Drowsiness Detection by Electrooculogram Signal Analysis in Driving Simulator Conditions for Gold Standard Signal Generation

摘要

Detection of drowsiness while driving is a leading objective in advanced driver assistance systems. This work presents a new index to assess the alertness state of drivers based on the EOG dynamics derived from a polysomnography device. More than 15 hours of laboratory tests were analyzed in order to detect drowsiness while doing cognitive activities. The proposed method has a sensitivity of 92, 41% and a VPP of 93,41% in detecting drowsiness. The results show that the proposed index may be promising to assess the alertness state of real drivers.