Traffic safety is one of the crucial problems of many countries in the world. To handle this problem, a great deal of research has been conducted considering various methods. This study includes analyses of black spots using different computing approaches. Integration of cluster analysis, entropy approach and fuzzy logic approaches are used in the analyses. The conventional black spot identification method includes marking the location of each accident with a pin and investigation of black spots considering density of the pins on a map. In this study, a systematic approach is employed. Firstly, the traffic accidents data of Denizli city have been analyzed using the fuzzy clustering methods. The spots that are densely located around the cluster centers are determined as "black spots". Secondly, the safety levels of black spots' are determined by Shannon Entropy Approach considering accident types and effective factors on accident occurrence. Geometrical and physical conditions, traffic volumes, average speeds and average accident rates at around black spots are considered as effective factors on occurrence of accidents. Entropy values are calculated using these parameters. Thirdly, the safety levels are classified by both fuzzy logic and crisp approaches based on calculated entropy values. Validation of entropy approach is tested by Chi-Square and truth value methods. The results are evaluated regarding all features of the black spots, and a series of recommendations to improve traffic safety are reported.
Murat, Y. S., & Cakici, Z. (2017). An Integration of Different Computing Approaches in Traffic Safety Analysis. In Transportation Research Procedia (Vol. 22, pp. 265–274). Elsevier B.V. https://doi.org/10.1016/j.trpro.2017.03.033