Automatic driver sleepiness detection using EEG, EOG and contextual information
作者：
Highlights：
• An automated driver sleepiness detection system has been developed.
• The system is based on physiological data combined with contextual information.
• 312 driving simulator sessions with alert and sleep deprived drivers were used.
• 79% accuracy for multiclass and 93% accuracy for binary classification was achieved.
• Adding contextual information as features showed improvement in accuracy by 4% and 5%.
摘要
•An automated driver sleepiness detection system has been developed.•The system is based on physiological data combined with contextual information.•312 driving simulator sessions with alert and sleep deprived drivers were used.•79% accuracy for multiclass and 93% accuracy for binary classification was achieved.•Adding contextual information as features showed improvement in accuracy by 4% and 5%.
论文关键词：Driver sleepiness,Electroencephalography,Electrooculography,Contextual information,Machine learning
论文评审过程：Received 5 March 2018, Revised 26 July 2018, Accepted 27 July 2018, Available online 3 August 2018, Version of Record 13 August 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.07.054
