Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks

Dursun Delen, Ramesh Sharda, Max Bessonov

Research output: Contribution to journalArticle

173 Citations (Scopus)

Abstract

Understanding the circumstances under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Factors that affect the risk of increased injury of occupants in the event of an automotive accident include demographic or behavioral characteristics of the person, environmental factors and roadway conditions at the time of the accident occurrence, technical characteristics of the vehicle itself, among others. This study uses a series of artificial neural networks to model the potentially non-linear relationships between the injury severity levels and crash-related factors. It then conducts sensitivity analysis on the trained neural network models to identify the prioritized importance of crash-related factors as they apply to different injury severity levels. In the process, the problem of five-class prediction is decomposed into a set of binary prediction models (using a nationally representative sample of 30 358 police-recorded crash reports) in order to obtain the granularity of information needed to identify the "true" cause and effect relationships between the crash-related factors and different levels of injury severity. The results, mostly validated by the findings of previous studies, provide insight into the changing importance of crash factors with the changing injury severity levels.

Original languageEnglish
Pages (from-to)434-444
Number of pages11
JournalAccident Analysis and Prevention
Volume38
Issue number3
DOIs
StatePublished - 1 May 2006
Externally publishedYes

Fingerprint

Highway accidents
Traffic Accidents
traffic accident
neural network
Accidents
accident
Neural networks
Wounds and Injuries
Neural Networks (Computer)
Law enforcement
Automobiles
Sensitivity analysis
motor vehicle
environmental factors
police
driver
Police
cause
human being
event

Keywords

  • Artificial neural networks
  • Classification
  • Injury severity
  • Problem decomposition
  • Sensitivity analysis

Cite this

@article{e387a1c0d50940eca278358105fad5f5,
title = "Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks",
abstract = "Understanding the circumstances under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Factors that affect the risk of increased injury of occupants in the event of an automotive accident include demographic or behavioral characteristics of the person, environmental factors and roadway conditions at the time of the accident occurrence, technical characteristics of the vehicle itself, among others. This study uses a series of artificial neural networks to model the potentially non-linear relationships between the injury severity levels and crash-related factors. It then conducts sensitivity analysis on the trained neural network models to identify the prioritized importance of crash-related factors as they apply to different injury severity levels. In the process, the problem of five-class prediction is decomposed into a set of binary prediction models (using a nationally representative sample of 30 358 police-recorded crash reports) in order to obtain the granularity of information needed to identify the {"}true{"} cause and effect relationships between the crash-related factors and different levels of injury severity. The results, mostly validated by the findings of previous studies, provide insight into the changing importance of crash factors with the changing injury severity levels.",
keywords = "Artificial neural networks, Classification, Injury severity, Problem decomposition, Sensitivity analysis",
author = "Dursun Delen and Ramesh Sharda and Max Bessonov",
year = "2006",
month = "5",
day = "1",
doi = "10.1016/j.aap.2005.06.024",
language = "English",
volume = "38",
pages = "434--444",
journal = "Accident Analysis and Prevention",
issn = "0001-4575",
publisher = "Elsevier Ltd",
number = "3",

}

Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. / Delen, Dursun; Sharda, Ramesh; Bessonov, Max.

In: Accident Analysis and Prevention, Vol. 38, No. 3, 01.05.2006, p. 434-444.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks

AU - Delen, Dursun

AU - Sharda, Ramesh

AU - Bessonov, Max

PY - 2006/5/1

Y1 - 2006/5/1

N2 - Understanding the circumstances under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Factors that affect the risk of increased injury of occupants in the event of an automotive accident include demographic or behavioral characteristics of the person, environmental factors and roadway conditions at the time of the accident occurrence, technical characteristics of the vehicle itself, among others. This study uses a series of artificial neural networks to model the potentially non-linear relationships between the injury severity levels and crash-related factors. It then conducts sensitivity analysis on the trained neural network models to identify the prioritized importance of crash-related factors as they apply to different injury severity levels. In the process, the problem of five-class prediction is decomposed into a set of binary prediction models (using a nationally representative sample of 30 358 police-recorded crash reports) in order to obtain the granularity of information needed to identify the "true" cause and effect relationships between the crash-related factors and different levels of injury severity. The results, mostly validated by the findings of previous studies, provide insight into the changing importance of crash factors with the changing injury severity levels.

AB - Understanding the circumstances under which drivers and passengers are more likely to be killed or more severely injured in an automobile accident can help improve the overall driving safety situation. Factors that affect the risk of increased injury of occupants in the event of an automotive accident include demographic or behavioral characteristics of the person, environmental factors and roadway conditions at the time of the accident occurrence, technical characteristics of the vehicle itself, among others. This study uses a series of artificial neural networks to model the potentially non-linear relationships between the injury severity levels and crash-related factors. It then conducts sensitivity analysis on the trained neural network models to identify the prioritized importance of crash-related factors as they apply to different injury severity levels. In the process, the problem of five-class prediction is decomposed into a set of binary prediction models (using a nationally representative sample of 30 358 police-recorded crash reports) in order to obtain the granularity of information needed to identify the "true" cause and effect relationships between the crash-related factors and different levels of injury severity. The results, mostly validated by the findings of previous studies, provide insight into the changing importance of crash factors with the changing injury severity levels.

KW - Artificial neural networks

KW - Classification

KW - Injury severity

KW - Problem decomposition

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=33644889643&partnerID=8YFLogxK

U2 - 10.1016/j.aap.2005.06.024

DO - 10.1016/j.aap.2005.06.024

M3 - Article

C2 - 16337137

AN - SCOPUS:33644889643

VL - 38

SP - 434

EP - 444

JO - Accident Analysis and Prevention

JF - Accident Analysis and Prevention

SN - 0001-4575

IS - 3

ER -