| Summary: | The purpose of this research is to present a new method for considering accidents according to the environmental, traffic and geometrical conditions of the road, which considers accidents according to the interaction of the components that lead to them. In order to enter the physical characteristics, this approach divides the road into units or parts with homogeneous physical characteristics, and as a result, the decision about the safety status of the road is made for a length of road with specific characteristics instead of a single point. This approach has been carried out using the Data Envelopment Analysis (DEA) method, which, unlike regression methods, does not require obtaining the distribution function and considering hypotheses about it. This method gives scores (inefficiencies) that allow road segments to be appropriately ranked and prioritized in terms of accident proneness. In the current research, a case study was conducted on routes with a length of 144.4 kilometers, which resulted in the identification of 154 road sections with different relative risk scores, thus the accident sections were identified and prioritized with the proposed method, which in terms of the definition of entry indicators and the output based on the data coverage analysis method is considered as a new experience for the priority of road sections. Furthermore, this study focuses on the application of artificial neural networks (ANNs) in analyzing road safety. An idealized ANN model is developed using a database of various input parameters related to road segments, and the weighted index of accidents as the target variable. The results reveal the relative importance of different parameters on the weighted index, with the Ratio of curvature, Length of the segment, and Condition of the pavement identified as the most influential factors. These findings highlight the significance of road curvature, segment length, and pavement condition in determining accident severity. The study underscores the potential of ANNs for assessing road safety and informs targeted interventions to mitigate accidents.
|
|---|