Prediction of neck injury using multiple linear regression and bumper damage: Case study for low-speed rear-end collisions

Abstract

The most frequent type of traffic accident is a low-speed rear-end collision, which can damage parts of the vehicle, including the bumper, and cause neck injury to the occupants. Even in minor damage accidents, such as scratches on bumper covers, 26.3% of occupants received treatment for bodily injuries whose main symptom was neck injuries through auto insurance. This study was conducted to evaluate the potential for neck injuries in low-speed accidents. Fifty-nine low-speed rear-end impact tests were conducted, and the motion of the struck vehicle and the neck injury criterion (NIC) of the occupant according to the test conditions were predicted using multiple linear regression derived via supervised machine learning. It was confirmed that the NIC can be predicted using vehicle motion values that can be obtained through an event data recorder. The coefficients of determination of the regression equations were 0.67–0.83. Lastly, we investigated whether neck injuries can be predicted through bumper cover damage that can be checked immediately after a vehicle accident. In the case of the vehicle damage type 1/2/3 category applied to auto insurance by the Korean government, an occupant would have a very low possibility of neck injury or symptoms. No symptoms or injuries were reported in the volunteer tests conducted for this study.