Novel Driver’s Drowsiness Detection System and its Evaluation in a Driving Simulator Environment

Abstract

Driver’s drowsiness is one of the leading causes of traffic accidents. Drowsiness can be detected using brain waves (EEG) because it reflects the cognitive state of the brain. However, using EEG for drowsiness detection in vehicles is still impractical. The non-contact brain signal sensor NBM (Neuro-Bio Monitor), introduced by Freer Logic, has a potential to detect the driver’s drowsiness while driving due to its unobtrusive nature of brain signal sensing. In this study, a novel driver drowsiness detection algorithm was introduced using NBM signals. In addition, the feasibility of the NBM-based drowsiness detection algorithm in a driving simulator environment was evaluated by comparison with conventional methods including the eyelid closure ratio (PERCLOS) and the self-reported Karolinska Sleepiness Scale (KSS). The study recruited 14 healthy adults and asked them to drive about 70 minutes on a night drive mode. NBM signals were recorded simultaneously with PERCLOS and KSS. The algorithm shows an accuracy of 78.79% and a detection rate of 95% by comparison with KSS based drowsiness. It also shows a correlation of more than 70% with PERCLOS. This study demonstrated that NBM can be used in vehicle to detect driver drowsiness during driving.