Cargando…

Classification-based Segmentation for Rehabilitation Exercise Monitoring

INTRODUCTION: Exercise segmentation, the process of isolating individual repetitions from continuous time series measurement of human motion, is key to providing online feedback to patients during rehabilitation and enables the computation of useful metrics such as joint velocity and range of motion...

Descripción completa

Detalles Bibliográficos
Autores principales: Lin, Jonathan Feng-Shun, Joukov, Vladimir, Kulić, Dana
Formato: Online Artículo Texto
Lenguaje:English
Publicado: SAGE Publications 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6453256/
https://www.ncbi.nlm.nih.gov/pubmed/31191926
http://dx.doi.org/10.1177/2055668318761523
_version_ 1783409386588209152
author Lin, Jonathan Feng-Shun
Joukov, Vladimir
Kulić, Dana
author_facet Lin, Jonathan Feng-Shun
Joukov, Vladimir
Kulić, Dana
author_sort Lin, Jonathan Feng-Shun
collection PubMed
description INTRODUCTION: Exercise segmentation, the process of isolating individual repetitions from continuous time series measurement of human motion, is key to providing online feedback to patients during rehabilitation and enables the computation of useful metrics such as joint velocity and range of motion that are otherwise difficult to measure in the clinical setting. METHODS: This paper proposes a classifier-based approach, where the motion segmentation problem is formulated as a two-class classification problem, classifying between segment and non-segment points. The proposed approach does not require domain knowledge of the exercises and generalizes to groups of participants and exercises that were not part of the training set, allowing for more robustness in clinical applications. RESULTS: Using only data from healthy participants for training, the proposed algorithm achieves an average segmentation accuracy of 92% on a 30-participant healthy dataset and 87% on a 44-patient rehabilitation dataset. CONCLUSION: A real-time approach for segmentation of rehabilitation exercises is proposed, based on two-class classification approach. The method is validated on both healthy and rehabilitation motion datasets and generalizes to a variety of demographics and exercises not part of the training set.
format Online
Article
Text
id pubmed-6453256
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher SAGE Publications
record_format MEDLINE/PubMed
spelling pubmed-64532562019-06-12 Classification-based Segmentation for Rehabilitation Exercise Monitoring Lin, Jonathan Feng-Shun Joukov, Vladimir Kulić, Dana J Rehabil Assist Technol Eng Original Article INTRODUCTION: Exercise segmentation, the process of isolating individual repetitions from continuous time series measurement of human motion, is key to providing online feedback to patients during rehabilitation and enables the computation of useful metrics such as joint velocity and range of motion that are otherwise difficult to measure in the clinical setting. METHODS: This paper proposes a classifier-based approach, where the motion segmentation problem is formulated as a two-class classification problem, classifying between segment and non-segment points. The proposed approach does not require domain knowledge of the exercises and generalizes to groups of participants and exercises that were not part of the training set, allowing for more robustness in clinical applications. RESULTS: Using only data from healthy participants for training, the proposed algorithm achieves an average segmentation accuracy of 92% on a 30-participant healthy dataset and 87% on a 44-patient rehabilitation dataset. CONCLUSION: A real-time approach for segmentation of rehabilitation exercises is proposed, based on two-class classification approach. The method is validated on both healthy and rehabilitation motion datasets and generalizes to a variety of demographics and exercises not part of the training set. SAGE Publications 2018-03-09 /pmc/articles/PMC6453256/ /pubmed/31191926 http://dx.doi.org/10.1177/2055668318761523 Text en © The Author(s) 2018 http://creativecommons.org/licenses/by-nc/4.0/ Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (http://www.creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).
spellingShingle Original Article
Lin, Jonathan Feng-Shun
Joukov, Vladimir
Kulić, Dana
Classification-based Segmentation for Rehabilitation Exercise Monitoring
title Classification-based Segmentation for Rehabilitation Exercise Monitoring
title_full Classification-based Segmentation for Rehabilitation Exercise Monitoring
title_fullStr Classification-based Segmentation for Rehabilitation Exercise Monitoring
title_full_unstemmed Classification-based Segmentation for Rehabilitation Exercise Monitoring
title_short Classification-based Segmentation for Rehabilitation Exercise Monitoring
title_sort classification-based segmentation for rehabilitation exercise monitoring
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6453256/
https://www.ncbi.nlm.nih.gov/pubmed/31191926
http://dx.doi.org/10.1177/2055668318761523
work_keys_str_mv AT linjonathanfengshun classificationbasedsegmentationforrehabilitationexercisemonitoring
AT joukovvladimir classificationbasedsegmentationforrehabilitationexercisemonitoring
AT kulicdana classificationbasedsegmentationforrehabilitationexercisemonitoring