A machine learning approach for highway intersection risk caused by harmful lane-changing behaviors

Yanping Hao, Liangjie Xu, Bozhao Qi, Teng Wang, Wei Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Highway intersection-related crashes are suspected to be associated with harmful lane-changing behaviors. To better understand the relationship between them, this study applied an innovative machine learning approach to identify crash risk factors and find solutions to reduce the intersection-related crash frequency and severity caused by harmful lane-changing behaviors. First, a vehicles approach time (VAT) model was developed to define and classify different types of harmful lane-changing behaviors. Second, the real world driving video data was collected and preprocessed to identify the potential crash risk factors of harmful lane-changing behaviors. Finally, an advanced machine learning algorithm, Lasso-LARS, was applied to analyze the relation between intersection-related crash risk factors and lane-changing behaviors. There were no significant differences in the VAT values between the VAT model and the Lasso-LARS regression model. The result shows that both the two models are suitable for the analysis of risk factors of harmful lane-changing behaviors.

Original languageEnglish
Title of host publicationCICTP 2019
Subtitle of host publicationTransportation in China - Connecting the World - Proceedings of the 19th COTA International Conference of Transportation Professionals
EditorsLei Zhang, Jianming Ma, Pan Liu, Guangjun Zhang
Pages5623-5635
Number of pages13
ISBN (Electronic)9780784482292
DOIs
StatePublished - 2019
Event19th COTA International Conference of Transportation Professionals: Transportation in China - Connecting the World, CICTP 2019 - Nanjing, China
Duration: Jul 6 2019Jul 8 2019

Publication series

NameCICTP 2019: Transportation in China - Connecting the World - Proceedings of the 19th COTA International Conference of Transportation Professionals

Conference

Conference19th COTA International Conference of Transportation Professionals: Transportation in China - Connecting the World, CICTP 2019
Country/TerritoryChina
CityNanjing
Period7/6/197/8/19

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This research project is supported by the State of Key Laboratory of Vehicle of VNH and Safety Technology through 2019 annual public foundation awards, research topic No. 12. The project is also supported by the innovation fund project of Inner Mongolia University of Science and Technology, research on the coupling mechanism between productive services and leading industries in Baotou city through project No. 2016QDW-B05. Yanping Hao and Bozhao Qi contributed equally to this work.

Publisher Copyright:
© ASCE.

ASJC Scopus subject areas

  • Transportation

Fingerprint

Dive into the research topics of 'A machine learning approach for highway intersection risk caused by harmful lane-changing behaviors'. Together they form a unique fingerprint.

Cite this