Advertisement

Traffic Accident Prediction Model Using Support Vector Machines with Gaussian Kernel

  • Bharti Sharma
  • Vinod Kumar Katiyar
  • Kranti Kumar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 437)

Abstract

Road traffic accident prediction models play a critical role to the improvement of traffic safety planning. The focus of this study is to extract key factors from the collected data sets which are responsible for majority of accidents. In this paper urban traffic accident analysis has been done using support vector machines (SVM) with Gaussian kernel. Multilayer perceptron (MLP) and SVM models were trained, tested, and compared using collected data. The results of the study reveal that proposed model has significantly higher predication accuracy as compared with traditional MLP approach. There is a good relationship between the simulated and the experimental values. Simulations were carried out using LIBSVM (library for support vector machines) integrated with octave.

Keywords

Artificial neural networks Accident characteristics Data mining Road traffic safety 

References

  1. 1.
    Ministry of Road Transport & Highways India 15 Dec 2011 16:26 ISTGoogle Scholar
  2. 2.
    LaScala, E., Gerber, D., Gruenwald, P.J.: Demographic and environmental correlates of pedestrian injury collisions: a spatial analysis. Accid. Anal. Prev. 32, 651–658 (2000)Google Scholar
  3. 3.
    McCarthy, P.: Effect of speed limits on speed distribution and highway safety: a survey of recent literature. Transp. Rev. 21(1), 31–50 (2001)CrossRefGoogle Scholar
  4. 4.
    Mungnimit, S.: Road Traffic Accident Losses. Transport and Communications Policy and Planning Bureau, Ministry of Transport and Communications, Thailand (2001)Google Scholar
  5. 5.
    Bener, A.: The neglected epidemic: road traffic accidents in a developing country, State of Qatar. Int. J. Inj. Control Saf. Promot. 12(1), 45–47 (2005)CrossRefGoogle Scholar
  6. 6.
    Yau, K.K.W.: Risk factors affecting the severity of single vehicle traffic accidents in Hong Kong. Accid. Anal. Prev. 36(3), 333–340 (2004)CrossRefGoogle Scholar
  7. 7.
    Cropper, M.L., Kopits, E.: Traffic fatalities and economic growth. World Bank Policy Research Working Paper, vol. 3035, pp. 1–42 (2003)Google Scholar
  8. 8.
    Mohan, D.: Road accidents in India. Transportation Research and Injury Prevention Programme, Indian Institute of Technology Delhi, New Delhi, India (2009)Google Scholar
  9. 9.
    Stutts, J.C., Reinfurt, D.W., et al.: The role of driver distraction in traffic crashes. AAA Foundation for Traffic Safety, Washington, DC (2001)CrossRefGoogle Scholar
  10. 10.
    Lin, M.-L., Fearn, K.T.: The provisional license: nighttime and passenger restrictions—a literature review. J. Saf. Res. 34, 51–61 (2003)CrossRefGoogle Scholar
  11. 11.
    Shultz, R., Compton, R.: What we know, what we dont know, and what we need to know about graduated driver licensing. J. Saf. Res. 34, 107–115 (2003)CrossRefGoogle Scholar
  12. 12.
    Lajunen, T., Parker, D., et al.: The manchester driver behaviour questionnaire: a cross-cultural study. Accid. Anal. Prev. 36(2), 231–238 (2004)CrossRefGoogle Scholar
  13. 13.
    Chang, H.L., Yeh, T.H.: Motorcyclist accident involvement by age, gender, and risky behaviors in Taipei, Taiwan. Transp. Res. Part F: Psychol. Behav. 10(2), 109–122 (2007)CrossRefGoogle Scholar
  14. 14.
    Schalkoff, R.J.: Artificial neural networks, pp. 146–188. Mcgrawhill, New York (1997)zbMATHGoogle Scholar
  15. 15.
    Baby Deepa, V.: Classification of EEG data using FHT and SVM based on bayesian network. Int. J. Comput. Sci. Issues (IJCSI)Google Scholar
  16. 16.
    Boser, B.E.: The support vector machines (SVM) (1992)Google Scholar
  17. 17.
    Hsu, C.W., Chang, C.C., et.al.: A practical guide to support vector classification. Technical report, Department of Computer Science, National Taiwan University (2003)Google Scholar

Copyright information

© Springer Science+Business Media Singapore 2016

Authors and Affiliations

  • Bharti Sharma
    • 1
  • Vinod Kumar Katiyar
    • 2
  • Kranti Kumar
    • 3
  1. 1.College of Engineering RoorkeeRoorkeeIndia
  2. 2.Department of MathematicsIndian Institute of Technology RoorkeeRoorkeeIndia
  3. 3.School of Liberal StudiesAmbedkar University DelhiDelhiIndia

Personalised recommendations