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

Abstract

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.