Cargando…

An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM

Many studies have used sensors attached to adults in order to collect signals by which one can carry out analyses to predict falls. In addition, there are research studies in which videos and photographs were used to extract and analyze body posture and body kinematics. The present study proposes an...

Descripción completa

Detalles Bibliográficos
Autores principales: Mobasheri, Bahareh, Tabbakh, Seyed Reza Kamel, Forghani, Yahya
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657864/
https://www.ncbi.nlm.nih.gov/pubmed/36360642
http://dx.doi.org/10.3390/ijerph192113762
_version_ 1784829803183996928
author Mobasheri, Bahareh
Tabbakh, Seyed Reza Kamel
Forghani, Yahya
author_facet Mobasheri, Bahareh
Tabbakh, Seyed Reza Kamel
Forghani, Yahya
author_sort Mobasheri, Bahareh
collection PubMed
description Many studies have used sensors attached to adults in order to collect signals by which one can carry out analyses to predict falls. In addition, there are research studies in which videos and photographs were used to extract and analyze body posture and body kinematics. The present study proposes an integrated approach consisting of body kinematics and machine learning. The model data consist of video recordings collected in the UP-Fall Detection dataset experiment. Three models based on long-short-term memory (LSTM) network—4p-SAFE, 5p-SAFE, and 6p-SAFE for four, five, and six parameters—were developed in this work. The parameters needed for these models consist of some coordinates and angles extracted from videos. These models are easy to apply to the sequential images collected by ordinary cameras, which are installed everywhere, especially on aged-care premises. The accuracy of predictions was as good as 98%. Finally, the authors discuss that, by applying these models, the health and wellness of adults and elderlies will be considerably promoted.
format Online
Article
Text
id pubmed-9657864
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96578642022-11-15 An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM Mobasheri, Bahareh Tabbakh, Seyed Reza Kamel Forghani, Yahya Int J Environ Res Public Health Article Many studies have used sensors attached to adults in order to collect signals by which one can carry out analyses to predict falls. In addition, there are research studies in which videos and photographs were used to extract and analyze body posture and body kinematics. The present study proposes an integrated approach consisting of body kinematics and machine learning. The model data consist of video recordings collected in the UP-Fall Detection dataset experiment. Three models based on long-short-term memory (LSTM) network—4p-SAFE, 5p-SAFE, and 6p-SAFE for four, five, and six parameters—were developed in this work. The parameters needed for these models consist of some coordinates and angles extracted from videos. These models are easy to apply to the sequential images collected by ordinary cameras, which are installed everywhere, especially on aged-care premises. The accuracy of predictions was as good as 98%. Finally, the authors discuss that, by applying these models, the health and wellness of adults and elderlies will be considerably promoted. MDPI 2022-10-22 /pmc/articles/PMC9657864/ /pubmed/36360642 http://dx.doi.org/10.3390/ijerph192113762 Text en © 2022 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
Mobasheri, Bahareh
Tabbakh, Seyed Reza Kamel
Forghani, Yahya
An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title_full An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title_fullStr An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title_full_unstemmed An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title_short An Approach for Fall Prediction Based on Kinematics of Body Key Points Using LSTM
title_sort approach for fall prediction based on kinematics of body key points using lstm
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657864/
https://www.ncbi.nlm.nih.gov/pubmed/36360642
http://dx.doi.org/10.3390/ijerph192113762
work_keys_str_mv AT mobasheribahareh anapproachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm
AT tabbakhseyedrezakamel anapproachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm
AT forghaniyahya anapproachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm
AT mobasheribahareh approachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm
AT tabbakhseyedrezakamel approachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm
AT forghaniyahya approachforfallpredictionbasedonkinematicsofbodykeypointsusinglstm