3301 Study on Injury Prediction Model based on Japanese Accidents

Bibliographic Information

Other Title
  • 3301 交通事故マクロデータを用いた乗員傷害予測アルゴリズムの構築(OS5-1 自動車の安全,OS5 安全,安心,防災,環境負荷低減,オーガナイズド・セッション(OS))

Description

Advanced Automatic Collision Notification (AACN) is a notification system that uses data about previous accidents to predict the extent of passenger injuries. The purpose of this study is to develop injury prediction model based on 2.8 million cases of Japanese car accident data. This accident data was split into a training data and a validation data. Receiver operating characteristic (ROC) curves were generated by evaluating serious injury risks from the 1.3 million cases data, and the best models were selected to maximize the Area Under the Curve (AUC) of ROC. Each prediction models of this study has good possibility injury risk ,witch predicted by delta v pseudo, impact direction, seat belt use, occupant age, multiple impacts and vehicle type.

Journal

Citations (1)*help

See more

Details 詳細情報について

Report a problem

Back to top