Driving anger detection based on multivariate time series features of driving behavior

被引：0
|
作者：
Wan P. [1 ,2 ,3 ]
Wu C.-Z. [1 ,2 ]
Lin Y.-Z. [3 ]
Ma X.-F. [1 ,2 ]
机构：
[1] Intelligent Transport Systems Research Center, Wuhan University of Technology, Wuhan
[2] Engineering Research Center for Transportation Safety, Ministry of Education, Wuhan
[3] Intelligent Human-Machine Systems Laboratory, Northeastern University, Boston
来源：
Ma, Xiao-Feng (maxiaofeng@whut.edu.cn) | 2017年 / Editorial Board of Jilin University卷 / 47期
关键词：
Driving anger detection; Driving behaviors; Engineering of communication and transportation system; Multivariate time series; Piecewise linear representation;
D O I：
10.13229/j.cnki.jdxbgxb201705014
中图分类号：
学科分类号：
摘要：
To explore effective approaches of intervention on road rage, a driving anger detection model based on driving behavior is proposed. The driving behavior data in angry and neutral states were acquired by conducting timed experiments for driving anger induction in busy traffic sections. Piecewise Linear Representation (PLR) method was used to fit multivariate time series, which consists of steering wheel angle and vehicle lateral position, and a bottom-up algorithm was implemented to separate the multivariate time series. The slope and time interval of each segment were extracted as the input features of a Support Vector Machine (SVM) model, which was used to recognize the driving anger. The validation results show that the accuracy of the proposed model with ten segments is 78.69%, which is 8.57% and 4.85% higher than that with five segments and twenty segments, respectively. This study may provide reference for the design of real driving anger detection devices based on driving behavior. © 2017, Editorial Board of Jilin University. All right reserved.
引用
收藏
页码：1426 / 1435
页数：9
相关论文
共 17 条
  • [1] Wu C.-Z., Lei H., Review on the study of motorists' driving anger, China Safety Science Journal, 20, 7, pp. 3-8, (2010)
  • [2] National highway traffic safety administration (NHTSA): traffic safety facts: a compilation of motor vehicle crash data from the fatality analysis reporting system and the general estimates system
  • [3] Lei H., The characteristics of angry driving behaviors and its effects on traffic safety, (2011)
  • [4] Dahlen E.R., Martin R.C., Ragan K., Et al., Driving anger, sensation seeking, impulsiveness, and boredom proneness in the prediction of unsafe driving, Accident Analysis and Prevention, 37, 2, pp. 341-348, (2005)
  • [5] Zhang D., Wan B.-K., Ming D., Research progress on emotion recognition based on physiologicalsignals, Journal of Biomedical Engineering, 32, 1, pp. 229-234, (2015)
  • [6] Lin Q.-W., Research on driving behavior based on emotional computing, (2014)
  • [7] Jones C., Jonsson I., Detecting emotions in conversations between driver and in-car information systems, Proceedings of the First International Conference on Affective Computing and Intelligent Interaction, pp. 780-787, (2005)
  • [8] Kessous L., Castellano G., Caridakis G., Multimodal emotion recognition in speech-based interaction using facial expression, body gesture and acoustic analysis, Journal on Multimodal User Interfaces, 3, 1, pp. 33-48, (2010)
  • [9] Wang J.-J., Gong Y.-H., Normalizing multi-subject variation for drivers' emotion recognition, IEEE International Conference on Multimedia and Expo, pp. 354-357, (2009)
  • [10] Katsis C., Goletsis Y., Rigas G., Et al., A wearable system for the affective monitoring of car racing driversduring simulated conditions, Transportation Research Part C: Emerging Technologies, 19, pp. 541-551, (2011)
12