Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics

<p dir="ltr">Ground reaction force and moment (GRF&M) measurements are vital for biomechanical analysis and significantly impact the clinical domain for early abnormality detection for different neurodegenerative diseases. Force platforms have become the de facto standard for mea...

Full description

Saved in:
Bibliographic Details
Main Author: Md. Ahasan Atick Faisal (15302410) (author)
Other Authors: Sakib Mahmud (15302404) (author), Muhammad E. H. Chowdhury (14150526) (author), Amith Khandakar (14151981) (author), Mosabber Uddin Ahmed (17773200) (author), Abdulrahman Alqahtani (6056309) (author), Mohammed Alhatou (14777758) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513521166843904
author Md. Ahasan Atick Faisal (15302410)
author2 Sakib Mahmud (15302404)
Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Mosabber Uddin Ahmed (17773200)
Abdulrahman Alqahtani (6056309)
Mohammed Alhatou (14777758)
author2_role author
author
author
author
author
author
author_facet Md. Ahasan Atick Faisal (15302410)
Sakib Mahmud (15302404)
Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Mosabber Uddin Ahmed (17773200)
Abdulrahman Alqahtani (6056309)
Mohammed Alhatou (14777758)
author_role author
dc.creator.none.fl_str_mv Md. Ahasan Atick Faisal (15302410)
Sakib Mahmud (15302404)
Muhammad E. H. Chowdhury (14150526)
Amith Khandakar (14151981)
Mosabber Uddin Ahmed (17773200)
Abdulrahman Alqahtani (6056309)
Mohammed Alhatou (14777758)
dc.date.none.fl_str_mv 2023-10-23T03:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s00521-023-09081-z
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Robust_and_novel_attention_guided_MultiResUnet_model_for_3D_ground_reaction_force_and_moment_prediction_from_foot_kinematics/24980829
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Foot kinematics
Ground reaction forces
Ground reaction moment
Machine learning
Deep learning
Signal synthesis
dc.title.none.fl_str_mv Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Ground reaction force and moment (GRF&M) measurements are vital for biomechanical analysis and significantly impact the clinical domain for early abnormality detection for different neurodegenerative diseases. Force platforms have become the de facto standard for measuring GRF&M signals in recent years. Although the signal quality achieved from these devices is unparalleled, they are expensive and require laboratory setup, making them unsuitable for many clinical applications. For these reasons, predicting GRF&M from cheaper and more feasible alternatives has become a topic of interest. Several works have been done on predicting GRF&M from kinematic data captured from the subject’s body with the help of motion capture cameras. The problem with these solutions is that they rely on markers placed on the whole body to capture the movements, which can be very infeasible in many practical scenarios. This paper proposes a novel deep learning-based approach to predict 3D GRF&M from only 5 markers placed on the shoe. The proposed network “Attention Guided MultiResUNet” can predict the force and moment signals accurately and reliably compared to the techniques relying on full-body markers. The proposed deep learning model is tested on two publicly available datasets containing data from 66 healthy subjects to validate the approach. The framework has achieved an average correlation coefficient of 0.96 for 3D ground reaction force prediction and 0.86 for 3D ground reaction momentum prediction in cross-dataset validation. The framework can provide a cheaper and more feasible alternative for predicting GRF&M in many practical applications.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<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/10.1007/s00521-023-09081-z" target="_blank">https://dx.doi.org/10.1007/s00521-023-09081-z</a></p>
eu_rights_str_mv openAccess
id Manara2_7665638289abf58d96f85ec65764d97e
identifier_str_mv 10.1007/s00521-023-09081-z
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24980829
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematicsMd. Ahasan Atick Faisal (15302410)Sakib Mahmud (15302404)Muhammad E. H. Chowdhury (14150526)Amith Khandakar (14151981)Mosabber Uddin Ahmed (17773200)Abdulrahman Alqahtani (6056309)Mohammed Alhatou (14777758)EngineeringBiomedical engineeringInformation and computing sciencesData management and data scienceMachine learningFoot kinematicsGround reaction forcesGround reaction momentMachine learningDeep learningSignal synthesis<p dir="ltr">Ground reaction force and moment (GRF&M) measurements are vital for biomechanical analysis and significantly impact the clinical domain for early abnormality detection for different neurodegenerative diseases. Force platforms have become the de facto standard for measuring GRF&M signals in recent years. Although the signal quality achieved from these devices is unparalleled, they are expensive and require laboratory setup, making them unsuitable for many clinical applications. For these reasons, predicting GRF&M from cheaper and more feasible alternatives has become a topic of interest. Several works have been done on predicting GRF&M from kinematic data captured from the subject’s body with the help of motion capture cameras. The problem with these solutions is that they rely on markers placed on the whole body to capture the movements, which can be very infeasible in many practical scenarios. This paper proposes a novel deep learning-based approach to predict 3D GRF&M from only 5 markers placed on the shoe. The proposed network “Attention Guided MultiResUNet” can predict the force and moment signals accurately and reliably compared to the techniques relying on full-body markers. The proposed deep learning model is tested on two publicly available datasets containing data from 66 healthy subjects to validate the approach. The framework has achieved an average correlation coefficient of 0.96 for 3D ground reaction force prediction and 0.86 for 3D ground reaction momentum prediction in cross-dataset validation. The framework can provide a cheaper and more feasible alternative for predicting GRF&M in many practical applications.</p><h2>Other Information</h2><p dir="ltr">Published in: Neural Computing and Applications<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/10.1007/s00521-023-09081-z" target="_blank">https://dx.doi.org/10.1007/s00521-023-09081-z</a></p>2023-10-23T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00521-023-09081-zhttps://figshare.com/articles/journal_contribution/Robust_and_novel_attention_guided_MultiResUnet_model_for_3D_ground_reaction_force_and_moment_prediction_from_foot_kinematics/24980829CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/249808292023-10-23T03:00:00Z
spellingShingle Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
Md. Ahasan Atick Faisal (15302410)
Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Foot kinematics
Ground reaction forces
Ground reaction moment
Machine learning
Deep learning
Signal synthesis
status_str publishedVersion
title Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
title_full Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
title_fullStr Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
title_full_unstemmed Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
title_short Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
title_sort Robust and novel attention guided MultiResUnet model for 3D ground reaction force and moment prediction from foot kinematics
topic Engineering
Biomedical engineering
Information and computing sciences
Data management and data science
Machine learning
Foot kinematics
Ground reaction forces
Ground reaction moment
Machine learning
Deep learning
Signal synthesis