Cargando…

The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions

Gait analysis based on inertial sensors has become an effective method of quantifying movement mechanics, such as joint kinematics and kinetics. Machine learning techniques are used to reliably predict joint mechanics directly from streams of IMU signals for various activities. These data-driven mod...

Descripción completa

Detalles Bibliográficos
Autores principales: Sharifi Renani, Mohsen, Eustace, Abigail M., Myers, Casey A., Clary, Chadd W.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434290/
https://www.ncbi.nlm.nih.gov/pubmed/34502766
http://dx.doi.org/10.3390/s21175876
_version_ 1783751563109466112
author Sharifi Renani, Mohsen
Eustace, Abigail M.
Myers, Casey A.
Clary, Chadd W.
author_facet Sharifi Renani, Mohsen
Eustace, Abigail M.
Myers, Casey A.
Clary, Chadd W.
author_sort Sharifi Renani, Mohsen
collection PubMed
description Gait analysis based on inertial sensors has become an effective method of quantifying movement mechanics, such as joint kinematics and kinetics. Machine learning techniques are used to reliably predict joint mechanics directly from streams of IMU signals for various activities. These data-driven models require comprehensive and representative training datasets to be generalizable across the movement variability seen in the population at large. Bottlenecks in model development frequently occur due to the lack of sufficient training data and the significant time and resources necessary to acquire these datasets. Reliable methods to generate synthetic biomechanical training data could streamline model development and potentially improve model performance. In this study, we developed a methodology to generate synthetic kinematics and the associated predicted IMU signals using open source musculoskeletal modeling software. These synthetic data were used to train neural networks to predict three degree-of-freedom joint rotations at the hip and knee during gait either in lieu of or along with previously measured experimental gait data. The accuracy of the models’ kinematic predictions was assessed using experimentally measured IMU signals and gait kinematics. Models trained using the synthetic data out-performed models using only the experimental data in five of the six rotational degrees of freedom at the hip and knee. On average, root mean square errors in joint angle predictions were improved by 38% at the hip (synthetic data RMSE: 2.3°, measured data RMSE: 4.5°) and 11% at the knee (synthetic data RMSE: 2.9°, measured data RMSE: 3.3°), when models trained solely on synthetic data were compared to measured data. When models were trained on both measured and synthetic data, root mean square errors were reduced by 54% at the hip (measured + synthetic data RMSE: 1.9°) and 45% at the knee (measured + synthetic data RMSE: 1.7°), compared to measured data alone. These findings enable future model development for different activities of clinical significance without the burden of generating large quantities of gait lab data for model training, streamlining model development, and ultimately improving model performance.
format Online
Article
Text
id pubmed-8434290
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84342902021-09-12 The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions Sharifi Renani, Mohsen Eustace, Abigail M. Myers, Casey A. Clary, Chadd W. Sensors (Basel) Article Gait analysis based on inertial sensors has become an effective method of quantifying movement mechanics, such as joint kinematics and kinetics. Machine learning techniques are used to reliably predict joint mechanics directly from streams of IMU signals for various activities. These data-driven models require comprehensive and representative training datasets to be generalizable across the movement variability seen in the population at large. Bottlenecks in model development frequently occur due to the lack of sufficient training data and the significant time and resources necessary to acquire these datasets. Reliable methods to generate synthetic biomechanical training data could streamline model development and potentially improve model performance. In this study, we developed a methodology to generate synthetic kinematics and the associated predicted IMU signals using open source musculoskeletal modeling software. These synthetic data were used to train neural networks to predict three degree-of-freedom joint rotations at the hip and knee during gait either in lieu of or along with previously measured experimental gait data. The accuracy of the models’ kinematic predictions was assessed using experimentally measured IMU signals and gait kinematics. Models trained using the synthetic data out-performed models using only the experimental data in five of the six rotational degrees of freedom at the hip and knee. On average, root mean square errors in joint angle predictions were improved by 38% at the hip (synthetic data RMSE: 2.3°, measured data RMSE: 4.5°) and 11% at the knee (synthetic data RMSE: 2.9°, measured data RMSE: 3.3°), when models trained solely on synthetic data were compared to measured data. When models were trained on both measured and synthetic data, root mean square errors were reduced by 54% at the hip (measured + synthetic data RMSE: 1.9°) and 45% at the knee (measured + synthetic data RMSE: 1.7°), compared to measured data alone. These findings enable future model development for different activities of clinical significance without the burden of generating large quantities of gait lab data for model training, streamlining model development, and ultimately improving model performance. MDPI 2021-08-31 /pmc/articles/PMC8434290/ /pubmed/34502766 http://dx.doi.org/10.3390/s21175876 Text en © 2021 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
Sharifi Renani, Mohsen
Eustace, Abigail M.
Myers, Casey A.
Clary, Chadd W.
The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title_full The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title_fullStr The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title_full_unstemmed The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title_short The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions
title_sort use of synthetic imu signals in the training of deep learning models significantly improves the accuracy of joint kinematic predictions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8434290/
https://www.ncbi.nlm.nih.gov/pubmed/34502766
http://dx.doi.org/10.3390/s21175876
work_keys_str_mv AT sharifirenanimohsen theuseofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT eustaceabigailm theuseofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT myerscaseya theuseofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT clarychaddw theuseofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT sharifirenanimohsen useofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT eustaceabigailm useofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT myerscaseya useofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions
AT clarychaddw useofsyntheticimusignalsinthetrainingofdeeplearningmodelssignificantlyimprovestheaccuracyofjointkinematicpredictions