Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models

Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models

Machine learning algorithms aim to improve the power of predictors over conventional regression models. This study aims to tap the predictive potential of crash mechanism-related variables using ensemble machine learning models. The results demonstrate selected models can predict severity at a high...

Full description

Bibliographic Details
Main Authors: Ang Ji, David Levinson
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Open Journal of Intelligent Transportation Systems
Subjects:
Injury severity
machine learning algorithms
vehicle crashes
ensemble technique
crash mechanisms
Online Access:https://ieeexplore.ieee.org/document/9241829/
id doaj-dd5f9e11a11e44b4b5aaa468c4f9dbb3
record_format Article
spelling doaj-dd5f9e11a11e44b4b5aaa468c4f9dbb32021-03-29T16:59:39ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132020-01-01121722610.1109/OJITS.2020.30335239241829Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble ModelsAng Ji0https://orcid.org/0000-0002-7943-7461David Levinson1https://orcid.org/0000-0002-4563-2963School of Civil Engineering, The University of Sydney, Sydney, NSW, AustraliaSchool of Civil Engineering, The University of Sydney, Sydney, NSW, AustraliaMachine learning algorithms aim to improve the power of predictors over conventional regression models. This study aims to tap the predictive potential of crash mechanism-related variables using ensemble machine learning models. The results demonstrate selected models can predict severity at a high level of accuracy. The stacking model with a linear blender is preferred for the designed ensemble combination. Most bagging, boosting, and stacking algorithms perform well, indicating ensemble models are capable of improving upon individual models.https://ieeexplore.ieee.org/document/9241829/Injury severitymachine learning algorithmsvehicle crashesensemble techniquecrash mechanisms
collection DOAJ
language English
format Article
sources DOAJ
author Ang Ji
David Levinson
spellingShingle Ang Ji
David Levinson
Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
IEEE Open Journal of Intelligent Transportation Systems
Injury severity
machine learning algorithms
vehicle crashes
ensemble technique
crash mechanisms
author_facet Ang Ji
David Levinson
author_sort Ang Ji
title Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
title_short Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
title_full Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
title_fullStr Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
title_full_unstemmed Injury Severity Prediction From Two-Vehicle Crash Mechanisms With Machine Learning and Ensemble Models
title_sort injury severity prediction from two-vehicle crash mechanisms with machine learning and ensemble models
publisher IEEE
series IEEE Open Journal of Intelligent Transportation Systems
issn 2687-7813
publishDate 2020-01-01
description Machine learning algorithms aim to improve the power of predictors over conventional regression models. This study aims to tap the predictive potential of crash mechanism-related variables using ensemble machine learning models. The results demonstrate selected models can predict severity at a high level of accuracy. The stacking model with a linear blender is preferred for the designed ensemble combination. Most bagging, boosting, and stacking algorithms perform well, indicating ensemble models are capable of improving upon individual models.
topic Injury severity
machine learning algorithms
vehicle crashes
ensemble technique
crash mechanisms
url https://ieeexplore.ieee.org/document/9241829/
work_keys_str_mv AT angji injuryseveritypredictionfromtwovehiclecrashmechanismswithmachinelearningandensemblemodels
AT davidlevinson injuryseveritypredictionfromtwovehiclecrashmechanismswithmachinelearningandensemblemodels
_version_ 1724198469701206016

Similar Items