Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea

So Young Sohn, Sung Ho Lee

Research output: Contribution to journalArticle

75 Citations (Scopus)

Abstract

Increasing amount of road traffic in 1990s has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving environmental factors based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we use various algorithms to improve the accuracy of individual classifiers for two categories of severity of road traffic accident. Individual classifiers used are neural network and decision tree. Mainly three different approaches are applied: classifier fusion based on the Dempster-Shafer algorithm, the Bayesian procedure and logistic model; data ensemble fusion based on arcing and bagging; and clustering based on the k-means algorithm. Our empirical study results indicate that a clustering based classification algorithm works best for road traffic accident classification in Korea.

Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalSafety Science
Volume41
Issue number1
DOIs
Publication statusPublished - 2003 Jan 1

Fingerprint

Highway accidents
Traffic Accidents
traffic accident
Data fusion
road traffic
Korea
Cluster Analysis
Accident Prevention
accident prevention
Decision Trees
Classifiers
neural network
Accidents
environmental factors
accident
data analysis
Logistic Models
logistics
road
Safety

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Safety Research
  • Public Health, Environmental and Occupational Health

Cite this

@article{3628de7ff900416795546f12817485d7,
title = "Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea",
abstract = "Increasing amount of road traffic in 1990s has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving environmental factors based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we use various algorithms to improve the accuracy of individual classifiers for two categories of severity of road traffic accident. Individual classifiers used are neural network and decision tree. Mainly three different approaches are applied: classifier fusion based on the Dempster-Shafer algorithm, the Bayesian procedure and logistic model; data ensemble fusion based on arcing and bagging; and clustering based on the k-means algorithm. Our empirical study results indicate that a clustering based classification algorithm works best for road traffic accident classification in Korea.",
author = "Sohn, {So Young} and Lee, {Sung Ho}",
year = "2003",
month = "1",
day = "1",
doi = "10.1016/S0925-7535(01)00032-7",
language = "English",
volume = "41",
pages = "1--14",
journal = "Safety Science",
issn = "0925-7535",
publisher = "Elsevier",
number = "1",

}

Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea. / Sohn, So Young; Lee, Sung Ho.

In: Safety Science, Vol. 41, No. 1, 01.01.2003, p. 1-14.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accidents in Korea

AU - Sohn, So Young

AU - Lee, Sung Ho

PY - 2003/1/1

Y1 - 2003/1/1

N2 - Increasing amount of road traffic in 1990s has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving environmental factors based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we use various algorithms to improve the accuracy of individual classifiers for two categories of severity of road traffic accident. Individual classifiers used are neural network and decision tree. Mainly three different approaches are applied: classifier fusion based on the Dempster-Shafer algorithm, the Bayesian procedure and logistic model; data ensemble fusion based on arcing and bagging; and clustering based on the k-means algorithm. Our empirical study results indicate that a clustering based classification algorithm works best for road traffic accident classification in Korea.

AB - Increasing amount of road traffic in 1990s has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving environmental factors based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we use various algorithms to improve the accuracy of individual classifiers for two categories of severity of road traffic accident. Individual classifiers used are neural network and decision tree. Mainly three different approaches are applied: classifier fusion based on the Dempster-Shafer algorithm, the Bayesian procedure and logistic model; data ensemble fusion based on arcing and bagging; and clustering based on the k-means algorithm. Our empirical study results indicate that a clustering based classification algorithm works best for road traffic accident classification in Korea.

UR - http://www.scopus.com/inward/record.url?scp=0037290189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037290189&partnerID=8YFLogxK

U2 - 10.1016/S0925-7535(01)00032-7

DO - 10.1016/S0925-7535(01)00032-7

M3 - Article

AN - SCOPUS:0037290189

VL - 41

SP - 1

EP - 14

JO - Safety Science

JF - Safety Science

SN - 0925-7535

IS - 1

ER -