A clustering regression approach: A comprehensive injury severity analysis of pedestrian-vehicle crashes in New York, US and Montreal, Canada

被引:223
作者
Mohamed, Mohamed Gomaa [1 ]
Saunier, Nicolas [1 ]
Miranda-Moreno, Luis F. [2 ]
Ukkusuri, Satish V. [3 ]
机构
[1] Ecole Polytech, Dept Civil Geol & Min Engn, Montreal, PQ H3C 3A7, Canada
[2] McGill Univ, Dept Civil Engn & Appl Mech, Montreal, PQ H3A 2K6, Canada
[3] Purdue Univ, Sch Civil Engn, W Lafayette, IN 47907 USA
关键词
Pedestrian safety; Contributing factors; Latent class; Clustering injury severity; Pedestrian-driver characteristics; Built environmental; TRAFFIC CRASHES; MODEL;
D O I
10.1016/j.ssci.2012.11.001
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Understanding the underlying relationship between pedestrian injury severity outcomes and factors leading to more severe injuries is very important in addressing the problem of pedestrian safety. This research combines data mining and statistical regression methods to identify the main factors associated with the levels of pedestrian injury severity outcomes. This work relies on the analysis of two unique pedestrian injury severity datasets from New York City, US (2002-2006) and the City of Montreal, Canada (2003-2006). General injury severity models were estimated for each dataset and for sub-populations obtained through clustering analysis. This paper shows how the segmentation of the accident datasets helps to better understand the complex relationship between the injury severity outcomes and the contribution of geometric, built environment and socio-demographic factors. While using the same methodology for the two datasets, different techniques were tested. Within the New York dataset, a latent class with ordered probit method provides the best results. However, for Montreal, K-means with a multinomial logit model proves most appropriate. Among other results, it was found that pedestrian age, location type, driver age, vehicle type, driver alcohol involvement, lighting conditions, and several built environment characteristics influence the likelihood of fatal crashes. Finally, the research provides recommendations for policy makers, traffic engineers, and law enforcement in order to reduce the severity of pedestrian-vehicle collisions. (C) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:27 / 37
页数:11
相关论文
共 21 条
[1]  
Aziz H., 2012, ACCID ANAL IN PRESS
[2]  
Berkhin P., 2002, SURVEY CLUSTERING DA
[3]  
Borooah VaniK., 2002, Logit and Probit: Ordered and Multinomial Models
[4]   Analysis of traffic injury severity: An application of non-parametric classification tree techniques [J].
Chang, Li-Yen ;
Wang, Hsiu-Wen .
ACCIDENT ANALYSIS AND PREVENTION, 2006, 38 (05) :1019-1027
[5]   Severity of injury resulting from pedestrian-vehicle crashes: What can we learn from examining the built environment? [J].
Clifton, Kelly J. ;
Burnier, Carolina V. ;
Akar, Gulsah .
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT, 2009, 14 (06) :425-436
[6]   Traffic accident segmentation by means of latent class clustering [J].
Depaire, Benoit ;
Wets, Geert ;
Vanhoof, Koen .
ACCIDENT ANALYSIS AND PREVENTION, 2008, 40 (04) :1257-1266
[7]   A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes [J].
Eluru, Naveen ;
Bhat, Chandra R. ;
Hensher, David A. .
ACCIDENT ANALYSIS AND PREVENTION, 2008, 40 (03) :1033-1054
[8]   A latent class modeling approach for identifying vehicle driver injury severity factors at highway-railway crossings [J].
Eluru, Naveen ;
Bagheri, Morteza ;
Miranda-Moreno, Luis F. ;
Fu, Liping .
ACCIDENT ANALYSIS AND PREVENTION, 2012, 47 :119-127
[9]  
Jackman S., 2000, POLITICAL SCI C
[10]   Using a K-means clustering algorithm to examine patterns of pedestrian involved crashes in Honolulu, Hawaii [J].
Kim, Karl ;
Yamashita, Eric Y. .
JOURNAL OF ADVANCED TRANSPORTATION, 2007, 41 (01) :69-89