Crash injury severity analysis using a two-layer Stacking framework

•A two-layer Stacking model is proposed to predict crash injury severity.•The fist layer combines three classification methods: RF, AdaBoost and GBDT.•The second layer predicts crash injury severity based on a Logistic Regression model.•Several traditional models are compared in binary and multi cla...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Accident analysis and prevention Jg. 122; S. 226 - 238
Hauptverfasser:	Tang, Jinjun, Liang, Jian, Han, Chunyang, Li, Zhibin, Huang, Helai
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	England Elsevier Ltd 01.01.2019
Schlagworte:	Accidents, Traffic - classification Accidents, Traffic - statistics & numerical data Adaptive Boosting Built Environment - statistics & numerical data Crash injury severity Decision Trees Gradient Boosting Decision Tree Humans Injury Severity Score Logistic Models Neural Networks (Computer) Random Forests Severity classification Stacking model Support Vector Machine Wounds and Injuries - classification Wounds and Injuries - epidemiology Severity classification Crash injury severity Random Forests Adaptive Boosting Stacking model Gradient Boosting Decision Tree
ISSN:	0001-4575, 1879-2057, 1879-2057
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!