twenty subjects who participated in a 1-h monotonous driving simulation experiment were used to develop this model with fifteen subjects for a building model and five subjects for a testing model. According to a video-based reference, the proposed system obtained an accuracy of 91. 25% for an alert group (73 out of 80 data sets), 83. 78% for an early-warning group (93 out of 111 data sets), and 91. 92% for a full-warning group (91 out of 99 data sets). These results indicate that the combination of the proposed SVMPPM, the EEG headband, and the wrist-worn smart device constitutes an effective, simple, and inexpensive wearable solution for DDD.