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...

Full description

Saved in:

Bibliographic Details
Published in:	Accident analysis and prevention Vol. 122; pp. 226 - 238
Main Authors:	Tang, Jinjun, Liang, Jian, Han, Chunyang, Li, Zhibin, Huang, Helai
Format:	Journal Article
Language:	English
Published:	England Elsevier Ltd 01.01.2019
Subjects:	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 Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!