A data-driven, kinematic feature-based, near real-time algorithm for injury severity prediction of vehicle occupants

•Accurate prediction on injury severity is a prerequisite for enhancing road traffic safety.•We designed a two-phase framework consisting of CNN-based model construction and kinematic feature extraction.•We built an SVM-based algorithm, obtaining 85.4 % prediction accuracy in 1.2 ms.•The proposed al...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Accident analysis and prevention 2021-06, Vol.156, p.106149-106149, Article 106149
Hauptverfasser:	Wang, Qingfan, Gan, Shun, Chen, Wentao, Li, Quan, Nie, Bingbing
Format:	Artikel
Sprache:	eng
Schlagworte:	Injury risk Machine-learning algorithms Motor vehicle crashes Occupant protection Prediction models
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!