A Bayesian Network model for contextual versus non-contextual driving behavior assessment

Xiaoyu Zhu, Yifei Yuan, Xianbiao Hu, Yi Chang Chiu, Yu Luen Ma

Research output: Research - peer-reviewArticle

  • 2 Citations

Abstract

Driving behavior is generally considered to be one of the most important factors in crash occurrence. This paper aims to evaluate the benefits of utilizing context-relevant information in the driving behavior assessment process (i.e. contextual driving behavior assessment approach). We use a Bayesian Network (BN) model that investigates the relationships between GPS driving observations, individual driving behavior, individual driving risks, and individual crash frequency. In contrast to prior studies without context information (i.e. non-contextual approach), the data used in the BN approach is a combination of contextual features in the surrounding environment that may contribute to crash risk, such as road conditions surrounding the vehicle of interest and dynamic traffic flow information, as well as the non-contextual data such as instantaneous driving speed and the acceleration/deceleration of a vehicle. An information-aggregation mechanism is developed to aggregates massive amounts of vehicle GPS data points, kinematic events and context information into drivel-level data. With the proposed model, driving behavior risks for drivers is assessed and the relationship between contextual driving behavior and crash occurrence is established. The analysis results in the case study section show that the contextual model has significantly better performance than the non-contextual model, and that drivers who drive at a speed faster than others or much slower than the speed limit at the ramp, and with more rapid acceleration or deceleration on freeways are more likely to be involved in crash events. In addition, younger drivers, and female drivers with higher VMT are found to have higher crash risk.

LanguageEnglish (US)
Pages172-187
Number of pages16
JournalTransportation Research Part C: Emerging Technologies
Volume81
DOIs
StatePublished - Aug 1 2017

Fingerprint

Bayesian networks
Network model
Crash
traffic behavior
driver
Deceleration
Global positioning system
event
Highway systems
Kinematics
Agglomeration
Factors
Information aggregation
Traffic flow
Roads
Individual behaviour
speed limit
information flow
aggregation
road

Keywords

  • Bayesian Network model
  • Contextual driving risk analysis
  • Information-aggregation
  • Regression models

ASJC Scopus subject areas

  • Automotive Engineering
  • Transportation
  • Computer Science Applications
  • Management Science and Operations Research

Cite this

A Bayesian Network model for contextual versus non-contextual driving behavior assessment. / Zhu, Xiaoyu; Yuan, Yifei; Hu, Xianbiao; Chiu, Yi Chang; Ma, Yu Luen.

In: Transportation Research Part C: Emerging Technologies, Vol. 81, 01.08.2017, p. 172-187.

Research output: Research - peer-reviewArticle

@article{7a5fad8342d348ff870f2e9563de2bf0,
title = "A Bayesian Network model for contextual versus non-contextual driving behavior assessment",
abstract = "Driving behavior is generally considered to be one of the most important factors in crash occurrence. This paper aims to evaluate the benefits of utilizing context-relevant information in the driving behavior assessment process (i.e. contextual driving behavior assessment approach). We use a Bayesian Network (BN) model that investigates the relationships between GPS driving observations, individual driving behavior, individual driving risks, and individual crash frequency. In contrast to prior studies without context information (i.e. non-contextual approach), the data used in the BN approach is a combination of contextual features in the surrounding environment that may contribute to crash risk, such as road conditions surrounding the vehicle of interest and dynamic traffic flow information, as well as the non-contextual data such as instantaneous driving speed and the acceleration/deceleration of a vehicle. An information-aggregation mechanism is developed to aggregates massive amounts of vehicle GPS data points, kinematic events and context information into drivel-level data. With the proposed model, driving behavior risks for drivers is assessed and the relationship between contextual driving behavior and crash occurrence is established. The analysis results in the case study section show that the contextual model has significantly better performance than the non-contextual model, and that drivers who drive at a speed faster than others or much slower than the speed limit at the ramp, and with more rapid acceleration or deceleration on freeways are more likely to be involved in crash events. In addition, younger drivers, and female drivers with higher VMT are found to have higher crash risk.",
keywords = "Bayesian Network model, Contextual driving risk analysis, Information-aggregation, Regression models",
author = "Xiaoyu Zhu and Yifei Yuan and Xianbiao Hu and Chiu, {Yi Chang} and Ma, {Yu Luen}",
year = "2017",
month = "8",
doi = "10.1016/j.trc.2017.05.015",
volume = "81",
pages = "172--187",
journal = "Transportation Research Part C: Emerging Technologies",
issn = "0968-090X",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A Bayesian Network model for contextual versus non-contextual driving behavior assessment

