Prediction Method of Motor Vehicle Traffic Accident Based on Support Vector Machine

Abstract:

With the rapid development of economy and the improvement of people's living standard, there are more and more vehicles in China, with the increase of traffic accidents. In this paper, by analyzing the factors of social influence on motor vehicle traffic accident, we establish the index system, that is corresponding relationship of motor vehicle traffic accident and factors of social influence, According to this index system, design of motor vehicle traffic accident prediction method based on SVM. Based on the statistical data of social factors and motor vehicle traffic accident in 1985-2012 in china, to train the SVM model, at the same time, the kernel function and parameters of SVM used were setting and compared. The experimental results show that, the accuracy of the use of the RBF function is 97.2%, predicted by using time 95ms, with higher accuracy and faster computing speed.

• Periodical: Applied Mechanics and Materials (Volumes 631-632)
• Pages: 284-287
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.631-632.284
• Online since: September 2014
• Authors: Bo Yang*, Li Na Zhang
• Keywords: Experimental Prediction, Motor Vehicle Traffic Accident, SVM Kernel Function

References

[1] G Bianch. i Performance analysis of the IEEE 802. 11 distributed coordination Function [J]. IEEE J. Se. l Areas Commun, M ar. 2000, 18 (3): 535- 547.

[2] Linwas K H, Liu B D. A gray system modeling approach to the prediction of calibration intervals of Calibration Intervals [J]. IEEE Transactions on Instrumentation and Measurement, 2005, 54 (1): 297-304.

DOI: 10.1109/tim.2004.840234

[3] Vladimir N Vapnik. An overview of statistical learning theory [J]. IEEE Transactions on Neural Networks (S1045-9227), 1999, 10(5): 988-999.

DOI: 10.1109/72.788640

[4] TIAN X, DENG F Q. An improved multi2class SVM algorithm and its application to the credit scoring model [A]. Proceedings of the fifth World Congress on Intelligent Control and Automation[C]. Hangzhou, China, (2004).

DOI: 10.1109/wcica.2004.1341918

[5] PHETKAEW T, KIJ SIRIKUL B, RIV EPIBOON W. Reordering adaptive directed acyclic graphs: an improved algorithm for multiclass support vector machines [A]. Proceedings of the 2003 International Joint Conference on Neural Networks [C]. Portland, OR, USA, 2003, 2(3): 236-241.

DOI: 10.1109/ijcnn.2003.1223939