Document Type : Applied Article

Authors

• Morteza Mohammadi Zanjireh ¹
• farzad morady ²

¹ Computer Engineering Department, Faculty of Technical and Engineering, Imam-Khomeini International University

² Ph.D Student,Department of Civil–Transportation Planning, Imam Khomeini International University, Qazvin, Iran

Abstract

This paper predicts the severity of crashes based on the analysis of multiple variables and using machine learning methods. For this purpose, data related to the years 2012 to 2024 of Tempe city in the state of Arizona USA was used. Features were selected using the metaheuristic method. Then, by using decision tree and artificial neural network, the classification of the severity of crashes was carried out. Based on the metrics, decision tree with an overall accuracy of 54% was the optimal. Finally, using the permutation feature importance method, the optimal model was interpreted. The results show that the characteristics of the year with 0.22 and the spatial characteristics with 0.11 and the collision manner with 0.1 have a higher importance in predicting the severity of crashes on urban roads.

Keywords

• crash severity
• spatiotemporal analysis
• machine learning
• metaheuristic algorithm

Main Subjects

• A.1. General