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

Abstract

Understanding the underlying relationship between pedestrian injury severity outcomes and factors leading to more severe injuries is very important in dealing with the problem of pedestrian safety. To investigate injury severity outcomes, many previous works relied on statistical regression models. There has also been some interest for data mining techniques, in particular for clustering techniques which segment the data into more homogeneous subsets. This research combines these two approaches (data mining and statistical regression methods) to identify the main contributing factors associated with the levels of pedestrian injury severity outcomes. This work relies on the analysis of two unique pedestrian injury severity datasets from the City of New York, US (2002US ( -2006 and the City of Montreal, Canada (2003-2006. General injury severity models were estimated for the whole datasets and for subpopulations obtained through clustering analysis. This paper shows how the segmentation of the accident datasets help to better understand the complex relationship between the injury severity outcomes and the contributing geometric, built environment and socio-demographic factors. While using the same methodology for the two datasets, different techniques were tested. For instance, for New York, latent class with ordered probit method provides the best results. However, for Montreal, the K-means with multinomial logit model is identified as the most appropriate technique. The results show the power of using clustering with regression to provide a complementary and more detailed analysis. Among other results, it was found that pedestrian age, location at intersection, actions prior to accident, driver age, vehicle type, vehicle movement, driver alcohol involvement and lighting conditions have an influence on the likelihood of a fatal crash. Moreover, several features within the built environment are shown to have an effect. Finally, the research provides recommendations for policy makers, traffic engineers, and law enforcement to reduce the severity of pedestrian-vehicle collisions. KEYWORDS:Pedestrian safety, regression, latent class, clustering, severity, built environmental, land use variables Mohamed, Saunier, Miranda-Moreno, Ukkusuri 3 INTRODUCTIONRoad user safety is a primary concern, not only for traffic safety specialists and traffic engineers, but for educators and law enforcement as well. Most importantly, pedestrian safety is a vital traffic issue as all road users are pedestrians at one point or another. Since pedestrians are vulnerable road users and suffer more in road crashes, it is important to understand the factors affecting pedestrian injury severity levels. In this way, traffic engineers, planners, decision makers and law enforcement will be able to precisely target these factors through various counter-measures, such as improvements to motorized vehicles, roadway and pedestrian facility design, control strategies at conflict locations, and driver and pedestrian education programs.This pape...

The Effect of Drivers' Demographic Characteristics on Road Accidents in Different Seasons Using Data Mining

“…Second, based on the variable importance index which identifies the relative importance of each contributed variable in the clustering stage, the following variables were regarded as the most relative factors in accidents: type of region, type of collision, weather condition, road geometric characteristics, road surface condition, and road defects. This is in line with the findings of Xu C et al [11] study, and in total contrast to Mohamed MG et al [13] where none of the foregoing variables were mentioned as effective factors in accident.…”

“…In Iran, as in most countries, the legal age to have could be used to help authorities identify effectively the areas with high accident risks, and serve as reference for town planners as far as road safety is considered. Authors of study [13] combined data mining and statistical regression methods to identify the main factors associated with the levels of pedestrian injury. Based on their research, 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.…”

“…This forms record information on accidents and their causes in five major parts. The data included information regarding the conditions of x 5 Road defects Lack of safety barriers along the road, poor lighting on roads, road erosion, surface defects, bumps, inadequate traffic road signs [20] x 6 Road geometric characteristic Uphill, straight, downhill, flat [21] x 7 Road surface condition Dry, wet, icy, gravel/sand, slush/mud, standing oil, other [22] x 8 Safety equipment No special safety equipment, air bag, ABS break [20] x 9 Road direction One-way, separated two-way, unseparated two-way [19] x 10 General cause of accident Not looking ahead, sudden opening of the car door, exceeding the speed limit, swerve to the left or right, abrupt change in direction [18] x 11 Type of collision Collision with motorcycle/bicycle, two-vehicle collision, multi-vehicle collision, collision with pedestrian, collision with animal, fixed object collision, overturn, fire/explosion [21] x 12 Type of region Mountain, plain, foothill [23] x 13 Type of shoulder No shoulder, asphalt [10] x 14 Vehicle type Mini bus, bus, pickup, light truck, truck, ambulance, truck with trailer, motorcycle, bicycle, agricultural vehicles, highway const. equipment, fire truck, police car, other [20] x 15 Weather conditions Clear, fog, rain, snow, storm, cloud, dust [22] …”

Influence of built environment on pedestrian crashes: A network-based GIS analysis

“…The first step was to identify hotspots of pedestrian crashes using the NKDE implemented in SANET for ArcGIS 10.1 (Okabe, Okunuki, & Shiode, 2006;Okabe et al, 2009) followed by a built-environment audit. Hotspots of pedestrian crashes allow one to target specific areas for further investigation (Mohamed, Saunier, Miranda-Moreno, & Ukkusuri, 2013;Yamada & Thill, 2010). The NKDE used the equal-split continuous kernel method because it is unbiased (Okabe et al, 2009).…”

Analyzing pedestrian crash injury severity at signalized and non-signalized locations

“…The significant variables included roadway width, vehicle type, alcohol involvement, and pedestrian age. Using the same approach, Mohamed et al (2013) used two pedestrian injury severity datasets from New York City, U.S. (2002)(2003)(2004)(2005)(2006) and Montreal, Canada (2003-2006 and applied the ordered probit and multinomial logit models to analyze severity of pedestrian crashes. Several common variables, such as presence of heavy vehicles, absence of lighting, and prevalence of mixed land use, were found to increase the probability of fatal pedestrian crashes in both cities.…”