Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection

<p dir="ltr">Distraction can cause delayed decision-making and slower awareness, posing significant risks in driving. For reliable driving systems, continuous monitoring of driver behavior is essential to mitigate the impact of distractions. Current strategies for distraction detecti...

Full description

Saved in:
Bibliographic Details
Main Author: Mamun Or Rashid (21976373) (author)
Other Authors: Md. Mosarrof Hossen (21976376) (author), Mohammad Nashbat (17542194) (author), Mazhar Hasan-Zia (21399896) (author), Ali K. Ansaruddin Kunju (21323918) (author), Amith Khandakar (14151981) (author), Azad Ashraf (17541924) (author), Molla Ehsanul Majid (21976379) (author), Saad Bin Abul Kashem (19117156) (author), Muhammad E. H. Chowdhury (14150526) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513542650068992
author Mamun Or Rashid (21976373)
author2 Md. Mosarrof Hossen (21976376)
Mohammad Nashbat (17542194)
Mazhar Hasan-Zia (21399896)
Ali K. Ansaruddin Kunju (21323918)
Amith Khandakar (14151981)
Azad Ashraf (17541924)
Molla Ehsanul Majid (21976379)
Saad Bin Abul Kashem (19117156)
Muhammad E. H. Chowdhury (14150526)
author2_role author
author
author
author
author
author
author
author
author
author_facet Mamun Or Rashid (21976373)
Md. Mosarrof Hossen (21976376)
Mohammad Nashbat (17542194)
Mazhar Hasan-Zia (21399896)
Ali K. Ansaruddin Kunju (21323918)
Amith Khandakar (14151981)
Azad Ashraf (17541924)
Molla Ehsanul Majid (21976379)
Saad Bin Abul Kashem (19117156)
Muhammad E. H. Chowdhury (14150526)
author_role author
dc.creator.none.fl_str_mv Mamun Or Rashid (21976373)
Md. Mosarrof Hossen (21976376)
Mohammad Nashbat (17542194)
Mazhar Hasan-Zia (21399896)
Ali K. Ansaruddin Kunju (21323918)
Amith Khandakar (14151981)
Azad Ashraf (17541924)
Molla Ehsanul Majid (21976379)
Saad Bin Abul Kashem (19117156)
Muhammad E. H. Chowdhury (14150526)
dc.date.none.fl_str_mv 2025-02-24T03:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2025.3545359
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Self-DSNet_A_Novel_Self-ONNs_Based_Deep_Learning_Framework_for_Multimodal_Driving_Distraction_Detection/29816183
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Automotive engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Human-centred computing
Machine learning
Driving distraction detection
Self-organizing neural network (Self-ONN)
Multimodal data
Machine learning
Driver behavior monitoring
Vehicle dynamics
Vehicles
Feature extraction
Drives
Driver behavior
Biomedical monitoring
Data models
Brain modeling
Accidents
dc.title.none.fl_str_mv Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Distraction can cause delayed decision-making and slower awareness, posing significant risks in driving. For reliable driving systems, continuous monitoring of driver behavior is essential to mitigate the impact of distractions. Current strategies for distraction detection widely rely on machine learning models, but the non-linear relationships among various data modalities complicate the identification of optimal combinations. To address these challenges, we propose a novel model, Self-DSNet, for efficient driving distraction detection. The proposed Self-DSNet model utilizes Self-Organizing Neural Network (Self-ONN) layers to enhance complex pattern learning within the data. We employed a publicly available multimodal dataset encompassing three data categories: physiological, vehicle dynamics, and vision-based data. Our approach aims to identify the normal state and three types of distractions: cognitive, emotional, and sensorimotor. The model was evaluated using both single-modality and combined-modality data, focusing on binary classification to distinguish between distracted and non-distracted driving states. The Self-DSNet model demonstrated an impressive accuracy of 94.23% when using vision-based data alone. Incorporating additional physiological data, such as heart rate and breathing rate, alongside vehicle dynamics data, such as steering behavior, further enhanced the model’s performance. The combined data approach achieved a 95.13% accuracy in detecting driving distractions. Specifically, the binary classification yielded a 96.58% accuracy with vision-based data, which increased to 97.31% when steering, breathing rate, and heart rate data were included. Our approach significantly outperformed state-of-the-art methods in terms of classification accuracy. The proposed Self-DSNet model offers a robust solution for driving distraction detection by effectively leveraging multimodal data and enhancing complex pattern recognition through the Self-ONN layers. The model’s high accuracy rates underscore its potential for improving driving safety by providing reliable and continuous monitoring of driver behavior. Future research may focus on real-time implementation and the integration of additional data sources to further refine and validate the model’s effectiveness in diverse driving scenarios.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3545359" target="_blank">https://dx.doi.org/10.1109/access.2025.3545359</a></p>
