Transactions of Society of Automotive Engineers of Japan
Online ISSN : 1883-0811
Print ISSN : 0287-8321
ISSN-L : 0287-8321
Injury Prediction Model for Automatic Collision Notification Based on Japanese Accident Data
Suguru YoshidaTakashi HasegawaShigeru TominagaTetsuya Nishimoto
Author information
JOURNAL FREE ACCESS

2012 Volume 43 Issue 2 Pages 275-280

Details
Abstract
The estimation results of passenger injury risk from quantitative information recorded by SRS unit are useful both of emergency activity and medical treatment service after accidents. Injury prediction model for estimating occupant′s serious injury risk based on Japanese accident data base using logistic regression modeling technique. Risk factors using in this model are delta-V, crash direction, belt use, multiple impact and occupant′s age. Serious injury risk of a total of 240 cases of crash mode was estimated by the model. The comparison has done between estimated serious injury risk and actual injury of 22 cases of Japanese in-depth accident data. The results show that injury prediction model has a good possibility for predicting injury risk based on onboard data and its application for post crash safety.
Content from these authors
© 2012 Society of Automotive Engineers of Japan, Inc.
Previous article Next article
feedback
Top