Modeling of time-dependent safety performance using anonymized and aggregated smartphone-based dangerous driving event data

Di Yang, Kun Xie, Kaan Ozbay, Hong Yang, Noah Budnick

Research output: Contribution to journalArticle

Abstract

Safety performance functions (SPFs) are generally used to relate exposure to the expected number of crashes aggregated over a long time (e.g. a year) by holding all other risk factors constant, and to identify hotspots that have excessive crashes regardless of different time periods. However, it is highly likely that the relationships of exposure, risk factors and crash occurrence can vary across different times of day. This study aims to establish time-dependent SPFs for urban roads by using large-scale dangerous driving event data captured by smartphones in different times of day. Multivariate conditional autoregressive (MVCAR) models are developed to jointly account for spatial and temporal dependence of crash observations. Results of two-sample Kolmogorov-Smirnov tests affirm the heterogeneity of the safety effects of dangerous driving events in different time periods. Time-dependent hotspots are identified using potential for safety improvement (PSI) metric. The assumption here is that due to the change of traffic conditions and environment across different times of day, safety hotspots for different time periods should be different from each other. According to the results of Wilcoxon signed-rank tests, hotspots identified by times of day are found to be mostly different from each other. The findings of this study provide insights into temporal effects of risk factors and can support the development of time-dependent safety countermeasures. Besides, this study also shows the potential of leveraging anonymized and aggregated dangerous driving data to assess traffic safety issues.

Original languageEnglish (US)
Article number105286
JournalAccident Analysis and Prevention
Volume132
DOIs
StatePublished - Nov 1 2019

Fingerprint

Smartphones
time of day
Safety
event
performance
Nonparametric Statistics
traffic safety
time
Smartphone
road
traffic

Keywords

  • Connected vehicles
  • Dangerous driving events
  • Multivariate conditional autoregressive model
  • Safety performance functions
  • Time-dependent hotspots

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Safety, Risk, Reliability and Quality
  • Public Health, Environmental and Occupational Health
  • Law

Cite this

Modeling of time-dependent safety performance using anonymized and aggregated smartphone-based dangerous driving event data. / Yang, Di; Xie, Kun; Ozbay, Kaan; Yang, Hong; Budnick, Noah.

In: Accident Analysis and Prevention, Vol. 132, 105286, 01.11.2019.

Research output: Contribution to journalArticle

@article{59c7e9fa20f8427490b56e3351dd62b0,
title = "Modeling of time-dependent safety performance using anonymized and aggregated smartphone-based dangerous driving event data",
abstract = "Safety performance functions (SPFs) are generally used to relate exposure to the expected number of crashes aggregated over a long time (e.g. a year) by holding all other risk factors constant, and to identify hotspots that have excessive crashes regardless of different time periods. However, it is highly likely that the relationships of exposure, risk factors and crash occurrence can vary across different times of day. This study aims to establish time-dependent SPFs for urban roads by using large-scale dangerous driving event data captured by smartphones in different times of day. Multivariate conditional autoregressive (MVCAR) models are developed to jointly account for spatial and temporal dependence of crash observations. Results of two-sample Kolmogorov-Smirnov tests affirm the heterogeneity of the safety effects of dangerous driving events in different time periods. Time-dependent hotspots are identified using potential for safety improvement (PSI) metric. The assumption here is that due to the change of traffic conditions and environment across different times of day, safety hotspots for different time periods should be different from each other. According to the results of Wilcoxon signed-rank tests, hotspots identified by times of day are found to be mostly different from each other. The findings of this study provide insights into temporal effects of risk factors and can support the development of time-dependent safety countermeasures. Besides, this study also shows the potential of leveraging anonymized and aggregated dangerous driving data to assess traffic safety issues.",
keywords = "Connected vehicles, Dangerous driving events, Multivariate conditional autoregressive model, Safety performance functions, Time-dependent hotspots",
author = "Di Yang and Kun Xie and Kaan Ozbay and Hong Yang and Noah Budnick",
year = "2019",
month = "11",
day = "1",
doi = "10.1016/j.aap.2019.105286",
language = "English (US)",
volume = "132",
journal = "Accident Analysis and Prevention",
issn = "0001-4575",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Modeling of time-dependent safety performance using anonymized and aggregated smartphone-based dangerous driving event data

AU - Yang, Di

AU - Xie, Kun

AU - Ozbay, Kaan

AU - Yang, Hong

AU - Budnick, Noah

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Safety performance functions (SPFs) are generally used to relate exposure to the expected number of crashes aggregated over a long time (e.g. a year) by holding all other risk factors constant, and to identify hotspots that have excessive crashes regardless of different time periods. However, it is highly likely that the relationships of exposure, risk factors and crash occurrence can vary across different times of day. This study aims to establish time-dependent SPFs for urban roads by using large-scale dangerous driving event data captured by smartphones in different times of day. Multivariate conditional autoregressive (MVCAR) models are developed to jointly account for spatial and temporal dependence of crash observations. Results of two-sample Kolmogorov-Smirnov tests affirm the heterogeneity of the safety effects of dangerous driving events in different time periods. Time-dependent hotspots are identified using potential for safety improvement (PSI) metric. The assumption here is that due to the change of traffic conditions and environment across different times of day, safety hotspots for different time periods should be different from each other. According to the results of Wilcoxon signed-rank tests, hotspots identified by times of day are found to be mostly different from each other. The findings of this study provide insights into temporal effects of risk factors and can support the development of time-dependent safety countermeasures. Besides, this study also shows the potential of leveraging anonymized and aggregated dangerous driving data to assess traffic safety issues.

AB - Safety performance functions (SPFs) are generally used to relate exposure to the expected number of crashes aggregated over a long time (e.g. a year) by holding all other risk factors constant, and to identify hotspots that have excessive crashes regardless of different time periods. However, it is highly likely that the relationships of exposure, risk factors and crash occurrence can vary across different times of day. This study aims to establish time-dependent SPFs for urban roads by using large-scale dangerous driving event data captured by smartphones in different times of day. Multivariate conditional autoregressive (MVCAR) models are developed to jointly account for spatial and temporal dependence of crash observations. Results of two-sample Kolmogorov-Smirnov tests affirm the heterogeneity of the safety effects of dangerous driving events in different time periods. Time-dependent hotspots are identified using potential for safety improvement (PSI) metric. The assumption here is that due to the change of traffic conditions and environment across different times of day, safety hotspots for different time periods should be different from each other. According to the results of Wilcoxon signed-rank tests, hotspots identified by times of day are found to be mostly different from each other. The findings of this study provide insights into temporal effects of risk factors and can support the development of time-dependent safety countermeasures. Besides, this study also shows the potential of leveraging anonymized and aggregated dangerous driving data to assess traffic safety issues.

KW - Connected vehicles

KW - Dangerous driving events

KW - Multivariate conditional autoregressive model

KW - Safety performance functions

KW - Time-dependent hotspots

UR - http://www.scopus.com/inward/record.url?scp=85071534023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071534023&partnerID=8YFLogxK

U2 - 10.1016/j.aap.2019.105286

DO - 10.1016/j.aap.2019.105286

M3 - Article

C2 - 31487665

AN - SCOPUS:85071534023

VL - 132

JO - Accident Analysis and Prevention

JF - Accident Analysis and Prevention

SN - 0001-4575

M1 - 105286

ER -