eu_rights_str_mv openAccess
id Manara2_1b94c07883f4e9f6a2f7b4979e125731
identifier_str_mv 10.1109/access.2025.3545359
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29816183
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction DetectionMamun Or Rashid (21976373)Md. Mosarrof Hossen (21976376)Mohammad Nashbat (17542194)Mazhar Hasan-Zia (21399896)Ali K. Ansaruddin Kunju (21323918)Amith Khandakar (14151981)Azad Ashraf (17541924)Molla Ehsanul Majid (21976379)Saad Bin Abul Kashem (19117156)Muhammad E. H. Chowdhury (14150526)EngineeringAutomotive engineeringBiomedical engineeringInformation and computing sciencesArtificial intelligenceComputer vision and multimedia computationData management and data scienceHuman-centred computingMachine learningDriving distraction detectionSelf-organizing neural network (Self-ONN)Multimodal dataMachine learningDriver behavior monitoringVehicle dynamicsVehiclesFeature extractionDrivesDriver behaviorBiomedical monitoringData modelsBrain modelingAccidents<p dir="ltr">Distraction can cause delayed decision-making and slower awareness, posing significant risks in driving. For reliable driving systems, continuous monitoring of driver behavior is essential to mitigate the impact of distractions. Current strategies for distraction detection widely rely on machine learning models, but the non-linear relationships among various data modalities complicate the identification of optimal combinations. To address these challenges, we propose a novel model, Self-DSNet, for efficient driving distraction detection. The proposed Self-DSNet model utilizes Self-Organizing Neural Network (Self-ONN) layers to enhance complex pattern learning within the data. We employed a publicly available multimodal dataset encompassing three data categories: physiological, vehicle dynamics, and vision-based data. Our approach aims to identify the normal state and three types of distractions: cognitive, emotional, and sensorimotor. The model was evaluated using both single-modality and combined-modality data, focusing on binary classification to distinguish between distracted and non-distracted driving states. The Self-DSNet model demonstrated an impressive accuracy of 94.23% when using vision-based data alone. Incorporating additional physiological data, such as heart rate and breathing rate, alongside vehicle dynamics data, such as steering behavior, further enhanced the model’s performance. The combined data approach achieved a 95.13% accuracy in detecting driving distractions. Specifically, the binary classification yielded a 96.58% accuracy with vision-based data, which increased to 97.31% when steering, breathing rate, and heart rate data were included. Our approach significantly outperformed state-of-the-art methods in terms of classification accuracy. The proposed Self-DSNet model offers a robust solution for driving distraction detection by effectively leveraging multimodal data and enhancing complex pattern recognition through the Self-ONN layers. The model’s high accuracy rates underscore its potential for improving driving safety by providing reliable and continuous monitoring of driver behavior. Future research may focus on real-time implementation and the integration of additional data sources to further refine and validate the model’s effectiveness in diverse driving scenarios.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2025.3545359" target="_blank">https://dx.doi.org/10.1109/access.2025.3545359</a></p>2025-02-24T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2025.3545359https://figshare.com/articles/journal_contribution/Self-DSNet_A_Novel_Self-ONNs_Based_Deep_Learning_Framework_for_Multimodal_Driving_Distraction_Detection/29816183CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/298161832025-02-24T03:00:00Z
spellingShingle Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
Mamun Or Rashid (21976373)
Engineering
Automotive engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Human-centred computing
Machine learning
Driving distraction detection
Self-organizing neural network (Self-ONN)
Multimodal data
Machine learning
Driver behavior monitoring
Vehicle dynamics
Vehicles
Feature extraction
Drives
Driver behavior
Biomedical monitoring
Data models
Brain modeling
Accidents
status_str publishedVersion
title Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
title_full Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
title_fullStr Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
title_full_unstemmed Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
title_short Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
title_sort Self-DSNet: A Novel Self-ONNs Based Deep Learning Framework for Multimodal Driving Distraction Detection
topic Engineering
Automotive engineering
Biomedical engineering
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Human-centred computing
Machine learning
Driving distraction detection
Self-organizing neural network (Self-ONN)
Multimodal data
Machine learning
Driver behavior monitoring
Vehicle dynamics
Vehicles
Feature extraction
Drives
Driver behavior
Biomedical monitoring
Data models
Brain modeling
Accidents