State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction

In recent years, the application of deep learning (DL) models to identify dangerous driving behaviors has emerged as a novel approach to enhance road safety and detect high-risk driving behaviors. However, these advanced algorithms still face several challenges. We analyze relevant literature from 2...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongguang Li, Shafrida Sahrani, Mahidur R. Sarker, Yinglin Xiao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11104155/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849394090037215232
author Hongguang Li
Shafrida Sahrani
Mahidur R. Sarker
Yinglin Xiao
author_facet Hongguang Li
Shafrida Sahrani
Mahidur R. Sarker
Yinglin Xiao
author_sort Hongguang Li
collection DOAJ
description In recent years, the application of deep learning (DL) models to identify dangerous driving behaviors has emerged as a novel approach to enhance road safety and detect high-risk driving behaviors. However, these advanced algorithms still face several challenges. We analyze relevant literature from 2015 to 2024, to uncover key trends and gaps in the development of applications for identifying dangerous driving behaviors, with a primary focus on optimizing integration to improve the accuracy and real-time capability of driving behavior prediction. The analysis reveals that data quality, computational demands, and privacy issues are currently hindering the full realization of this technology. The Internet of Vehicles (IoV) collects data based on real driving environments, offering unique advantages in terms of data timeliness, sufficiency, and diversity. Therefore, this paper proposes an active IoV based DL framework, emphasizing the feasibility of enhancing data processing techniques and algorithmic improvements to boost model accuracy and generalization ability, and highlighting the potential of integrating edge and cloud computing to support real-time data analysis and decision-making. Future research should concentrate on multimodal data fusion and federated learning to further enhance recognition performance and ensure broader applicability of deep learning in the internet of vehicles environments.
format Article
id doaj-art-0e9a9c80364047248c9d0e1ecf1ab8e5
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0e9a9c80364047248c9d0e1ecf1ab8e52025-08-20T03:40:11ZengIEEEIEEE Access2169-35362025-01-011313596913598910.1109/ACCESS.2025.359409111104155State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future DirectionHongguang Li0https://orcid.org/0009-0005-7174-7325Shafrida Sahrani1https://orcid.org/0000-0003-4634-8021Mahidur R. Sarker2https://orcid.org/0000-0002-5363-6219Yinglin Xiao3Institute of Visual Informatics, Universiti Kebangsaan Malaysia, Bangi, MalaysiaInstitute of Visual Informatics, Universiti Kebangsaan Malaysia, Bangi, MalaysiaInstitute of Visual Informatics, Universiti Kebangsaan Malaysia, Bangi, MalaysiaInstitute of Visual Informatics, Universiti Kebangsaan Malaysia, Bangi, MalaysiaIn recent years, the application of deep learning (DL) models to identify dangerous driving behaviors has emerged as a novel approach to enhance road safety and detect high-risk driving behaviors. However, these advanced algorithms still face several challenges. We analyze relevant literature from 2015 to 2024, to uncover key trends and gaps in the development of applications for identifying dangerous driving behaviors, with a primary focus on optimizing integration to improve the accuracy and real-time capability of driving behavior prediction. The analysis reveals that data quality, computational demands, and privacy issues are currently hindering the full realization of this technology. The Internet of Vehicles (IoV) collects data based on real driving environments, offering unique advantages in terms of data timeliness, sufficiency, and diversity. Therefore, this paper proposes an active IoV based DL framework, emphasizing the feasibility of enhancing data processing techniques and algorithmic improvements to boost model accuracy and generalization ability, and highlighting the potential of integrating edge and cloud computing to support real-time data analysis and decision-making. Future research should concentrate on multimodal data fusion and federated learning to further enhance recognition performance and ensure broader applicability of deep learning in the internet of vehicles environments.https://ieeexplore.ieee.org/document/11104155/Deep learningInternet of Vehicles (IoV)driving behavior recognitionintelligent transportation systems (ITS)proposed framework
spellingShingle Hongguang Li
Shafrida Sahrani
Mahidur R. Sarker
Yinglin Xiao
State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
IEEE Access
Deep learning
Internet of Vehicles (IoV)
driving behavior recognition
intelligent transportation systems (ITS)
proposed framework
title State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
title_full State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
title_fullStr State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
title_full_unstemmed State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
title_short State-of-the-Art on IoV-Based Deep Learning Framework for Enhanced Driving Behavior Recognition: Recent Progress, Technology Updates, Challenges, and Future Direction
title_sort state of the art on iov based deep learning framework for enhanced driving behavior recognition recent progress technology updates challenges and future direction
topic Deep learning
Internet of Vehicles (IoV)
driving behavior recognition
intelligent transportation systems (ITS)
proposed framework
url https://ieeexplore.ieee.org/document/11104155/
work_keys_str_mv AT hongguangli stateoftheartoniovbaseddeeplearningframeworkforenhanceddrivingbehaviorrecognitionrecentprogresstechnologyupdateschallengesandfuturedirection
AT shafridasahrani stateoftheartoniovbaseddeeplearningframeworkforenhanceddrivingbehaviorrecognitionrecentprogresstechnologyupdateschallengesandfuturedirection
AT mahidurrsarker stateoftheartoniovbaseddeeplearningframeworkforenhanceddrivingbehaviorrecognitionrecentprogresstechnologyupdateschallengesandfuturedirection
AT yinglinxiao stateoftheartoniovbaseddeeplearningframeworkforenhanceddrivingbehaviorrecognitionrecentprogresstechnologyupdateschallengesandfuturedirection