Traffic Accident Location Clustering Based on Improved DBSCAN Algorithm

被引：0

作者：

Huang G. ^{[1
]}

Qu W.-B. ^{[1
]}

Xu H.-Y. ^{[1
]}

机构：

[1] Key Laboratory of Ministry of Public Security for Road Traffic Safety, Traffic Management Research Institute of the Ministry of Public Security, Wuxi

来源：

Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2020年 / 20卷 / 05期

关键词：

Density clustering; Geocoding; Silhouette coefficient; Traffic safety; Urban traffic;

D O I：

10.16097/j.cnki.1009-6744.2020.05.025

中图分类号：

学科分类号：

摘要：

Traffic accident characteristics are significantly affected by regional distribution. In this paper, traffic accident characteristics are clustered by the optimized density-based spatial clustering of applications with noise (DBSCAN) clustering method. The 2019 traffic accident data in Wuxi, China is used as a case study. The open map API is used to obtain the longitude and latitude of the accident location as an input for the proposed method. The traditional DBSCAN clustering algorithm normally requires accurate input of the distance threshold and sample number threshold. This paper develops the DBSCAN clustering model with an adaptive search distance threshold and sample number threshold. The comparison results of the proposed algorithm with traditional algorithm show that the optimized algorithm is more intelligent in determining parameters and more accurate in dividing clusters; the recognition of noise points is more reasonable than the traditional algorithm. The applicability of the algorithm in the geographical location clustering for urban road traffic accidents is proved by calculating the model score of the silhouette coefficient in machine learning. Copyright © 2020 by Science Press.

引用

页码：169 / 176

页数：7

共 9 条

[1] KIM D K., The study of reflecting regional characteristics in car insurance for reduction of traffic accidents, Journal of Korean Society of Transportation, 33, 3, pp. 223-236, (2015)
[2] FANG S E, GUO Z Y, YANG Z., A new identification method for accident prone location on highway, Journal of Traffic and Transportation Engineering, 1, pp. 90-94, (2001)
[3] MILLER TED R., Cost and functional consequences of U.S. roadway crashes, Accidents Analysis and Prevent, 25, 5, pp. 593-607, (1993)
[4] XU C C, WANG W, LIU P., Identifying crash-prone traffic conditions under different weather on freeways, Journal of Safety Research, 46, pp. 135-144, (2013)
[5] MANDLOI D, GUPTA R., Evaluation of accident black spots on roads using geographical information system (GIS), Map India Conference, Transportation, (2003)
[6] YAN J, YUAN H Y, SHU X M, Et al., Optimal clustering algorithm for crime spatial aggregation states analysis, Tsinghua University(Science & Technology), 49, 2, pp. 176-178, (2009)
[7] TIAN Q, GONG Y, KANG M J, Et al., A comparative evaluation of online geocoding services in China, Geomatics and Information Science of Wuhan University, 41, 10, pp. 1351-1358, (2016)
[8] ESTER M, KRIEGEL H P, SANDER J, Et al., A density-based algorithm for discovering clusters in large spatial databases with noise, 2nd International Conference on Knowledge Discovery and Data Mining, pp. 226-231, (1996)
[9] KUMAR K, MSHESH K, REDDY A, MOHAN R., A fast DBSCAN clustering algorithm by accelerating neighbor searching using groups method, Pattern Recognition, 58, pp. 39-48, (2016)

← 1 →