Journal Home > Volume 22 , Issue 6
Tsinghua Science and Technology 2017, 22(6): 682-690 https://doi.org/10.23919/TST.2017.8195350
Open Access | Issue | Published: 14 December 2017

Dangerous Driving Behavior Recognition and Prevention Using an Autoregressive Time-Series Model

Show Author's Information Hongxin Chen,  Shuo Feng,  Xin Pei( ),  Zuo Zhang,  Danya Yao
Department of Automation, Tsinghua University, Beijing 100084, China.
Keywords:
driving behavior, time headway, traffic safety, autoregressive time-series model, remaining life, driving warning strategy
Cite this article:
Chen H, Feng S, Pei X, et al. Dangerous Driving Behavior Recognition and Prevention Using an Autoregressive Time-Series Model. Tsinghua Science and Technology, 2017, 22(6): 682-690. https://doi.org/10.23919/TST.2017.8195350
Download citation
EndNote(RIS)
BibTeX

459

Views

18

Downloads

Citations

16

Crossref

N/A

WoS

19

Scopus

3

CSCD

Abstract Full text About this article

Time headway is an important index used in characterizing dangerous driving behaviors. This research focuses on the decreasing tendency of time headway and investigates its association with crash occurrence. An autoregressive (AR) time-series model is improved and adopted to describe the dynamic variations of average daily time headway. Based on the model, a simple approach for dangerous driving behavior recognition is proposed with the aim of significantly decreasing headway. The effectivity of the proposed approach is validated by means of empirical data collected from a medium-sized city in northern China. Finally, a practical early-warning strategy focused on both the remaining life and low headway is proposed to remind drivers to pay attention to their driving behaviors and the possible occurrence of crash-related risks.


menu
Abstract
Full text
Outline
About this article

Dangerous Driving Behavior Recognition and Prevention Using an Autoregressive Time-Series Model

Show Author's information Hongxin Chen, Shuo Feng, Xin Pei( ), Zuo Zhang, Danya Yao
Department of Automation, Tsinghua University, Beijing 100084, China.

Abstract

Time headway is an important index used in characterizing dangerous driving behaviors. This research focuses on the decreasing tendency of time headway and investigates its association with crash occurrence. An autoregressive (AR) time-series model is improved and adopted to describe the dynamic variations of average daily time headway. Based on the model, a simple approach for dangerous driving behavior recognition is proposed with the aim of significantly decreasing headway. The effectivity of the proposed approach is validated by means of empirical data collected from a medium-sized city in northern China. Finally, a practical early-warning strategy focused on both the remaining life and low headway is proposed to remind drivers to pay attention to their driving behaviors and the possible occurrence of crash-related risks.

Keywords: driving behavior, time headway, traffic safety, autoregressive time-series model, remaining life, driving warning strategy

References(21)

