Paper Infomation
Evaluation of Factors Affecting Driver’s Behaviors using Association Rule
Full Text(PDF, 466KB)
Author: Jingdian Yang
Abstract: In this paper, association rule mining algorithm is utilized to analyze the correlations of various factors of causing traffic accidents, from which the research model of dangerous driving behaviors is established. In this model, the factors and their correlations include: ability of risk control, ability of driving self-confidence, individual characteristics and incorrect driving operations. Selecting the drivers in the city of Chengdu to be the objects of investigation, a group of valid sample data is obtained. Based on these data, the Support and Confidence for association rules are analyzed. In the process, two stage computing of Apriori algorithm programming is simulated and some important rules are acquired. With these rules, departments of traffic administration can focus on these key factors in their processing of traffic transactions. Through training in drivers’ skills and their physical and mental behaviors, the incorrect driving operations can be greatly reduced and the traffic safety can be effectively guaranteed.
Keywords: Driving Technique, Traffic Safety, Big Data, Association Rules, Apriori Algorithm
References:
[1] People's Republic of China National Bureau of Statistics, 2011 Road Accident Statistics Annual, Statistics Press of China, Beijing, China, 2011.
[2] W. Chen, Q. Wu, and Y. Gu, “Statistical analysis on urban roads dangerous driving factors,” Statistics and Decision, 386 (14), pp.0 107-111, 2013.
[3] C. Oha, S. Park, and S. G. Ritchie. “A Method for identifying rear-end collision risks using inductive loop detectors,” Accident Analysis and Prevention, 2006, (38): 212-220.
[4] W. Yang, “Factors affecting safety driving of motorized vehicles and the corresponding strategy,” Estate and Science Tribune, 2013, 12(14): 122-128.
[5] Y. Li., “Factors of safety driving and their corresponding measures,” Technology and Creation, 2015(17):31-31, 2015.
[6] D. Lord. and F. Mannering., “The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives,” Transportation Research Part A Policy & Practice, 44(5):291-305, 2010.
[7] P. Savolainen, F. Mannering, and D. Lord, “The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives,” Accident Analysis & Prevention, 43(5):1666-1676, 2011.
[8] J. Han. and M. Kamber. Data Ming, Concepts and Techniques, Second Edition, China Machine Press, Beijing, China, 2007.
[9] Q. Lea, T. Leb, B. Vob, and B. Lea, “An efficient and effective algorithm for mining top-rank-k frequent patterns,” Expert Systems with Applications, 42(1):156-164, 2015.
[10] D. Nguyena. L. Nguyenc, B. Vod, and T. Honge, “A novel method for constrained class association rule mining,” Information Sciences, 320(1):107-125, 2015.
[11] J. Fdez, R. Alcala, and F. Herrera, “A Fuzzy Association Rule-Based Classification Model for High-Dimensional Problems with Genetic Rule Selection and Lateral Tuning,” IEEE Transactions on Fuzzy Systems, 19(5):857-872, 2011.
[12] Z. Du, H. Li, S. Lian, H. Zhou, and R, Fan, “Association rule mining of simulated annealing-based quantization space,” Geographic Space Information, 14(5):8-10, 2016.
[13] X. Lu, W. Chen, and X. Yang, “Research and application of space Association rule mining technology,” Computer Technology and Development, 2013(05):26-29, 2013.