Cargando…

A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells

Ground reaction force (GRF) is essential for estimating muscle strength and joint torque in inverse dynamic analysis. Typically, it is measured using a force plate. However, force plates have spatial limitations, and studies of gaits involve numerous steps and thus require a large number of force pl...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Junggil, Kang, Hyeon, Lee, Seulgi, Choi, Jinseung, Tack, Gyerae
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099259/
https://www.ncbi.nlm.nih.gov/pubmed/37050487
http://dx.doi.org/10.3390/s23073428
_version_ 1785025019042070528
author Kim, Junggil
Kang, Hyeon
Lee, Seulgi
Choi, Jinseung
Tack, Gyerae
author_facet Kim, Junggil
Kang, Hyeon
Lee, Seulgi
Choi, Jinseung
Tack, Gyerae
author_sort Kim, Junggil
collection PubMed
description Ground reaction force (GRF) is essential for estimating muscle strength and joint torque in inverse dynamic analysis. Typically, it is measured using a force plate. However, force plates have spatial limitations, and studies of gaits involve numerous steps and thus require a large number of force plates, which is disadvantageous. To overcome these challenges, we developed a deep learning model for estimating three-axis GRF utilizing shoes with three uniaxial load cells. GRF data were collected from 81 people as they walked on two force plates while wearing shoes with three load cells. The three-axis GRF was calculated using a seq2seq approach based on long short-term memory (LSTM). To conduct the learning, validation, and testing, random selection was performed based on the subjects. The 60 selected participants were divided as follows: 37 were in the training set, 12 were in the validation set, and 11 were in the test set. The estimated GRF matched the force plate-measured GRF with correlation coefficients of 0.97, 0.96, and 0.90 and root mean square errors of 65.12 N, 15.50 N, and 9.83 N for the vertical, anterior–posterior, and medial–lateral directions, respectively, and there was a mid-stance timing error of 5.61% in the test dataset. A Bland–Altman analysis showed good agreement for the maximum vertical GRF. The proposed shoe with three uniaxial load cells and seq2seq LSTM can be utilized for estimating the 3D GRF in an outdoor environment with level ground and/or for gait research in which the subject takes several steps at their preferred walking speed, and hence can supply crucial data for a basic inverse dynamic analysis.
format Online
Article
Text
id pubmed-10099259
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100992592023-04-14 A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells Kim, Junggil Kang, Hyeon Lee, Seulgi Choi, Jinseung Tack, Gyerae Sensors (Basel) Article Ground reaction force (GRF) is essential for estimating muscle strength and joint torque in inverse dynamic analysis. Typically, it is measured using a force plate. However, force plates have spatial limitations, and studies of gaits involve numerous steps and thus require a large number of force plates, which is disadvantageous. To overcome these challenges, we developed a deep learning model for estimating three-axis GRF utilizing shoes with three uniaxial load cells. GRF data were collected from 81 people as they walked on two force plates while wearing shoes with three load cells. The three-axis GRF was calculated using a seq2seq approach based on long short-term memory (LSTM). To conduct the learning, validation, and testing, random selection was performed based on the subjects. The 60 selected participants were divided as follows: 37 were in the training set, 12 were in the validation set, and 11 were in the test set. The estimated GRF matched the force plate-measured GRF with correlation coefficients of 0.97, 0.96, and 0.90 and root mean square errors of 65.12 N, 15.50 N, and 9.83 N for the vertical, anterior–posterior, and medial–lateral directions, respectively, and there was a mid-stance timing error of 5.61% in the test dataset. A Bland–Altman analysis showed good agreement for the maximum vertical GRF. The proposed shoe with three uniaxial load cells and seq2seq LSTM can be utilized for estimating the 3D GRF in an outdoor environment with level ground and/or for gait research in which the subject takes several steps at their preferred walking speed, and hence can supply crucial data for a basic inverse dynamic analysis. MDPI 2023-03-24 /pmc/articles/PMC10099259/ /pubmed/37050487 http://dx.doi.org/10.3390/s23073428 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kim, Junggil
Kang, Hyeon
Lee, Seulgi
Choi, Jinseung
Tack, Gyerae
A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title_full A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title_fullStr A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title_full_unstemmed A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title_short A Deep Learning Model for 3D Ground Reaction Force Estimation Using Shoes with Three Uniaxial Load Cells
title_sort deep learning model for 3d ground reaction force estimation using shoes with three uniaxial load cells
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10099259/
https://www.ncbi.nlm.nih.gov/pubmed/37050487
http://dx.doi.org/10.3390/s23073428
work_keys_str_mv AT kimjunggil adeeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT kanghyeon adeeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT leeseulgi adeeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT choijinseung adeeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT tackgyerae adeeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT kimjunggil deeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT kanghyeon deeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT leeseulgi deeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT choijinseung deeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells
AT tackgyerae deeplearningmodelfor3dgroundreactionforceestimationusingshoeswiththreeuniaxialloadcells