Pedestrian Spatial Violation Analyses for Urban RoadwaysSource: Journal of Transportation Engineering, Part A: Systems:;2020:;Volume ( 146 ):;issue: 011DOI: 10.1061/JTEPBS.0000400Publisher: ASCE
Abstract: This study presents an investigation regarding the critical contributing factors in pedestrian spatial violations based on field observation of 15,090 samples at 14 roadway segments in Shanghai, China. A violation prediction model was applied to predict the impacts of roadway geometry design and traffic on the number of violations, and a real-time pedestrian violation prediction model was used to predict whether a pedestrian would spatially violate. For the violation prediction model, a Bayesian Poisson-lognormal model was used, and for the real-time pedestrian violation prediction model, a Bayesian logistic regression model was adopted. Then, random forest was employed to rank the importance of factors that are significant in violation prediction. The results showed that the presence of median, land use type, and number of lanes are the most significant variables in spatial violation. The findings of this study can provide a basis for traffic practitioners, researchers, and authorities to analyze the reasons for pedestrians’ spatial violations and develop guidelines for crossings design.
|
Show full item record
contributor author | Ling Wang | |
contributor author | Hao Zhong | |
contributor author | Wangyue Huang | |
contributor author | Wanjing Ma | |
date accessioned | 2022-01-30T21:23:46Z | |
date available | 2022-01-30T21:23:46Z | |
date issued | 11/1/2020 12:00:00 AM | |
identifier other | JTEPBS.0000400.pdf | |
identifier uri | http://yetl.yabesh.ir/yetl1/handle/yetl/4268125 | |
description abstract | This study presents an investigation regarding the critical contributing factors in pedestrian spatial violations based on field observation of 15,090 samples at 14 roadway segments in Shanghai, China. A violation prediction model was applied to predict the impacts of roadway geometry design and traffic on the number of violations, and a real-time pedestrian violation prediction model was used to predict whether a pedestrian would spatially violate. For the violation prediction model, a Bayesian Poisson-lognormal model was used, and for the real-time pedestrian violation prediction model, a Bayesian logistic regression model was adopted. Then, random forest was employed to rank the importance of factors that are significant in violation prediction. The results showed that the presence of median, land use type, and number of lanes are the most significant variables in spatial violation. The findings of this study can provide a basis for traffic practitioners, researchers, and authorities to analyze the reasons for pedestrians’ spatial violations and develop guidelines for crossings design. | |
publisher | ASCE | |
title | Pedestrian Spatial Violation Analyses for Urban Roadways | |
type | Journal Paper | |
journal volume | 146 | |
journal issue | 11 | |
journal title | Journal of Transportation Engineering, Part A: Systems | |
identifier doi | 10.1061/JTEPBS.0000400 | |
page | 6 | |
tree | Journal of Transportation Engineering, Part A: Systems:;2020:;Volume ( 146 ):;issue: 011 | |
contenttype | Fulltext |