Cargando…

Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear

The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in...

Descripción completa

Detalles Bibliográficos
Autores principales: Aznar-Gimeno, Rocío, Labata-Lezaun, Gorka, Adell-Lamora, Ana, Abadía-Gallego, David, del-Hoyo-Alonso, Rafael, González-Muñoz, Carlos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235668/
https://www.ncbi.nlm.nih.gov/pubmed/34205259
http://dx.doi.org/10.3390/e23060777
_version_ 1783714372120477696
author Aznar-Gimeno, Rocío
Labata-Lezaun, Gorka
Adell-Lamora, Ana
Abadía-Gallego, David
del-Hoyo-Alonso, Rafael
González-Muñoz, Carlos
author_facet Aznar-Gimeno, Rocío
Labata-Lezaun, Gorka
Adell-Lamora, Ana
Abadía-Gallego, David
del-Hoyo-Alonso, Rafael
González-Muñoz, Carlos
author_sort Aznar-Gimeno, Rocío
collection PubMed
description The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in order to prevent possible health problems in the elderly, facilitating their urban life as independently and safety as possible. This brings with it the challenge of handling the large amounts of data generated, transmitting and pre-processing that information and analysing it with the aim of obtaining useful information in real/near-real time. This is the basis of information theory. This work presents a complete system aiming at elderly people that can detect different user behaviours/events (sitting, standing without imbalance, standing with imbalance, walking, running, tripping) through information acquired from 20 types of sensor measurements (16 piezoelectric pressure sensors, one accelerometer returning reading for the 3 axis and one temperature sensor) and warn the relatives about possible risks in near-real time. For the detection of these events, a hierarchical structure of cascading binary models is designed and applied using artificial neural network (ANN) algorithms and deep learning techniques. The best models are achieved with convolutional layered ANN and multilayer perceptrons. The overall event detection performance achieves an average accuracy and area under the ROC curve of 0.84 and 0.96, respectively.
format Online
Article
Text
id pubmed-8235668
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82356682021-06-27 Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear Aznar-Gimeno, Rocío Labata-Lezaun, Gorka Adell-Lamora, Ana Abadía-Gallego, David del-Hoyo-Alonso, Rafael González-Muñoz, Carlos Entropy (Basel) Article The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in order to prevent possible health problems in the elderly, facilitating their urban life as independently and safety as possible. This brings with it the challenge of handling the large amounts of data generated, transmitting and pre-processing that information and analysing it with the aim of obtaining useful information in real/near-real time. This is the basis of information theory. This work presents a complete system aiming at elderly people that can detect different user behaviours/events (sitting, standing without imbalance, standing with imbalance, walking, running, tripping) through information acquired from 20 types of sensor measurements (16 piezoelectric pressure sensors, one accelerometer returning reading for the 3 axis and one temperature sensor) and warn the relatives about possible risks in near-real time. For the detection of these events, a hierarchical structure of cascading binary models is designed and applied using artificial neural network (ANN) algorithms and deep learning techniques. The best models are achieved with convolutional layered ANN and multilayer perceptrons. The overall event detection performance achieves an average accuracy and area under the ROC curve of 0.84 and 0.96, respectively. MDPI 2021-06-19 /pmc/articles/PMC8235668/ /pubmed/34205259 http://dx.doi.org/10.3390/e23060777 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
Aznar-Gimeno, Rocío
Labata-Lezaun, Gorka
Adell-Lamora, Ana
Abadía-Gallego, David
del-Hoyo-Alonso, Rafael
González-Muñoz, Carlos
Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title_full Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title_fullStr Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title_full_unstemmed Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title_short Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear
title_sort deep learning for walking behaviour detection in elderly people using smart footwear
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235668/
https://www.ncbi.nlm.nih.gov/pubmed/34205259
http://dx.doi.org/10.3390/e23060777
work_keys_str_mv AT aznargimenorocio deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear
AT labatalezaungorka deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear
AT adelllamoraana deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear
AT abadiagallegodavid deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear
AT delhoyoalonsorafael deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear
AT gonzalezmunozcarlos deeplearningforwalkingbehaviourdetectioninelderlypeopleusingsmartfootwear