Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning

Real-time traffic conflict prediction is crucial for developing proactive safety management strategies and improving overall traffic safety. However, existing studies have failed to fully consider the entire process of traffic conflict generation at both signalized and unsignalized intersections. Gi...

Full description

Saved in:
Bibliographic Details
Main Authors: Chuanyun Fu, Jiaming Liu, Huahua Liu, Xiaoli Wang, Zhaoyou Lu, Jushang Ou, Wei Bai
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Advanced Transportation
Online Access:http://dx.doi.org/10.1155/atr/2239983
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128838621659136
author Chuanyun Fu
Jiaming Liu
Huahua Liu
Xiaoli Wang
Zhaoyou Lu
Jushang Ou
Wei Bai
author_facet Chuanyun Fu
Jiaming Liu
Huahua Liu
Xiaoli Wang
Zhaoyou Lu
Jushang Ou
Wei Bai
author_sort Chuanyun Fu
collection DOAJ
description Real-time traffic conflict prediction is crucial for developing proactive safety management strategies and improving overall traffic safety. However, existing studies have failed to fully consider the entire process of traffic conflict generation at both signalized and unsignalized intersections. Given this, this study proposes a real-time three-stage approach integrating statistical and machine learning models developed from three perspectives to reveal the influencing factors, occurrence identification, and quantity prediction of traffic conflicts. The results show that the proposed approach can effectively predict traffic conflicts at signalized and nonsignalized intersections. The findings of this study provide new ideas for proactive safety management in urban road networks.
format Article
id doaj-art-ebfb025fd06a459e84d502bd20552c3e
institution OA Journals
issn 2042-3195
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Advanced Transportation
spelling doaj-art-ebfb025fd06a459e84d502bd20552c3e2025-08-20T02:33:09ZengWileyJournal of Advanced Transportation2042-31952025-01-01202510.1155/atr/2239983Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine LearningChuanyun Fu0Jiaming Liu1Huahua Liu2Xiaoli Wang3Zhaoyou Lu4Jushang Ou5Wei Bai6School of Transportation Science and EngineeringSchool of Transportation Science and EngineeringSchool of Transportation Science and EngineeringJiaozhou Transportation BureauSchool of Transportation Science and EngineeringDepartment of Road Traffic ManagementDepartment of Road Traffic ManagementReal-time traffic conflict prediction is crucial for developing proactive safety management strategies and improving overall traffic safety. However, existing studies have failed to fully consider the entire process of traffic conflict generation at both signalized and unsignalized intersections. Given this, this study proposes a real-time three-stage approach integrating statistical and machine learning models developed from three perspectives to reveal the influencing factors, occurrence identification, and quantity prediction of traffic conflicts. The results show that the proposed approach can effectively predict traffic conflicts at signalized and nonsignalized intersections. The findings of this study provide new ideas for proactive safety management in urban road networks.http://dx.doi.org/10.1155/atr/2239983
spellingShingle Chuanyun Fu
Jiaming Liu
Huahua Liu
Xiaoli Wang
Zhaoyou Lu
Jushang Ou
Wei Bai
Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
Journal of Advanced Transportation
title Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
title_full Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
title_fullStr Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
title_full_unstemmed Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
title_short Real-Time Traffic Conflict Prediction at Intersections: A Novel Approach Integrating Statistical Models and Machine Learning
title_sort real time traffic conflict prediction at intersections a novel approach integrating statistical models and machine learning
url http://dx.doi.org/10.1155/atr/2239983
work_keys_str_mv AT chuanyunfu realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT jiamingliu realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT huahualiu realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT xiaoliwang realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT zhaoyoulu realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT jushangou realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning
AT weibai realtimetrafficconflictpredictionatintersectionsanovelapproachintegratingstatisticalmodelsandmachinelearning