Identification of High Crash Road Segment using Genetic Algorithm and Dynamic Segmentation

Document Type : Research Paper


1 Department of Civil & Environmental Engineering, Tarbiat Modares University, Tehran, Iran

2 Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran

3 Department of Civil Engineering, Birjand University of Technology, Birjand, Iran, School of Transportation, Southeast University, Nanjing, China


This paper presents an evolutionary algorithm for recognizing high and low crash road segments using Genetic Algorithm as a dynamic segmentation method. Social and economic costs as well as physical and mental injuries make the governments perceiving to road safety indexes in order to diminish the consequences of road accidents. Due to the limitation of budget for safety improvement of all parts of the road, the road segments with more accidents should be recognized for safety budget assignment. So, considering this fact it's important to identify the segments with high and low number of accidents to optimize the road safety program. In this study, a novel chromosome coding method and a fitness function which are consistent with Genetic Algorithm are proposed. The proposed methodology is also validated by using two mathematical parameters so that the results confirm that the proposed modeling works properly. Afterward, the proposed dynamic segmentation method is compared with the other static segmentation methods along 51 km of Shahrood–Sabzevar highway. The proposed method may have more advantages comparing to static segmentation methods for all of the performance indexes which were considered in this study. The proposed method has a variance about two times higher than the one for accident density in comparison with the other static segmentation methods. About 62% and 34% improvement is achieved in average of segments accident density and total segments density respectively in comparison with the other fixed methods.


- Bonneson, J. and Zimmerman, K. (2006) "Procedure for using accident modification factors in the highway design process", Texas Transportation Institute, Report No. 0-4703-P5.
- Boroujerdian, A., Saffarzadeh M. and Abolhasannejad, V. (2009) "Developing a model for prioritizing high crash road segments", Proceedings the Institution of Civil engineers, Journal Transport, Vol. 163, pp. 19-28
- Boroujerdian, A. (2011) "Developing evaluation model of road safety based on the dynamic segmentation and caused based prioritization", Ph.D. Dissertation, Faculty of Civil and Environmental Engineering, Tarbiat 
- Boroujerdian, A. M., Saffarzadeh, M., Yousefi, H. and Ghassemian H. (2014) "A model to identify high crash road segments with the dynamic segmentation method", Accident Analysis and Prevention, Vol. 73, pp. 274–287.
- Boroujerdian, A. M., Fetanat, M and Abolhasannejad, V. (2015) "Dynamic segmentation method for identification of accident-prone road segments using genetic algorithm", Accepted 14th International Conference Traffic and On Transportation Engineering (ICTTE 2015).
- Elvik, R. (2008) "A survey of operational definitions of hazardous road locations in some European countries", Accident Analysis and Prevention, No. 40, pp. 1830–18357.
- Engelbrecht, A. P. (2007) "Computational intelligence: an introduction", 2nd edition.
- Federal Highway Administration (1981) "Highway safety improvement program", FHWA-TS-81-218, US Department of Transportation, Washington, DC, December.
- Geurts, K. (2006) "Ranking and profiling dangerous accident locations using data mining and statistical techniques", Doctoral Dissertation, Faculty of Applied Economics, Hasselt University, Hasselt.
- Goldberg, D. E. (1989) "Genetic algorithms in search, optimization, and machine learning reading”, MA: Addison-Wesley.
- Huang, C. J., Chen, Y. J., Wu, C. F., and Huang, Y. A. (2009) "Application of neural networks and genetic algorithms to the screening for high quality chips", Applied Soft Computing, Vol. 9, No, 2, pp. 824–832.
- Kononov J. and Allery B. (2003) "Level of service of safety conceptual blueprint and analytical framework", Transportation Research Record 1840, TRB, Washington, D.C, pp. 03-
- Pant, P. D., Rajagopal, A. S. and Cheng, Y. (2003) "Rational Schedule of Base Accident Rates for Rural Highways in Ohio (Phase II)", Report No. FHWA-OH-2003-008.
-Saffarzadeh, M., Abolhasannejad V and Boroujerdian A. (2007) "Developing a cause prioritizing model to identify high accident prone segments of roads for pedestrians", Journal of The Collage of Engineering, Vol. 42, Issue 4, pp. 457-467
- Samanta, B. (2004) "Artificial neural networks and genetic algorithms for gear fault detection", Mechanical Systems and Signal Processing, Vol. 18, No. 5, pp. 1273–1282.
- The Research Institute of Transportation (2008) "The accidents records methods and identifying high crash road segments", The Ministry of Road and Transportation, Tehran, Iran.
- Troche, L. R. (2007) "Methodology to identify hazardous locations for highways in Puerto Rico", Thesis submitted in partial fulfillment of the requirements for the degree of Master of Science.
- Vistisen, D. (2002) "Models and methods for hot spot safetywork", PhD Dissertation, Department for Informatics and Mathematical Models, Technical University of Denmark, Lyngby.