It was identified that traffic accidents relate closely to the driver�s mental and physical states immediately before the accident by our\r\nquestionnaire survey. Distraction is one of the key human factors involved in traffic accidents. We reproduced driver�s cognitive\r\ndistraction on a driving simulator by means of imposing cognitive loads such as doing arithmetic and having conversation while\r\ndriving.Visual features such as test subjects� gaze direction, pupil diameter, and head orientation, together with heart rate fromECG,\r\nwere used in this study to detect the cognitive distraction.We improved detection accuracy obtained from earlier studies by using\r\nthe AdaBoost. This paper also suggests a multiclass identification using Error-Correcting Output Coding, which can identify the\r\ndegree of cognitive load. Finally, we verified the effectiveness of the multiclass identification by conducting a series of experiments.\r\nAll these aimed at developing a constituent technology of a driver monitoring system that is expected to create adaptive driving\r\nsafety supporting system to lower the number of traffic accidents
Loading....