Cargando…
Comparing algorithms for assessing upper limb use with inertial measurement units
The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a sin...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9806112/ https://www.ncbi.nlm.nih.gov/pubmed/36601345 http://dx.doi.org/10.3389/fphys.2022.1023589 |
_version_ | 1784862464410648576 |
---|---|
author | Subash, Tanya David, Ann ReetaJanetSurekha, StephenSukumaran Gayathri, Sankaralingam Samuelkamaleshkumar, Selvaraj Magimairaj, Henry Prakash Malesevic, Nebojsa Antfolk, Christian SKM, Varadhan Melendez-Calderon, Alejandro Balasubramanian, Sivakumar |
author_facet | Subash, Tanya David, Ann ReetaJanetSurekha, StephenSukumaran Gayathri, Sankaralingam Samuelkamaleshkumar, Selvaraj Magimairaj, Henry Prakash Malesevic, Nebojsa Antfolk, Christian SKM, Varadhan Melendez-Calderon, Alejandro Balasubramanian, Sivakumar |
author_sort | Subash, Tanya |
collection | PubMed |
description | The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a single dataset. While machine learning is a promising approach to detecting upper limb use, there is currently no knowledge of the information used by machine learning measures and the data-related factors that influence their performance. The current study conducted a direct comparison of the 1) thresholded activity counting measures, 2) gross movement score,3) a hybrid activity counting and gross movement score measure (introduced in this study), and 4) machine learning measures for detecting upper-limb use, using previously collected data. Two additional analyses were also performed to understand the nature of the information used by machine learning measures and the influence of data on the performance of machine learning measures. The intra-subject random forest machine learning measure detected upper limb use more accurately than all other measures, confirming previous observations in the literature. Among the non-machine learning (or traditional) algorithms, the hybrid activity counting and gross movement score measure performed better than the other measures. Further analysis of the random forest measure revealed that this measure used information about the forearm’s orientation and amount of movement to detect upper limb use. The performance of machine learning measures was influenced by the types of movements and the proportion of functional data in the training/testing datasets. The study outcomes show that machine learning measures perform better than traditional measures and shed some light on how these methods detect upper-limb use. However, in the absence of annotated data for training machine learning measures, the hybrid activity counting and gross movement score measure presents a reasonable alternative. We believe this paper presents a step towards understanding and optimizing measures for upper limb use assessment using wearable sensors. |
format | Online Article Text |
id | pubmed-9806112 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-98061122023-01-03 Comparing algorithms for assessing upper limb use with inertial measurement units Subash, Tanya David, Ann ReetaJanetSurekha, StephenSukumaran Gayathri, Sankaralingam Samuelkamaleshkumar, Selvaraj Magimairaj, Henry Prakash Malesevic, Nebojsa Antfolk, Christian SKM, Varadhan Melendez-Calderon, Alejandro Balasubramanian, Sivakumar Front Physiol Physiology The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a single dataset. While machine learning is a promising approach to detecting upper limb use, there is currently no knowledge of the information used by machine learning measures and the data-related factors that influence their performance. The current study conducted a direct comparison of the 1) thresholded activity counting measures, 2) gross movement score,3) a hybrid activity counting and gross movement score measure (introduced in this study), and 4) machine learning measures for detecting upper-limb use, using previously collected data. Two additional analyses were also performed to understand the nature of the information used by machine learning measures and the influence of data on the performance of machine learning measures. The intra-subject random forest machine learning measure detected upper limb use more accurately than all other measures, confirming previous observations in the literature. Among the non-machine learning (or traditional) algorithms, the hybrid activity counting and gross movement score measure performed better than the other measures. Further analysis of the random forest measure revealed that this measure used information about the forearm’s orientation and amount of movement to detect upper limb use. The performance of machine learning measures was influenced by the types of movements and the proportion of functional data in the training/testing datasets. The study outcomes show that machine learning measures perform better than traditional measures and shed some light on how these methods detect upper-limb use. However, in the absence of annotated data for training machine learning measures, the hybrid activity counting and gross movement score measure presents a reasonable alternative. We believe this paper presents a step towards understanding and optimizing measures for upper limb use assessment using wearable sensors. Frontiers Media S.A. 2022-12-19 /pmc/articles/PMC9806112/ /pubmed/36601345 http://dx.doi.org/10.3389/fphys.2022.1023589 Text en Copyright © 2022 Subash, David, ReetaJanetSurekha, Gayathri, Samuelkamaleshkumar, Magimairaj, Malesevic, Antfolk, SKM, Melendez-Calderon and Balasubramanian. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Physiology Subash, Tanya David, Ann ReetaJanetSurekha, StephenSukumaran Gayathri, Sankaralingam Samuelkamaleshkumar, Selvaraj Magimairaj, Henry Prakash Malesevic, Nebojsa Antfolk, Christian SKM, Varadhan Melendez-Calderon, Alejandro Balasubramanian, Sivakumar Comparing algorithms for assessing upper limb use with inertial measurement units |
title | Comparing algorithms for assessing upper limb use with inertial measurement units |
title_full | Comparing algorithms for assessing upper limb use with inertial measurement units |
title_fullStr | Comparing algorithms for assessing upper limb use with inertial measurement units |
title_full_unstemmed | Comparing algorithms for assessing upper limb use with inertial measurement units |
title_short | Comparing algorithms for assessing upper limb use with inertial measurement units |
title_sort | comparing algorithms for assessing upper limb use with inertial measurement units |
topic | Physiology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9806112/ https://www.ncbi.nlm.nih.gov/pubmed/36601345 http://dx.doi.org/10.3389/fphys.2022.1023589 |
work_keys_str_mv | AT subashtanya comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT davidann comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT reetajanetsurekhastephensukumaran comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT gayathrisankaralingam comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT samuelkamaleshkumarselvaraj comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT magimairajhenryprakash comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT malesevicnebojsa comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT antfolkchristian comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT skmvaradhan comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT melendezcalderonalejandro comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT balasubramaniansivakumar comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits |