Injury Severity Analysis of Rural Passenger cars Crashes Involving Head-on collision

This study conducts a thorough analysis of factors affecting the severity of head-on collisions involving passenger vehicles on rural roads in Guilan province, Iran. Employing the non-parametric machine learning technique CART (Classification and Regression Trees), the research models and interprets outcomes based on a dataset of 1889 rural crashes spanning the period from 2014 to 2020, sourced from the traffic center of the Guilan rural police department. The results highlight critical elements such as driver familiarity with the route, accident timing, weather conditions, and road characteristics as influential factors shaping collision severity. The findings provide a nuanced understanding of the complexities in road safety, shedding light on specific circumstances contributing to property damage, injury, or fatality. Beyond academic discourse, it guides policymakers, road safety authorities, and planners. Identifying influential factors facilitates targeted interventions, enhancing road safety in similar contexts.

Injury Severity Analysis of Rural Passenger cars Crashes Involving Head-on collision Keywords:

Crash Severity , Head , on Collision , Passenger car , Soft Computing , CART Model