Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning
The emerging technology of internet of connected vehicles (IoCV) introduced many new solutions for accident prevention and traffic safety by monitoring the behavior of drivers. In addition, monitoring drivers’ behavior to reduce accidents has attracted considerable attention from industry and academ...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/21/10462 |
_version_ | 1797512775640023040 |
---|---|
author | Omar Aboulola Mashael Khayyat Basma Al-Harbi Mohammed Saleh Ali Muthanna Ammar Muthanna Heba Fasihuddin Majid H. Alsulami |
author_facet | Omar Aboulola Mashael Khayyat Basma Al-Harbi Mohammed Saleh Ali Muthanna Ammar Muthanna Heba Fasihuddin Majid H. Alsulami |
author_sort | Omar Aboulola |
collection | DOAJ |
description | The emerging technology of internet of connected vehicles (IoCV) introduced many new solutions for accident prevention and traffic safety by monitoring the behavior of drivers. In addition, monitoring drivers’ behavior to reduce accidents has attracted considerable attention from industry and academic researchers in recent years. However, there are still many issues that have not been addressed due to the lack of feature extraction. To this end, in this paper, we propose the multimodal driver analysis internet of connected vehicles (MODAL-IoCV) approach for analyzing drivers’ behavior using a deep learning method. This approach includes three consecutive phases. In the first phase, the hidden Markov model (HMM) is proposed to predict vehicle motion and lane changes. In the second phase, SqueezeNet is proposed to perform feature extraction from these classes. Lastly, in the final phase, tri-agent-based soft actor critic (TA-SAC) is proposed for recommendation and route planning, in which each driver is precisely handled by an edge node for personalized assistance. Finally, detailed experimental results prove that our proposed MODAL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works. |
first_indexed | 2024-03-10T06:05:29Z |
format | Article |
id | doaj.art-5378b03b131c4edfb2640a1a5733a15a |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T06:05:29Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-5378b03b131c4edfb2640a1a5733a15a2023-11-22T20:32:32ZengMDPI AGApplied Sciences2076-34172021-11-0111211046210.3390/app112110462Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep LearningOmar Aboulola0Mashael Khayyat1Basma Al-Harbi2Mohammed Saleh Ali Muthanna3Ammar Muthanna4Heba Fasihuddin5Majid H. Alsulami6Department of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah 23218, Saudi ArabiaDepartment of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah 23218, Saudi ArabiaDepartment of Computer Science and Artificial Intelligence, College of Computer Science and Engineering, University of Jeddah, Jeddah 21959, Saudi ArabiaDepartment of Mathematics & Mechanics, Saint Petersburg State University, 199178 St. Petersburg, RussiaDepartment of Communication Networks and Data Transmission, St. Petersburg State University of Telecommunications, 193232 St. Petersburg, RussiaDepartment of Information Systems and Technology, College of Computer Science and Engineering, University of Jeddah, Jeddah 23218, Saudi ArabiaComputer Science Department, Community College, Shaqra University, Shaqra 11961, Saudi ArabiaThe emerging technology of internet of connected vehicles (IoCV) introduced many new solutions for accident prevention and traffic safety by monitoring the behavior of drivers. In addition, monitoring drivers’ behavior to reduce accidents has attracted considerable attention from industry and academic researchers in recent years. However, there are still many issues that have not been addressed due to the lack of feature extraction. To this end, in this paper, we propose the multimodal driver analysis internet of connected vehicles (MODAL-IoCV) approach for analyzing drivers’ behavior using a deep learning method. This approach includes three consecutive phases. In the first phase, the hidden Markov model (HMM) is proposed to predict vehicle motion and lane changes. In the second phase, SqueezeNet is proposed to perform feature extraction from these classes. Lastly, in the final phase, tri-agent-based soft actor critic (TA-SAC) is proposed for recommendation and route planning, in which each driver is precisely handled by an edge node for personalized assistance. Finally, detailed experimental results prove that our proposed MODAL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works.https://www.mdpi.com/2076-3417/11/21/10462internet of connected vehicles (IoCV)edge nodedriver behavior analysishidden Markov model (HMM)tri-agent-based soft actor critic (TA-SAC)recommendations |
spellingShingle | Omar Aboulola Mashael Khayyat Basma Al-Harbi Mohammed Saleh Ali Muthanna Ammar Muthanna Heba Fasihuddin Majid H. Alsulami Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning Applied Sciences internet of connected vehicles (IoCV) edge node driver behavior analysis hidden Markov model (HMM) tri-agent-based soft actor critic (TA-SAC) recommendations |
title | Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning |
title_full | Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning |
title_fullStr | Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning |
title_full_unstemmed | Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning |
title_short | Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning |
title_sort | multimodal feature assisted continuous driver behavior analysis and solving for edge enabled internet of connected vehicles using deep learning |
topic | internet of connected vehicles (IoCV) edge node driver behavior analysis hidden Markov model (HMM) tri-agent-based soft actor critic (TA-SAC) recommendations |
url | https://www.mdpi.com/2076-3417/11/21/10462 |
work_keys_str_mv | AT omaraboulola multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT mashaelkhayyat multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT basmaalharbi multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT mohammedsalehalimuthanna multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT ammarmuthanna multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT hebafasihuddin multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning AT majidhalsulami multimodalfeatureassistedcontinuousdriverbehavioranalysisandsolvingforedgeenabledinternetofconnectedvehiclesusingdeeplearning |