Yan Sun This email address is being protected from spambots. You need JavaScript enabled to view it.1 and Zhixiang Hou2

1Xi’an Fanyi University, Xi’an, Shaanxi, 710105, P.R. China
2College of Automotive and Mechanical Engineering, Changsha University of Science and Technology, Changsha, 410114, P.R. China


Received: December 19, 2016
Accepted: December 14, 2017
Publication Date: March 1, 2018

Download Citation: ||https://doi.org/10.6180/jase.201803_21(1).0006  


In recent years,the traffic incident automatic detection technology has become a central issue in intelligent transportation field. In order to detect traffic incidents accurately, highway traffic incident detection model is setup based on the characteristics of highway traffic flow and the basic principles of traffic incident detection. This model includes data preprocessing module, construction of SVM and decision output module. Improved particle swarm optimization is adopted to optimize parameters of SVM model. By adjusting the penalty parameter and the size of the radial basis kernel parameter, we can make SVM has better classification performance. The simulation data is extracted from I-880 traffic dataset. By comparing and analyzing the simulation results, the SVM model based on improved particle swarm optimization achieves better comprehensive detection performance with less modeling time and higher detection accuracy, which provides important reference for highway abnormal traffic incident detection.

Keywords: Traffic Incident Detection, Particle Swarm Optimization, Support Vector Machine


  1. [1] Tang, S. and Gao, H., “Traffic-incident Detection-algorithm Based on Nonparametric Regression,” Intelligent Transportation Systems IEEE Transactions on, Vol. 6, No. 1, pp. 3842 (2005). doi: 10.1109/TITS. 2004.843112
  2. [2] Cheng, X., Lin, W., Liu, E. and Gu, D., “Highway Traffic Incident Detection Based on bpnn,” Procedia Engineering, Vol. 7, pp. 482489 (2010). doi: 10.1016/ j.proeng.2010.11.080
  3. [3] Yuan, F. and Cheu, R., “Incident Detection Using Support Vector Machines,” Transportation Research Part C: Emerging Technologies, Vol. 11, No. 3, pp. 309 328 (2003). doi: 10.1016/S0968-090X(03)00020-2
  4. [4] Binglei, X., Zheng, H. and Hongwei, M., “Fuzzy-logic-based Traffic Incident Detection Algorithm for Freeway,” Proc. The 7th International Conference on Machine Learning and Cybernetics, pp. 12541259 (2008). doi: 10.1109/ICMLC.2008.4620597
  5. [5] Cai, Z., Jiang, G. and Ding, Q., “Study on Automated Incident Detection Algorithms Based on Multi-svm Classifier,” Chinese Control and Decision Conference CCDC 2008, pp. 100106 (2008). doi: 10.1109/CCDC. 2008.4597539
  6. [6] Chen, S., Wang, W. and Van Zuylen, H., “Construct Support Vector Machine Ensemble to Detect Traffic Incident,” Expert Systems with Applications, Vol. 36, No. 8, pp. 1097610986 (2009). doi: 10.1016/j.eswa. 2009.02.039
  7. [7] Xiao, J. and Liu, Y., “Traffic Incident Detection Using Multiple Kernel Support Vector Machine,” Transportation Research Board 91th Annual Meeting, pp. 201 207 (2012). doi: 10.3141/2324-06
  8. [8] Wang, W., Chen, S. and Qu, G., “Incident Detection Algorithm Based on Partial Least Squares Regression,” Transportation Research Part C: Emerging Technologies, Vol. 16, No. 1, pp. 5470 (2008). doi: 10.1016/j. trc.2007.06.005
  9. [9] Yan, G., Olariu, S. and Popescu, D. C., “NOTICE: an Architecture for the Notification of Traffic Incidents,” IEEE Communications Magazine, Vol. 4, No. 4, pp. 616 (2012). doi: 10.1109/MITS.2012.2217571
  10. [10] Li, W. J., Jing, B. S. and Yang, G. W., “The Incident Detection Algorithm Based on Wavelet Analysis,” Journal of Xi ‘an Highway Traffic University, Vol. 17, No. 2, pp. 134138 (1997).
  11. [11] Jiang, Z. F. and Liu, X. K., “Traffic Incident Detection Algorithm Based on Neural Network,” JournalofXi’an Highway Traffic University, Vol. 17, No. 3, pp. 104 108 (2001). doi: 10.1061/41039(345)473
  12. [12] Wen, J. and He, G. G., “Neural Network Traffic Incident Automatic Detection Algorithm Based on Data Preprocessing of Rough Set Theory,” Transportation Systems Engineering and Information Technology, Vol. 4, pp. 5459 (2004).
  13. [13] Yao, Z. S. and Shao, C. F., “Traffic Incident Detection Method Research Based on V-support Vector Machine Classification,” Journal of ITS Communication, Vol. 7, No. 4, pp. 3841 (2005).
  14. [14] Liang, X. R. and Liu, Z. Y., “Highway Incident Detection Based on Support Vector Machine,” Computer Engineering and Application, No. 16, pp. 213218 (2006).
  15. [15] Cai, Z. L. and Jiang, G. Y., “Highway AID Based on Multiple SVM Classifier Fusion Technology,” The 27th Chinese Control Conference, Kunming, China, pp. 205 211 (2008).
  16. [16] Zhu, H. B., “Traffic Incident Detection Based on the Bagging Algorithm and Genetic Neural Network,” Journal of Computer Application and Software, Vol. 1, No. 27, pp. 234236 (2010).
  17. [17] Wang, Q., “Traffic Incident Detection Based on Artificial Neural Network,” Proc. IEEE 3rd International Conference on Communication Software and Networks, pp. 657659 (2011). doi: 10.1109/ICCSN.2011.6014812
  18. [18] Wang, F. Y., “Parallel Control and Management for Intelligent Transportation Systems: Concepts Architectures and Applications,” IEEE Trans. Intell. Transp. Syst., Vol. 11, No. 3, pp. 630638 (2010). doi: 10. 1109/TITS.2010.2060218
  19. [19] Barria, J. A. and Thajchayapong, S., “Detection and Classification of Traffic Anomalies Using Microscopic Traffic Variables,” IEEE Trans. Intelligent Transportation Systems, Vol. 12, No. 3, pp. 695704 (2011). doi: 10.1109/TITS.2011.2157689
  20. [20] Fan, S., Tian, F. C., He, Q. H., Jia, P. F., Feng, J. W. and Shen, Y., “Wound Infection Recognition Based on Quantum-behaved Particle Swarm Optimization,” Journal of Convergence Information Technology, Vol. 8, No. 5, pp. 12091219 (2012). doi: 10.4156/jcit.vol8. issue5.140