Democratizing clinical movement analysis: assessing the versatility of MoJoXlab with open-protocol inertial sensors

Islam, Riasat, Bennasar, Mohamed, Al-Amri, Mohammad ORCID: https://orcid.org/0000-0003-2806-0462, Holland, Simon, Mulholland, Paul and Price, Blaine 2024. Democratizing clinical movement analysis: assessing the versatility of MoJoXlab with open-protocol inertial sensors. Presented at: 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, Seville, Spain, 11 - 13 September 2024. Procedia Computer Science. , vol.246 Elsevier, pp. 2360-2369. 10.1016/j.procs.2024.09.536

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (2MB)

Abstract

This study evaluated the versatility of the MoJoXlab in conducting clinical movement analysis using inertial sensors from various manufacturers, including low-cost, non-proprietary, and open-protocol wearable options. Data were collected from 15 healthy participants who performed a range of clinically relevant activities and exercises using two sets of sensors. Dynamic time warping analysis of the sensor signals suggested that the collected dataset could be used for further algorithm development. The findings demonstrate that the current iteration of MoJoXlab can perform movement analysis using quaternions from sensors of any manufacturer. However, the accuracy of the resulting joint angles is not yet suitable for clinical applications across all sensor types, and only Xsens and NGIMU sensors are currently supported. This study also explored the potential for reducing the number of sensors required by MoJoXlab, which currently uses seven sensors to calculate joint angles for three joints (hip, knee and ankle) on both sides of the body. The creation of a comprehensive databank for lower limb movement analysis algorithms was an additional outcome of this work. Further research and development are necessary to expand MoJoXlab’s support for multiple sensor manufacturers and improve the accuracy of joint angle calculations for clinical applications.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Healthcare Sciences
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by-nc-nd/4.0/, Start Date: 2024-09-25
Publisher:	Elsevier
ISSN:	1877-0509
Date of First Compliant Deposit:	3 December 2024
Last Modified:	03 Dec 2024 13:15
URI:	https://orca.cardiff.ac.uk/id/eprint/174460

Actions (repository staff only)

Edit Item