Pattern recognition for road traffic accident severity in korea

So Young Sohn, Hyungwon Shin

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

An increasing number of road traffic accidents (RTA) in Korea has emerged as being harmful both for the economy and for safety. An accurately estimated classification model for several severity types of RTA as a function of related factors provides crucial information for the prevention of potential accidents. Here, three data-mining techniques (neural network, logistic regression, decision tree) are used to select a set of influential factors and to build up classification models for accident severity. The three approaches are then compared in terms of classification accuracy. The finding is that accuracy does not differ significantly for each model and that the protective device is the most important factor in the accident severity variation.

Original languageEnglish
Pages (from-to)107-117
Number of pages11
JournalErgonomics
Volume44
Issue number1
DOIs
Publication statusPublished - 2001 Jan 1

Fingerprint

pattern recognition
Highway accidents
Traffic Accidents
traffic accident
road traffic
Korea
Pattern recognition
accident
Accidents
Protective Devices
Accident Prevention
Decision Trees
Data Mining
neural network
Decision trees
Logistic Models
logistics
Data mining
Safety
Logistics

All Science Journal Classification (ASJC) codes

  • Human Factors and Ergonomics
  • Physical Therapy, Sports Therapy and Rehabilitation

Cite this

Sohn, So Young ; Shin, Hyungwon. / Pattern recognition for road traffic accident severity in korea. In: Ergonomics. 2001 ; Vol. 44, No. 1. pp. 107-117.
@article{e771aba1a7ce4b49a38816a5624c0d12,
title = "Pattern recognition for road traffic accident severity in korea",
abstract = "An increasing number of road traffic accidents (RTA) in Korea has emerged as being harmful both for the economy and for safety. An accurately estimated classification model for several severity types of RTA as a function of related factors provides crucial information for the prevention of potential accidents. Here, three data-mining techniques (neural network, logistic regression, decision tree) are used to select a set of influential factors and to build up classification models for accident severity. The three approaches are then compared in terms of classification accuracy. The finding is that accuracy does not differ significantly for each model and that the protective device is the most important factor in the accident severity variation.",
author = "Sohn, {So Young} and Hyungwon Shin",
year = "2001",
month = "1",
day = "1",
doi = "10.1080/00140130120928",
language = "English",
volume = "44",
pages = "107--117",
journal = "Ergonomics",
issn = "0014-0139",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

Pattern recognition for road traffic accident severity in korea. / Sohn, So Young; Shin, Hyungwon.

In: Ergonomics, Vol. 44, No. 1, 01.01.2001, p. 107-117.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pattern recognition for road traffic accident severity in korea

AU - Sohn, So Young

AU - Shin, Hyungwon

PY - 2001/1/1

Y1 - 2001/1/1

N2 - An increasing number of road traffic accidents (RTA) in Korea has emerged as being harmful both for the economy and for safety. An accurately estimated classification model for several severity types of RTA as a function of related factors provides crucial information for the prevention of potential accidents. Here, three data-mining techniques (neural network, logistic regression, decision tree) are used to select a set of influential factors and to build up classification models for accident severity. The three approaches are then compared in terms of classification accuracy. The finding is that accuracy does not differ significantly for each model and that the protective device is the most important factor in the accident severity variation.

AB - An increasing number of road traffic accidents (RTA) in Korea has emerged as being harmful both for the economy and for safety. An accurately estimated classification model for several severity types of RTA as a function of related factors provides crucial information for the prevention of potential accidents. Here, three data-mining techniques (neural network, logistic regression, decision tree) are used to select a set of influential factors and to build up classification models for accident severity. The three approaches are then compared in terms of classification accuracy. The finding is that accuracy does not differ significantly for each model and that the protective device is the most important factor in the accident severity variation.

UR - http://www.scopus.com/inward/record.url?scp=0035185594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035185594&partnerID=8YFLogxK

U2 - 10.1080/00140130120928

DO - 10.1080/00140130120928

M3 - Article

C2 - 11214896

AN - SCOPUS:0035185594

VL - 44

SP - 107

EP - 117

JO - Ergonomics

JF - Ergonomics

SN - 0014-0139

IS - 1

ER -