Analysis of injuries severity in multi-vehicle crashes: an application of classification and regression tree

Articles in Press

Document Type : Original Article

Authors

1 M.Sc student, Dept. of Civil Engineering, Iran University of Science and Technology, Tehran, Iran.

2 Professor, Dept. of Civil Engineering, Iran university of science and Technology, Tehran, Iran.

3 Associate Professor, Dept. of Civil Engineering, Isfahan University of Technology, Isfahan, Iran.

Abstract

Multi-vehicle crashes are being a considerable number of accidents every year. In this paper the factors that influence injuries severity in multi-vehicle crashes have been identified by using classification and regression tree (CART) model over data derived from accidents occurred in Tehran province in 1390. For improving accuracy instead of using three-class prediction, a binary prediction was used in two models. The first model and the second model classified 89.4% and 91.7% of accidents correctly. Results indicated that vehicle type, manner of collision, cause of crash and safety belt usage are the most significant factors influencing injuries severity in multi-vehicle crashes, moreover, among different kind of vehicle types, bicycles, motor cycles and trucks have the most significant impact on occurring more severe injuries and among cause of crashes, exceeding from assurance speed, deviation toward left and distraction from front side have the most significant influence on occurring more severe injuries.

Keywords

Main Subjects

Journal of Transportation Research

Articles in Press, Accepted Manuscript
Available Online from 27 June 2018

Files

Share

How to cite

Statistics