Analysis of traffic accidents with fuzzy and crisp data mining techniques to identify factors affecting injury severity

Abstract

Injury severity in motor vehicle traffic accidents is determined by a number of factors including driver, vehicle, and environment. Airbag deployment, vehicle speed, manner of collusion, atmospheric and light conditions, degree of ejection of occupant's body from the crash, the use of equipment or other forces to re-move occupants from the vehicle, model and type of vehicle have been considered as important risk factors affecting accident severity as well as driver-related conditions such as age, gender, seatbelt use, alcohol and drug involvement. In this study, we aim to identify important variables that contribute to injury severity in the traffic crashes. A contemporary dataset is obtained from National Highway Traffic Safety Administration's (NHTSA) Fatality Analysis Reporting System (FARS). To identify accident severity groups, we performed different clustering algorithms including fuzzy clustering. We then assessed the important factors affecting injury severity by using classification and regression trees (CRT). The results which would guide car manufacturers, policy makers and insurance companies indicate that the most important factor in defining injury severity is deployment of air-bag, followed by extrication, ejection occurrences, and travel speed and alcohol involvement.