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...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2022.1023589/full |
| _version_ | 1811196557844807680 |
|---|---|
| author | Tanya Subash Tanya Subash Ann David Ann David StephenSukumaran ReetaJanetSurekha Sankaralingam Gayathri Selvaraj Samuelkamaleshkumar Henry Prakash Magimairaj Nebojsa Malesevic Christian Antfolk Varadhan SKM Alejandro Melendez-Calderon Alejandro Melendez-Calderon Alejandro Melendez-Calderon Sivakumar Balasubramanian |
| author_facet | Tanya Subash Tanya Subash Ann David Ann David StephenSukumaran ReetaJanetSurekha Sankaralingam Gayathri Selvaraj Samuelkamaleshkumar Henry Prakash Magimairaj Nebojsa Malesevic Christian Antfolk Varadhan SKM Alejandro Melendez-Calderon Alejandro Melendez-Calderon Alejandro Melendez-Calderon Sivakumar Balasubramanian |
| author_sort | Tanya Subash |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-04-12T00:59:46Z |
| format | Article |
| id | doaj.art-25d421cced5746619036b7ef1304053f |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-12T00:59:46Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-25d421cced5746619036b7ef1304053f2022-12-22T03:54:29ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-12-011310.3389/fphys.2022.10235891023589Comparing algorithms for assessing upper limb use with inertial measurement unitsTanya Subash0Tanya Subash1Ann David2Ann David3StephenSukumaran ReetaJanetSurekha4Sankaralingam Gayathri5Selvaraj Samuelkamaleshkumar6Henry Prakash Magimairaj7Nebojsa Malesevic8Christian Antfolk9Varadhan SKM10Alejandro Melendez-Calderon11Alejandro Melendez-Calderon12Alejandro Melendez-Calderon13Sivakumar Balasubramanian14Department of Bioengineering, Christian Medical College, Vellore, IndiaDepartment of Mechanical Engineering, Indian Institute of Technology Madras, Chennai, IndiaDepartment of Bioengineering, Christian Medical College, Vellore, IndiaDepartment of Applied Mechanics, Indian Institute of Technology Madras, Chennai, IndiaDepartment of Physical Medicine and Rehabilitation, Christian Medical College, Vellore, IndiaDepartment of Physical Medicine and Rehabilitation, Christian Medical College, Vellore, IndiaDepartment of Physical Medicine and Rehabilitation, Christian Medical College, Vellore, IndiaDepartment of Physical Medicine and Rehabilitation, Christian Medical College, Vellore, IndiaDepartment of Biomedical Engineering, Lund University, Lund, SwedenDepartment of Biomedical Engineering, Lund University, Lund, SwedenDepartment of Applied Mechanics, Indian Institute of Technology Madras, Chennai, IndiaSchool of Information Technology and Electrical Engineering, University of Queensland, Brisbane, AustraliaSchool of Health and Rehabilitation Sciences, The University of Queensland, Brisbane, AustraliaJamieson Trauma Institute, Metro North Hospital and Health Service, Brisbane, AustraliaDepartment of Bioengineering, Christian Medical College, Vellore, IndiaThe 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.https://www.frontiersin.org/articles/10.3389/fphys.2022.1023589/fullhemiparesismachine learningsensorimotor assessmentupper-limb rehabilitationupper-limb usewearable sensors |
| spellingShingle | Tanya Subash Tanya Subash Ann David Ann David StephenSukumaran ReetaJanetSurekha Sankaralingam Gayathri Selvaraj Samuelkamaleshkumar Henry Prakash Magimairaj Nebojsa Malesevic Christian Antfolk Varadhan SKM Alejandro Melendez-Calderon Alejandro Melendez-Calderon Alejandro Melendez-Calderon Sivakumar Balasubramanian Comparing algorithms for assessing upper limb use with inertial measurement units Frontiers in Physiology hemiparesis machine learning sensorimotor assessment upper-limb rehabilitation upper-limb use wearable sensors |
| 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 | hemiparesis machine learning sensorimotor assessment upper-limb rehabilitation upper-limb use wearable sensors |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2022.1023589/full |
| work_keys_str_mv | AT tanyasubash comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT tanyasubash comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT anndavid comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT anndavid comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT stephensukumaranreetajanetsurekha comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT sankaralingamgayathri comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT selvarajsamuelkamaleshkumar comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT henryprakashmagimairaj comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT nebojsamalesevic comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT christianantfolk comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT varadhanskm comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT alejandromelendezcalderon comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT alejandromelendezcalderon comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT alejandromelendezcalderon comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits AT sivakumarbalasubramanian comparingalgorithmsforassessingupperlimbusewithinertialmeasurementunits |