A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors

Gait performance is an important marker of motor and cognitive decline in older adults. An instrumented gait analysis resorting to inertial sensors allows the complete evaluation of spatiotemporal gait parameters, offering an alternative to laboratory-based assessments. To estimate gait parameters,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Vânia Guimarães, Inês Sousa, Miguel Velhote Correia
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	inertial sensors gait analysis foot trajectory deep learning long short-term memory (LSTM) networks Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/1d1bbf7a71f949f0980e6d299fb88fb0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1d1bbf7a71f949f0980e6d299fb88fb0
record_format	dspace
spelling	oai:doaj.org-article:1d1bbf7a71f949f0980e6d299fb88fb02021-11-25T18:57:04ZA Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors10.3390/s212275171424-8220https://doaj.org/article/1d1bbf7a71f949f0980e6d299fb88fb02021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7517https://doaj.org/toc/1424-8220Gait performance is an important marker of motor and cognitive decline in older adults. An instrumented gait analysis resorting to inertial sensors allows the complete evaluation of spatiotemporal gait parameters, offering an alternative to laboratory-based assessments. To estimate gait parameters, foot trajectories are typically obtained by integrating acceleration two times. However, to deal with cumulative integration errors, additional error handling strategies are required. In this study, we propose an alternative approach based on a deep recurrent neural network to estimate heel and toe trajectories. We propose a coordinate frame transformation for stride trajectories that eliminates the dependency from previous strides and external inputs. Predicted trajectories are used to estimate an extensive set of spatiotemporal gait parameters. We evaluate the results in a dataset comprising foot-worn inertial sensor data acquired from a group of young adults, using an optical motion capture system as a reference. Heel and toe trajectories are predicted with low errors, in line with reference trajectories. A good agreement is also achieved between the reference and estimated gait parameters, in particular when turning strides are excluded from the analysis. The performance of the method is shown to be robust to imperfect sensor-foot alignment conditions.Vânia GuimarãesInês SousaMiguel Velhote CorreiaMDPI AGarticleinertial sensorsgait analysisfoot trajectorydeep learninglong short-term memory (LSTM) networksChemical technologyTP1-1185ENSensors, Vol 21, Iss 7517, p 7517 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	inertial sensors gait analysis foot trajectory deep learning long short-term memory (LSTM) networks Chemical technology TP1-1185
spellingShingle	inertial sensors gait analysis foot trajectory deep learning long short-term memory (LSTM) networks Chemical technology TP1-1185 Vânia Guimarães Inês Sousa Miguel Velhote Correia A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
description	Gait performance is an important marker of motor and cognitive decline in older adults. An instrumented gait analysis resorting to inertial sensors allows the complete evaluation of spatiotemporal gait parameters, offering an alternative to laboratory-based assessments. To estimate gait parameters, foot trajectories are typically obtained by integrating acceleration two times. However, to deal with cumulative integration errors, additional error handling strategies are required. In this study, we propose an alternative approach based on a deep recurrent neural network to estimate heel and toe trajectories. We propose a coordinate frame transformation for stride trajectories that eliminates the dependency from previous strides and external inputs. Predicted trajectories are used to estimate an extensive set of spatiotemporal gait parameters. We evaluate the results in a dataset comprising foot-worn inertial sensor data acquired from a group of young adults, using an optical motion capture system as a reference. Heel and toe trajectories are predicted with low errors, in line with reference trajectories. A good agreement is also achieved between the reference and estimated gait parameters, in particular when turning strides are excluded from the analysis. The performance of the method is shown to be robust to imperfect sensor-foot alignment conditions.
format	article
author	Vânia Guimarães Inês Sousa Miguel Velhote Correia
author_facet	Vânia Guimarães Inês Sousa Miguel Velhote Correia
author_sort	Vânia Guimarães
title	A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
title_short	A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
title_full	A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
title_fullStr	A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
title_full_unstemmed	A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors
title_sort	deep learning approach for foot trajectory estimation in gait analysis using inertial sensors
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1d1bbf7a71f949f0980e6d299fb88fb0
work_keys_str_mv	AT vaniaguimaraes adeeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors AT inessousa adeeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors AT miguelvelhotecorreia adeeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors AT vaniaguimaraes deeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors AT inessousa deeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors AT miguelvelhotecorreia deeplearningapproachforfoottrajectoryestimationingaitanalysisusinginertialsensors
_version_	1718410510672592896

A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors

Ejemplares similares