Injury estimation for Advanced Automatic Collision Notification (AACN) in Germany

  • This study aimed at developing an injury estimation algorithm for AACN technologies for Germany and compared them to findings based on Japanese data. The data to build and to verify the algorithm was obtained from the German in-depth Accident Database (GIDAS) and split into a training and a validation dataset. Significant input variables and the generalized linear regression model to predict severe injuries (ISS>15) were selected to maximize area under the receiver operating characteristic curve (AUC). Probit regression with the input parameter multiple impact, delta v, seatbelt use and impact direction gave the largest AUC of 0.91. Sensitivity of the algorithm was validated at 90% and specificity at 76% for an injury risk threshold of 2%. It appears that no major differences between Japan and Germany exist for injury estimation based on delta v and impact direction. However, far side impact and multiple crash events appear to be associated with a larger risk increase in the German data.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Nils Lubbe, Toru Kiuchi
URN:urn:nbn:de:hbz:opus-bast-13777
Document Type:Conference Proceeding
Language:English
Date of Publication (online):2015/08/07
Contributing corporation:Toyota Motor Europe
Release Date:2015/08/07
Tag:Deutschland; Fahrzeugteil (Sicherheit); Japan; Konferenz; Prognose; Regressionsanalyse; Schweregrad (Unfall; Unfallfolgemaßnahme; Unfallrekonstruktion; Verletzung; Verletzung)
Accident reconstruction; Conference; Estimation; Germany; Injury; Japan; Post crash; Regression analysis; Severity (accid; Vehicle safety device; injury)
Comment:
Außerdem beteiligt: Toyota Motor Corporation, Vehicle Engineering Development Division
Source:6th International Conference on ESAR 2014
Institutes:Sonstige / Sonstige
Dewey Decimal Classification:6 Technik, Medizin, angewandte Wissenschaften / 62 Ingenieurwissenschaften / 620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
collections:BASt-Beiträge / ITRD Sachgebiete / 84 Personenschäden
BASt-Beiträge / ITRD Sachgebiete / 91 Fahrzeugkonstruktion
BASt-Beiträge / Tagungen / International Conference on ESAR / 6th International Conference on ESAR

$Rev: 13581 $