Standard

Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning. / Aboulola, Omar; Khayyat, Mashael; Al-Harbi, Basma; Muthanna, Mohammed Saleh Ali; Muthanna, Ammar; Fasihuddin, Heba; Alsulami, Majid H.

In: Applied Sciences (Switzerland), Vol. 11, No. 21, 10462, 07.11.2021.

Research output: Contribution to journalArticlepeer-review

Harvard

Aboulola, O, Khayyat, M, Al-Harbi, B, Muthanna, MSA, Muthanna, A, Fasihuddin, H & Alsulami, MH 2021, 'Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning', Applied Sciences (Switzerland), vol. 11, no. 21, 10462. https://doi.org/10.3390/app112110462

APA

Aboulola, O., Khayyat, M., Al-Harbi, B., Muthanna, M. S. A., Muthanna, A., Fasihuddin, H., & Alsulami, M. H. (2021). Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning. Applied Sciences (Switzerland), 11(21), [10462]. https://doi.org/10.3390/app112110462

Vancouver

Author

Aboulola, Omar ; Khayyat, Mashael ; Al-Harbi, Basma ; Muthanna, Mohammed Saleh Ali ; Muthanna, Ammar ; Fasihuddin, Heba ; Alsulami, Majid H. / Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning. In: Applied Sciences (Switzerland). 2021 ; Vol. 11, No. 21.

BibTeX

@article{46d90f0fc7ce432788746edc2d49f249,
title = "Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning",
abstract = "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 addi-tion, monitoring drivers{\textquoteright} 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{\textquoteright} 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 MOD-AL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works.",
keywords = "Driver behavior analysis, Edge node, Hidden Markov model (HMM), Internet of connected vehicles (IoCV), Recommendations, Tri-agent-based soft actor critic (TA-SAC), edge node, tri-agent-based soft actor critic (TA-SAC), hidden Markov model (HMM), driver behavior analysis, recommendations, internet of connected vehicles (IoCV), MONITORING-SYSTEM",
author = "Omar Aboulola and Mashael Khayyat and Basma Al-Harbi and Muthanna, {Mohammed Saleh Ali} and Ammar Muthanna and Heba Fasihuddin and Alsulami, {Majid H.}",
note = "Aboulola, O.; Khayyat, M.; Al-Harbi, B.; Muthanna, M.S.A.; Muthanna, A.; Fasihuddin, H.; Alsulami, M.H. Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning. Appl. Sci. 2021, 11, 10462. https://doi.org/10.3390/app112110462",
year = "2021",
month = nov,
day = "7",
doi = "10.3390/app112110462",
language = "English",
volume = "11",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "MDPI AG",
number = "21",

}

RIS

TY - JOUR

T1 - Multimodal feature-assisted continuous driver behavior analysis and solving for edge-enabled internet of connected vehicles using deep learning

AU - Aboulola, Omar

AU - Khayyat, Mashael

AU - Al-Harbi, Basma

AU - Muthanna, Mohammed Saleh Ali

AU - Muthanna, Ammar

AU - Fasihuddin, Heba

AU - Alsulami, Majid H.

N1 - Aboulola, O.; Khayyat, M.; Al-Harbi, B.; Muthanna, M.S.A.; Muthanna, A.; Fasihuddin, H.; Alsulami, M.H. Multimodal Feature-Assisted Continuous Driver Behavior Analysis and Solving for Edge-Enabled Internet of Connected Vehicles Using Deep Learning. Appl. Sci. 2021, 11, 10462. https://doi.org/10.3390/app112110462

PY - 2021/11/7

Y1 - 2021/11/7

N2 - 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 addi-tion, 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 MOD-AL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works.

AB - 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 addi-tion, 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 MOD-AL-IoCV method can achieve high performance in terms of latency, accuracy, false alarm rate, and motion prediction error compared to existing works.

KW - Driver behavior analysis

KW - Edge node

KW - Hidden Markov model (HMM)

KW - Internet of connected vehicles (IoCV)

KW - Recommendations

KW - Tri-agent-based soft actor critic (TA-SAC)

KW - edge node

KW - tri-agent-based soft actor critic (TA-SAC)

KW - hidden Markov model (HMM)

KW - driver behavior analysis

KW - recommendations

KW - internet of connected vehicles (IoCV)

KW - MONITORING-SYSTEM

UR - http://www.scopus.com/inward/record.url?scp=85118790329&partnerID=8YFLogxK

U2 - 10.3390/app112110462

DO - 10.3390/app112110462

M3 - Article

AN - SCOPUS:85118790329

VL - 11

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 21

M1 - 10462

ER -

ID: 88866998