AU - Zhu,Xiaoyu

AU - Yuan,Yifei

AU - Hu,Xianbiao

AU - Chiu,Yi Chang

AU - Ma,Yu Luen

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Driving behavior is generally considered to be one of the most important factors in crash occurrence. This paper aims to evaluate the benefits of utilizing context-relevant information in the driving behavior assessment process (i.e. contextual driving behavior assessment approach). We use a Bayesian Network (BN) model that investigates the relationships between GPS driving observations, individual driving behavior, individual driving risks, and individual crash frequency. In contrast to prior studies without context information (i.e. non-contextual approach), the data used in the BN approach is a combination of contextual features in the surrounding environment that may contribute to crash risk, such as road conditions surrounding the vehicle of interest and dynamic traffic flow information, as well as the non-contextual data such as instantaneous driving speed and the acceleration/deceleration of a vehicle. An information-aggregation mechanism is developed to aggregates massive amounts of vehicle GPS data points, kinematic events and context information into drivel-level data. With the proposed model, driving behavior risks for drivers is assessed and the relationship between contextual driving behavior and crash occurrence is established. The analysis results in the case study section show that the contextual model has significantly better performance than the non-contextual model, and that drivers who drive at a speed faster than others or much slower than the speed limit at the ramp, and with more rapid acceleration or deceleration on freeways are more likely to be involved in crash events. In addition, younger drivers, and female drivers with higher VMT are found to have higher crash risk.

AB - Driving behavior is generally considered to be one of the most important factors in crash occurrence. This paper aims to evaluate the benefits of utilizing context-relevant information in the driving behavior assessment process (i.e. contextual driving behavior assessment approach). We use a Bayesian Network (BN) model that investigates the relationships between GPS driving observations, individual driving behavior, individual driving risks, and individual crash frequency. In contrast to prior studies without context information (i.e. non-contextual approach), the data used in the BN approach is a combination of contextual features in the surrounding environment that may contribute to crash risk, such as road conditions surrounding the vehicle of interest and dynamic traffic flow information, as well as the non-contextual data such as instantaneous driving speed and the acceleration/deceleration of a vehicle. An information-aggregation mechanism is developed to aggregates massive amounts of vehicle GPS data points, kinematic events and context information into drivel-level data. With the proposed model, driving behavior risks for drivers is assessed and the relationship between contextual driving behavior and crash occurrence is established. The analysis results in the case study section show that the contextual model has significantly better performance than the non-contextual model, and that drivers who drive at a speed faster than others or much slower than the speed limit at the ramp, and with more rapid acceleration or deceleration on freeways are more likely to be involved in crash events. In addition, younger drivers, and female drivers with higher VMT are found to have higher crash risk.

KW - Bayesian Network model

KW - Contextual driving risk analysis

KW - Information-aggregation

KW - Regression models

UR - http://www.scopus.com/inward/record.url?scp=85020410865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020410865&partnerID=8YFLogxK

U2 - 10.1016/j.trc.2017.05.015

DO - 10.1016/j.trc.2017.05.015

M3 - Article

VL - 81

SP - 172

EP - 187

JO - Transportation Research Part C: Emerging Technologies

T2 - Transportation Research Part C: Emerging Technologies

JF - Transportation Research Part C: Emerging Technologies

SN - 0968-090X

ER -