标题：Driver emotion recognition of multiple-ECG feature fusion based on BP network and D-S evidence
作者：Wang, Xiaoyuan; Guo, Yongqing; Ban, Jeff; Xu, Qing; Bai, Chenglin; Liu, Shanliang
作者机构：[Wang, Xiaoyuan; Liu, Shanliang] Qingdao Univ Sci & Technol, Coll Electromech Engn, Qingdao, Peoples R China.; [Wang, Xiaoyuan; Guo, Yongqing] Tsing 更多
会议名称：10th International Conference on Green Intelligent Transportation System and Safety
来源：IET INTELLIGENT TRANSPORT SYSTEMS
关键词：road safety; emotion recognition; road traffic; road accidents; driver; information systems; uncertainty handling; medical signal processing;; feature extraction; psychology; backpropagation; sensor fusion;; inference mechanisms; electrocardiography; cognition; driver emotion; recognition; BP network; D-S evidence; driving emotion; traffic; environment; anxiety; distracted driving; vehicle crash; driving safety;; back-propagation network; Dempster-Shafer evidence method; ECG signals;; time-frequency domain; nonlinear characteristics; emotion recognition; model; ECG evidence fusion; personalised driving warning system; road; traffic safety; multiple-electrocardiogram feature fusion; multiple-ECG; feature fusion; driver psychological reaction
摘要：Driving emotion is considered as driver's psychological reaction to a change in traffic environment, which affects driver's cognitive, judgement and behaviour. In anxiety, drivers are more likely to get engaged in distracted driving, increasing the likelihood of vehicle crash. Therefore, it is essential to identify driver's anxiety during driving, to provide a basis for driving safety. This study used multiple-electrocardiogram (ECG) feature fusion to recognise driver's emotion, based on back-propagation network and Dempster-Shafer evidence method. The three features of ECG signals, the time-frequency domain, waveform and non-linear characteristics were selected as the parameters for emotion recognition. An emotion recognition model was proposed to identify drivers' calm and anxiety during driving. The results show after ECG evidence fusion, the proposed model can recognise drivers' emotion, with an accuracy rate of 91.34% for calm and 92.89% for anxiety. The authors' findings of this study can be used to develop the personalised driving warning system and intelligent human-machine interaction in vehicles. This study would be of great theoretical significance and application value for improving road traffic safety.