Cargando…

Gait Stride Length Estimation Using Embedded Machine Learning

Introduction. Spatiotemporal gait parameters, e.g., gait stride length, are measurements that are classically derived from instrumented gait analysis. Today, different solutions are available for gait assessment outside the laboratory, specifically for spatiotemporal gait parameters. Such solutions...

Descripción completa

Detalles Bibliográficos
Autores principales: Verbiest, Joeri R., Bonnechère, Bruno, Saeys, Wim, Van de Walle, Patricia, Truijen, Steven, Meyns, Pieter
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10459491/
https://www.ncbi.nlm.nih.gov/pubmed/37631706
http://dx.doi.org/10.3390/s23167166
_version_ 1785097424150200320
author Verbiest, Joeri R.
Bonnechère, Bruno
Saeys, Wim
Van de Walle, Patricia
Truijen, Steven
Meyns, Pieter
author_facet Verbiest, Joeri R.
Bonnechère, Bruno
Saeys, Wim
Van de Walle, Patricia
Truijen, Steven
Meyns, Pieter
author_sort Verbiest, Joeri R.
collection PubMed
description Introduction. Spatiotemporal gait parameters, e.g., gait stride length, are measurements that are classically derived from instrumented gait analysis. Today, different solutions are available for gait assessment outside the laboratory, specifically for spatiotemporal gait parameters. Such solutions are wearable devices that comprise an inertial measurement unit (IMU) sensor and a microcontroller (MCU). However, these existing wearable devices are resource-constrained. They contain a processing unit with limited processing and memory capabilities which limit the use of machine learning to estimate spatiotemporal gait parameters directly on the device. The solution for this limitation is embedded machine learning or tiny machine learning (tinyML). This study aims to create a machine-learning model for gait stride length estimation deployable on a microcontroller. Materials and Method. Starting from a dataset consisting of 4467 gait strides from 15 healthy people, measured by IMU sensor, and using state-of-the-art machine learning frameworks and machine learning operations (MLOps) tools, a multilayer 1D convolutional float32 and int8 model for gait stride length estimation was developed. Results. The developed float32 model demonstrated a mean accuracy and precision of 0.23 ± 4.3 cm, and the int8 model demonstrated a mean accuracy and precision of 0.07 ± 4.3 cm. The memory usage for the float32 model was 284.5 kB flash and 31.9 kB RAM. The int8 model memory usage was 91.6 kB flash and 13.6 kB RAM. Both models were able to be deployed on a Cortex-M4F 64 MHz microcontroller with 1 MB flash memory and 256 kB RAM. Conclusions. This study shows that estimating gait stride length directly on a microcontroller is feasible and demonstrates the potential of embedded machine learning, or tinyML, in designing wearable sensor devices for gait analysis.
format Online
Article
Text
id pubmed-10459491
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104594912023-08-27 Gait Stride Length Estimation Using Embedded Machine Learning Verbiest, Joeri R. Bonnechère, Bruno Saeys, Wim Van de Walle, Patricia Truijen, Steven Meyns, Pieter Sensors (Basel) Article Introduction. Spatiotemporal gait parameters, e.g., gait stride length, are measurements that are classically derived from instrumented gait analysis. Today, different solutions are available for gait assessment outside the laboratory, specifically for spatiotemporal gait parameters. Such solutions are wearable devices that comprise an inertial measurement unit (IMU) sensor and a microcontroller (MCU). However, these existing wearable devices are resource-constrained. They contain a processing unit with limited processing and memory capabilities which limit the use of machine learning to estimate spatiotemporal gait parameters directly on the device. The solution for this limitation is embedded machine learning or tiny machine learning (tinyML). This study aims to create a machine-learning model for gait stride length estimation deployable on a microcontroller. Materials and Method. Starting from a dataset consisting of 4467 gait strides from 15 healthy people, measured by IMU sensor, and using state-of-the-art machine learning frameworks and machine learning operations (MLOps) tools, a multilayer 1D convolutional float32 and int8 model for gait stride length estimation was developed. Results. The developed float32 model demonstrated a mean accuracy and precision of 0.23 ± 4.3 cm, and the int8 model demonstrated a mean accuracy and precision of 0.07 ± 4.3 cm. The memory usage for the float32 model was 284.5 kB flash and 31.9 kB RAM. The int8 model memory usage was 91.6 kB flash and 13.6 kB RAM. Both models were able to be deployed on a Cortex-M4F 64 MHz microcontroller with 1 MB flash memory and 256 kB RAM. Conclusions. This study shows that estimating gait stride length directly on a microcontroller is feasible and demonstrates the potential of embedded machine learning, or tinyML, in designing wearable sensor devices for gait analysis. MDPI 2023-08-14 /pmc/articles/PMC10459491/ /pubmed/37631706 http://dx.doi.org/10.3390/s23167166 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
Verbiest, Joeri R.
Bonnechère, Bruno
Saeys, Wim
Van de Walle, Patricia
Truijen, Steven
Meyns, Pieter
Gait Stride Length Estimation Using Embedded Machine Learning
title Gait Stride Length Estimation Using Embedded Machine Learning
title_full Gait Stride Length Estimation Using Embedded Machine Learning
title_fullStr Gait Stride Length Estimation Using Embedded Machine Learning
title_full_unstemmed Gait Stride Length Estimation Using Embedded Machine Learning
title_short Gait Stride Length Estimation Using Embedded Machine Learning
title_sort gait stride length estimation using embedded machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10459491/
https://www.ncbi.nlm.nih.gov/pubmed/37631706
http://dx.doi.org/10.3390/s23167166
work_keys_str_mv AT verbiestjoerir gaitstridelengthestimationusingembeddedmachinelearning
AT bonnecherebruno gaitstridelengthestimationusingembeddedmachinelearning
AT saeyswim gaitstridelengthestimationusingembeddedmachinelearning
AT vandewallepatricia gaitstridelengthestimationusingembeddedmachinelearning
AT truijensteven gaitstridelengthestimationusingembeddedmachinelearning
AT meynspieter gaitstridelengthestimationusingembeddedmachinelearning