Development and application of traffic accident density estimation models using kernel density estimation

Seiji Hashimoto, Syuji Yoshiki, Ryoko Saeki, Yasuhiro Mimura, Ryosuke Ando, Shutaro Nanba

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Traffic accident frequency has been decreasing in Japan in recent years. Nevertheless, many accidents still occur on residential roads. Area-wide traffic calming measures including Zone 30, which discourages traffic by setting a speed limit of 30 km/h in residential areas, have been implemented. However, no objective implementation method has been established. Development of a model for traffic accident density estimation explained by GIS data can enable the determination of dangerous areas objectively and easily, indicating where area-wide traffic calming can be implemented preferentially. This study examined the relations between traffic accidents and city characteristics, such as population, road factors, and spatial factors. A model was developed to estimate traffic accident density. Kernel density estimation (KDE) techniques were used to assess the relations efficiently. Besides, 16 models were developed by combining accident locations, accident types, and data types. By using them, the applicability of traffic accident density estimation models was examined. Results obtained using Spearman rank correlation show high coefficients between the predicted number and the actual number. The model can indicate the relative accident risk in cities. Results of this study can be used for objective determination of areas where area-wide traffic calming can be implemented preferentially, even if sufficient traffic accident data are not available.

Original languageEnglish
Pages (from-to)262-270
Number of pages9
JournalJournal of Traffic and Transportation Engineering (English Edition)
Volume3
Issue number3
DOIs
Publication statusPublished - Jun 1 2016

Fingerprint

Highway accidents
traffic accident
traffic calming
Accidents
accident
road
accident frequency
accident risk
speed limit
residential area
estimation procedure
Geographic information systems
Geographical Information System
Japan
traffic

Keywords

  • Hotspots
  • Kernel density estimation (KDE)
  • Traffic safety
  • Zone 30

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Transportation

Cite this

Development and application of traffic accident density estimation models using kernel density estimation. / Hashimoto, Seiji; Yoshiki, Syuji; Saeki, Ryoko; Mimura, Yasuhiro; Ando, Ryosuke; Nanba, Shutaro.

In: Journal of Traffic and Transportation Engineering (English Edition), Vol. 3, No. 3, 01.06.2016, p. 262-270.

Research output: Contribution to journalArticle

Hashimoto, Seiji ; Yoshiki, Syuji ; Saeki, Ryoko ; Mimura, Yasuhiro ; Ando, Ryosuke ; Nanba, Shutaro. / Development and application of traffic accident density estimation models using kernel density estimation. In: Journal of Traffic and Transportation Engineering (English Edition). 2016 ; Vol. 3, No. 3. pp. 262-270.
@article{76601db426a94a669293bf449be0b33c,
title = "Development and application of traffic accident density estimation models using kernel density estimation",
abstract = "Traffic accident frequency has been decreasing in Japan in recent years. Nevertheless, many accidents still occur on residential roads. Area-wide traffic calming measures including Zone 30, which discourages traffic by setting a speed limit of 30 km/h in residential areas, have been implemented. However, no objective implementation method has been established. Development of a model for traffic accident density estimation explained by GIS data can enable the determination of dangerous areas objectively and easily, indicating where area-wide traffic calming can be implemented preferentially. This study examined the relations between traffic accidents and city characteristics, such as population, road factors, and spatial factors. A model was developed to estimate traffic accident density. Kernel density estimation (KDE) techniques were used to assess the relations efficiently. Besides, 16 models were developed by combining accident locations, accident types, and data types. By using them, the applicability of traffic accident density estimation models was examined. Results obtained using Spearman rank correlation show high coefficients between the predicted number and the actual number. The model can indicate the relative accident risk in cities. Results of this study can be used for objective determination of areas where area-wide traffic calming can be implemented preferentially, even if sufficient traffic accident data are not available.",
keywords = "Hotspots, Kernel density estimation (KDE), Traffic safety, Zone 30",
author = "Seiji Hashimoto and Syuji Yoshiki and Ryoko Saeki and Yasuhiro Mimura and Ryosuke Ando and Shutaro Nanba",
year = "2016",
month = "6",
day = "1",
doi = "10.1016/j.jtte.2016.01.005",
language = "English",
volume = "3",
pages = "262--270",
journal = "Journal of Traffic and Transportation Engineering (English Edition)",
issn = "2095-7564",
publisher = "Elsevier BV",
number = "3",

}

TY - JOUR

T1 - Development and application of traffic accident density estimation models using kernel density estimation

AU - Hashimoto, Seiji

AU - Yoshiki, Syuji

AU - Saeki, Ryoko

AU - Mimura, Yasuhiro

AU - Ando, Ryosuke

AU - Nanba, Shutaro

PY - 2016/6/1

Y1 - 2016/6/1

N2 - Traffic accident frequency has been decreasing in Japan in recent years. Nevertheless, many accidents still occur on residential roads. Area-wide traffic calming measures including Zone 30, which discourages traffic by setting a speed limit of 30 km/h in residential areas, have been implemented. However, no objective implementation method has been established. Development of a model for traffic accident density estimation explained by GIS data can enable the determination of dangerous areas objectively and easily, indicating where area-wide traffic calming can be implemented preferentially. This study examined the relations between traffic accidents and city characteristics, such as population, road factors, and spatial factors. A model was developed to estimate traffic accident density. Kernel density estimation (KDE) techniques were used to assess the relations efficiently. Besides, 16 models were developed by combining accident locations, accident types, and data types. By using them, the applicability of traffic accident density estimation models was examined. Results obtained using Spearman rank correlation show high coefficients between the predicted number and the actual number. The model can indicate the relative accident risk in cities. Results of this study can be used for objective determination of areas where area-wide traffic calming can be implemented preferentially, even if sufficient traffic accident data are not available.

AB - Traffic accident frequency has been decreasing in Japan in recent years. Nevertheless, many accidents still occur on residential roads. Area-wide traffic calming measures including Zone 30, which discourages traffic by setting a speed limit of 30 km/h in residential areas, have been implemented. However, no objective implementation method has been established. Development of a model for traffic accident density estimation explained by GIS data can enable the determination of dangerous areas objectively and easily, indicating where area-wide traffic calming can be implemented preferentially. This study examined the relations between traffic accidents and city characteristics, such as population, road factors, and spatial factors. A model was developed to estimate traffic accident density. Kernel density estimation (KDE) techniques were used to assess the relations efficiently. Besides, 16 models were developed by combining accident locations, accident types, and data types. By using them, the applicability of traffic accident density estimation models was examined. Results obtained using Spearman rank correlation show high coefficients between the predicted number and the actual number. The model can indicate the relative accident risk in cities. Results of this study can be used for objective determination of areas where area-wide traffic calming can be implemented preferentially, even if sufficient traffic accident data are not available.

KW - Hotspots

KW - Kernel density estimation (KDE)

KW - Traffic safety

KW - Zone 30

UR - http://www.scopus.com/inward/record.url?scp=85018302920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018302920&partnerID=8YFLogxK

U2 - 10.1016/j.jtte.2016.01.005

DO - 10.1016/j.jtte.2016.01.005

M3 - Article

VL - 3

SP - 262

EP - 270

JO - Journal of Traffic and Transportation Engineering (English Edition)

JF - Journal of Traffic and Transportation Engineering (English Edition)

SN - 2095-7564

IS - 3

ER -