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...
Autores principales: | , , , |
---|---|
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 |