[1]
Sabey B. E. and Taylor H., The known risks we run: The highway, in Societal Risk Assessment, Schwing R. C. and Albers W. A. Jr., eds. Boston, MA, USA: Springer, 1980, pp. 43-70.
DOI
[2]
American Association of State Highway and Transportation Officials, Highway safety manual, National Research Council, Washington, DC, USA, 2010.
[3]
Lewin I., Driver training: A perceptual-motor skill approach, Ergonomics, vol. 25, no. 10, pp. 917-924, 1982.
DOI Google Scholar
[4]
Taylor M. C., Lynam D. C., and Baruya A., The effects of drivers’ speed on the frequency of road accidents, TRL report 421, Transport Research Laboratory, UK, 2000.
[5]
Elvik R., Christensen P., and Amundsen A. H., Speed and road accidents: An evaluation of the power model, Nordic road and transport research, Oslo: Institute of Transport Economics, 2004.
[6]
Vogel K., A comparison of headway and time to collision as safety indicators, Accid. Anal. Prev., vol. 35, no. 3, pp. 427-433, 2003.
DOI Google Scholar
[7]
Paefgen J., Staake T., and Fleisch E., Multivariate exposure modeling of accident risk: Insights from pay-as-you-drive insurance data, Transp. Res. Part A Policy Pract., vol. 61, pp. 27-40, 2014.
DOI Google Scholar
[8]
Husnjak S., Perakovi D., Forenbacher I., and Mumdziev M., Telematics system in usage based motor insurance, Procedia Eng., vol. 100, pp. 816-825, 2015.
DOI Google Scholar
[9]
Heino A., van der Molen H. H., and Wilde G. J. S., Differences in risk experience between sensation avoiders and sensation seekers, Personal. Individ. Differ., vol. 20, no. 1, pp. 71-79, 1996.
DOI Google Scholar
[10]
Heino A., van der Molen H. H., and Wilde G. J. S., Risk perception, risk taking, accident involvement and the need for stimulation, Saf. Sci., vol. 22, nos. 1–3, pp. 35-48, 1996.
DOI Google Scholar
[11]
van Winsum W. and Heino A., Choice of time-headway in car-following and the role of time-to-collision information in braking, Ergonomics, vol. 39, no. 4, pp. 579-592, 1996.
DOI Google Scholar
[12]
Evans L. and Wasielewski P., Do accident-involved drivers exhibit riskier everyday driving behavior? Accid. Anal. Prev., vol. 14, no. 1, pp. 57-64, 1982.
DOI Google Scholar
[13]
Chen H. X., Pei X., Zhang Z., Yao D. Y., Feng Q. J., and Wang Z. Z., Driving behavior differences between crash-involved and crash-not-involved drivers using urban traffic surveillance data, presented at the IEEE International Conference on Service Operations and Logistics, and Informatics, Beijing, China, 2016.
[14]
Händel P., Ohlsson J., Ohlsson M., Skog I., and Nygren E., Smartphone-based measurement systems for road vehicle traffic monitoring and usage-based insurance, IEEE Syst. J., vol. 8, no. 4, pp. 1238-1248, 2014.
DOI Google Scholar
[15]
Guo W., Zhang Y., and Li L., The integration of CPS, CPSS, and ITS: A focus on data, Tsinghua Sci. Technol., vol. 20, no. 4, pp. 327-335, 2015.
DOI Google Scholar
[16]
Shang C., Yang F., Gao X. Q., Huang X, L., Suykens J. A. K., and Huang D. X., Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis, AIChE J., vol. 61, no. 11, pp. 3666-3682, 2015.
DOI Google Scholar
[17]
Shang C., Huang B., Yang F., and Huang D. X., Probabilistic slow feature analysis based-representation learning from massive process data for soft sensor modeling, AIChE J., vol. 61, no. 12, pp. 4126-4139, 2015.
DOI Google Scholar
[18]
Liao H. T., Zhao W. B., and Guo H. R., Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model, presented at RAMS ’06 Annual Reliability and Maintainability Symposium, Newport Beach, CA, USA, 2006.
[19]
Si X. S., Wang W. B., Hu C. H., and Zhou D. H., Remaining useful life estimation-a review on the statistical data driven approaches, Eur. J. Oper. Res., vol. 213, no. 1, pp. 1-14, 2011.
DOI Google Scholar
[20]
Li G., Qin J., Ji Y. D., and Zhou D. H., Reconstruction based fault prognosis for continuous processes, Control Eng. Pract., vol. 18, no. 10, pp. 1211-1219, 2010.
DOI Google Scholar
[21]
Deng Z. L., Self-Tuning Filtering Theory with Applications: Modern Time Series Analysis Method, (in Chinese). Harbin, China: Press of Harbin Institute of Technology, 2003.
Publication history
Copyright
Rights and permissions

Publication history

Received: 21 July 2016
Revised: 28 September 2016
Accepted: 03 October 2016
Published: 14 December 2017
Issue date: December 2017

Copyright

© The author(s) 2017

Rights and permissions

Return