TY  - CONF
A1  - Lubbe, Nils
A1  - Kiuchi, Toru
T1  - Injury estimation for Advanced Automatic Collision Notification (AACN) in Germany
N2  - 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.
KW  - Deutschland
KW  - Fahrzeugteil (Sicherheit)
KW  - Japan
KW  - Konferenz
KW  - Prognose
KW  - Regressionsanalyse
KW  - Schweregrad (Unfall
KW  - Verletzung)
KW  - Unfallfolgemaßnahme
KW  - Unfallrekonstruktion
KW  - Verletzung
KW  - Accident reconstruction
KW  - Conference
KW  - Estimation
KW  - Germany
KW  - Injury
KW  - Japan
KW  - Post crash
KW  - Regression analysis
KW  - Severity (accid
KW  - injury)
KW  - Vehicle safety device
Y1  - 2015
UR  - https://bast.opus.hbz-nrw.de/frontdoor/index/index/docId/1377
UR  - https://nbn-resolving.org/urn:nbn:de:hbz:opus-bast-13777
N1  - Außerdem beteiligt: Toyota Motor Corporation, Vehicle Engineering Development Division
ER  -