Modeling Injury Severity of Vehicular Traffic Crashes

Data mining techniques constitute an alternative approach that has received increasing attention from researchers in recent years in road safety analysis field. In this paper Bayesian networks were used to develop models in order to identify factors that affect the injury severity of a crash within urban areas based on traffic crashes data on Jordanian roads collected for three years (2009-2011). The following variables were found to have a significant effect on classifying crashes according to their injury severity: lighting of roadway, crash type, road type, crash manner, surface condition, number of lanes, number of vehicles, gradient, type of pavement, traffic control devices, and speed limit. The results of this research can be used to determine the factors that should be taken into consideration when designing a new roadway or for improving safety of existing roads.