Citation

Astarita V, Haghshenas SS, Guido G, Vitale A. Transp. Eng. (Amsterdam) 2023; 12: e100164.

Copyright

(Copyright © 2023, Elsevier Publishing)

DOI

10.1016/j.treng.2023.100164

PMID

unavailable

Abstract

With more cars on the road and an increasing travel rate, one of the main issues in transportation engineering is how to make roads safe. The evaluation of the level of road crash severity is a significant component of the road safety assessment in terms of financial and personal losses. One of the most advanced ways to control and manage traffic information in modern traffic management systems is through intelligent transportation systems (ITS). ITS plays a big part in improving road safety. On the other hand, machine learning techniques play an important role in increasing the level of ITS performance. Hence, this study aims to predict the level of crash severity through a classification approach. In this study, two machine learning techniques namely artificial neural network (ANN) and Grey Wolf optimization algorithm (GWO)-ANN were developed to predict the level of road crash severity, and several performance metrics were used to assess the predictive algorithms' predictive capability. For this purpose, some factors that affect the level of severity were considered, including light condition (LC), weekday (W), horizontal alignment (HA), road element (RE), type of crash (TC), vehicle type (VT), driver gender (DG), average speed (AS) and annual average daily traffic (AADT). 202 case studies were recorded from urban roads in Calabria in southern Italy. When comparing the proposed GWO-ANN model to the ANN model, the findings clearly demonstrated the superiority of the proposed GWO-ANN model.

Language: en

Keywords

ANNs; Classification; Crash severity; GWO algorithm; Machine learning; Road safety; Urban roads