Scoring Performance on the Y-Balance Test Using a Deep Learning Approach

The Y Balance Test (YBT) is a dynamic balance assessment typically used in sports medicine. This work proposes a deep learning approach to automatically score this YBT by estimating the normalized reach distance (NRD) using a wearable sensor to register inertial signals during the movement. This pap...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Manuel Gil-Martín, William Johnston, Rubén San-Segundo, Brian Caulfield
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	wearable sensors Y Balance Test time series data recurrent neural networks Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/8abcf27ddae7415d804981cdfbaa1165
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8abcf27ddae7415d804981cdfbaa1165
record_format	dspace
spelling	oai:doaj.org-article:8abcf27ddae7415d804981cdfbaa11652021-11-11T19:07:10ZScoring Performance on the Y-Balance Test Using a Deep Learning Approach10.3390/s212171101424-8220https://doaj.org/article/8abcf27ddae7415d804981cdfbaa11652021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7110https://doaj.org/toc/1424-8220The Y Balance Test (YBT) is a dynamic balance assessment typically used in sports medicine. This work proposes a deep learning approach to automatically score this YBT by estimating the normalized reach distance (NRD) using a wearable sensor to register inertial signals during the movement. This paper evaluates several signal processing techniques to extract relevant information to feed the deep neural network. This evaluation was performed using a state-of-the-art human activity recognition system based on recurrent neural networks (RNNs). This deep neural network includes long short-term memory (LSTM) layers to learn features from time series by modeling temporal patterns and an additional fully connected layer to estimate the NRD (normalized by the leg length). All analyses were carried out using a dataset with YBT assessments from 407 subjects, including young and middle-aged volunteers and athletes from different sports. This dataset allowed developing a global and robust solution for scoring the YBT in a wide range of applications. The experimentation setup considered a 10-fold subject-wise cross-validation using training, validation, and testing subsets. The mean absolute percentage error (MAPE) obtained was 7.88 ± 0.20%. Moreover, this work proposes specific regression systems to estimate the NRD for each direction separately, obtaining an average MAPE of 7.33 ± 0.26%. This deep learning approach was compared to a previous work using dynamic time warping and k-NN algorithms, obtaining a relative MAPE reduction of 10%.Manuel Gil-MartínWilliam JohnstonRubén San-SegundoBrian CaulfieldMDPI AGarticlewearable sensorsY Balance Testtime series datarecurrent neural networksChemical technologyTP1-1185ENSensors, Vol 21, Iss 7110, p 7110 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	wearable sensors Y Balance Test time series data recurrent neural networks Chemical technology TP1-1185
spellingShingle	wearable sensors Y Balance Test time series data recurrent neural networks Chemical technology TP1-1185 Manuel Gil-Martín William Johnston Rubén San-Segundo Brian Caulfield Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
description	The Y Balance Test (YBT) is a dynamic balance assessment typically used in sports medicine. This work proposes a deep learning approach to automatically score this YBT by estimating the normalized reach distance (NRD) using a wearable sensor to register inertial signals during the movement. This paper evaluates several signal processing techniques to extract relevant information to feed the deep neural network. This evaluation was performed using a state-of-the-art human activity recognition system based on recurrent neural networks (RNNs). This deep neural network includes long short-term memory (LSTM) layers to learn features from time series by modeling temporal patterns and an additional fully connected layer to estimate the NRD (normalized by the leg length). All analyses were carried out using a dataset with YBT assessments from 407 subjects, including young and middle-aged volunteers and athletes from different sports. This dataset allowed developing a global and robust solution for scoring the YBT in a wide range of applications. The experimentation setup considered a 10-fold subject-wise cross-validation using training, validation, and testing subsets. The mean absolute percentage error (MAPE) obtained was 7.88 ± 0.20%. Moreover, this work proposes specific regression systems to estimate the NRD for each direction separately, obtaining an average MAPE of 7.33 ± 0.26%. This deep learning approach was compared to a previous work using dynamic time warping and k-NN algorithms, obtaining a relative MAPE reduction of 10%.
format	article
author	Manuel Gil-Martín William Johnston Rubén San-Segundo Brian Caulfield
author_facet	Manuel Gil-Martín William Johnston Rubén San-Segundo Brian Caulfield
author_sort	Manuel Gil-Martín
title	Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
title_short	Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
title_full	Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
title_fullStr	Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
title_full_unstemmed	Scoring Performance on the Y-Balance Test Using a Deep Learning Approach
title_sort	scoring performance on the y-balance test using a deep learning approach
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8abcf27ddae7415d804981cdfbaa1165
work_keys_str_mv	AT manuelgilmartin scoringperformanceontheybalancetestusingadeeplearningapproach AT williamjohnston scoringperformanceontheybalancetestusingadeeplearningapproach AT rubensansegundo scoringperformanceontheybalancetestusingadeeplearningapproach AT briancaulfield scoringperformanceontheybalancetestusingadeeplearningapproach
_version_	1718431596886884352

Scoring Performance on the Y-Balance Test Using a Deep Learning Approach

Ejemplares similares