Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach

Connected vehicle (CV) is regarded as a typical feature of the future road transportation system. One core benefit of promoting CV is to improve traffic safety, and to achieve that, accurate driving risk assessment under Vehicle-to-Vehicle (V2V) communications is critical. There are two main differe...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin Zheng, Lei Han, Jiqing Yu, Rongjie Yu
Format: Article
Language:English
Published: Maximum Academic Press 2023-09-01
Series:Digital Transportation and Safety
Subjects:
Online Access:https://www.maxapress.com/article/doi/10.48130/DTS-2023-0017
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850199846078644224
author Yin Zheng
Lei Han
Jiqing Yu
Rongjie Yu
author_facet Yin Zheng
Lei Han
Jiqing Yu
Rongjie Yu
author_sort Yin Zheng
collection DOAJ
description Connected vehicle (CV) is regarded as a typical feature of the future road transportation system. One core benefit of promoting CV is to improve traffic safety, and to achieve that, accurate driving risk assessment under Vehicle-to-Vehicle (V2V) communications is critical. There are two main differences concluded by comparing driving risk assessment under the CV environment with traditional ones: (1) the CV environment provides high-resolution and multi-dimensional data, e.g., vehicle trajectory data, (2) Rare existing studies can comprehensively address the heterogeneity of the vehicle operating environment, e.g., the multiple interacting objects and the time-series variability. Hence, this study proposes a driving risk assessment framework under the CV environment. Specifically, first, a set of time-series top views was proposed to describe the CV environment data, expressing the detailed information on the vehicles surrounding the subject vehicle. Then, a hybrid CNN-LSTM model was established with the CNN component extracting the spatial interaction with multiple interacting vehicles and the LSTM component solving the time-series variability of the driving environment. It is proved that this model can reach an AUC of 0.997, outperforming the existing machine learning algorithms. This study contributes to the improvement of driving risk assessment under the CV environment.
format Article
id doaj-art-d1409c3e7f5e459b982932d6ee1ebb19
institution OA Journals
issn 2837-7842
language English
publishDate 2023-09-01
publisher Maximum Academic Press
record_format Article
series Digital Transportation and Safety
spelling doaj-art-d1409c3e7f5e459b982932d6ee1ebb192025-08-20T02:12:30ZengMaximum Academic PressDigital Transportation and Safety2837-78422023-09-012321121910.48130/DTS-2023-0017DTS-2023-0017Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approachYin Zheng0Lei Han1Jiqing Yu2Rongjie Yu3The Key Laboratory of Road and Traffic Engineering, Ministry of Education, No. 4800 Cao'an Road, Shanghai 201804, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, No. 4800 Cao'an Road, Shanghai 201804, ChinaNingbo Hangzhou Bay Bridge Development Co., Ltd., No. 1 Hongqiao Road, Cixi 315300, Ningbo, ChinaThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, No. 4800 Cao'an Road, Shanghai 201804, ChinaConnected vehicle (CV) is regarded as a typical feature of the future road transportation system. One core benefit of promoting CV is to improve traffic safety, and to achieve that, accurate driving risk assessment under Vehicle-to-Vehicle (V2V) communications is critical. There are two main differences concluded by comparing driving risk assessment under the CV environment with traditional ones: (1) the CV environment provides high-resolution and multi-dimensional data, e.g., vehicle trajectory data, (2) Rare existing studies can comprehensively address the heterogeneity of the vehicle operating environment, e.g., the multiple interacting objects and the time-series variability. Hence, this study proposes a driving risk assessment framework under the CV environment. Specifically, first, a set of time-series top views was proposed to describe the CV environment data, expressing the detailed information on the vehicles surrounding the subject vehicle. Then, a hybrid CNN-LSTM model was established with the CNN component extracting the spatial interaction with multiple interacting vehicles and the LSTM component solving the time-series variability of the driving environment. It is proved that this model can reach an AUC of 0.997, outperforming the existing machine learning algorithms. This study contributes to the improvement of driving risk assessment under the CV environment.https://www.maxapress.com/article/doi/10.48130/DTS-2023-0017connected vehicleconnected vehicle environmentdriving risk assessmentcnn-lstmtraffic safety
spellingShingle Yin Zheng
Lei Han
Jiqing Yu
Rongjie Yu
Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
Digital Transportation and Safety
connected vehicle
connected vehicle environment
driving risk assessment
cnn-lstm
traffic safety
title Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
title_full Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
title_fullStr Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
title_full_unstemmed Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
title_short Driving risk assessment under the connected vehicle environment: a CNN-LSTM modeling approach
title_sort driving risk assessment under the connected vehicle environment a cnn lstm modeling approach
topic connected vehicle
connected vehicle environment
driving risk assessment
cnn-lstm
traffic safety
url https://www.maxapress.com/article/doi/10.48130/DTS-2023-0017
work_keys_str_mv AT yinzheng drivingriskassessmentundertheconnectedvehicleenvironmentacnnlstmmodelingapproach
AT leihan drivingriskassessmentundertheconnectedvehicleenvironmentacnnlstmmodelingapproach
AT jiqingyu drivingriskassessmentundertheconnectedvehicleenvironmentacnnlstmmodelingapproach
AT rongjieyu drivingriskassessmentundertheconnectedvehicleenvironmentacnnlstmmodelingapproach