Using lower limb wearable sensors to identify gait modalities: a machine-learning-based approach

Hughes, LD ORCID logoORCID: https://orcid.org/0000-0002-1787-7672, Bencsik, M ORCID logoORCID: https://orcid.org/0000-0002-6278-0378, Bisele, M and Barnett, CT ORCID logoORCID: https://orcid.org/0000-0001-6898-9095, 2023. Using lower limb wearable sensors to identify gait modalities: a machine-learning-based approach. Sensors, 23 (22): 9241. ISSN 1424-8220

Full text not available from this repository.

Abstract

Real-world gait analysis can aid in clinical assessments and influence related interventions, free from the restrictions of a laboratory setting. Using individual accelerometers, we aimed to use a simple machine learning method to quantify the performance of the discrimination between three self-selected cyclical locomotion types using accelerometers placed at frequently referenced attachment locations. Thirty-five participants walked along a 10 m walkway at three different speeds. Triaxial accelerometers were attached to the sacrum, thighs and shanks. Slabs of magnitude, three-second-long accelerometer data were transformed into two-dimensional Fourier spectra. Principal component analysis was undertaken for data reduction and feature selection, followed by discriminant function analysis for classification. Accuracy was quantified by calculating scalar accounting for the distances between the three centroids and the scatter of each category’s cloud. The algorithm could successfully discriminate between gait modalities with 91% accuracy at the sacrum, 90% at the shanks and 87% at the thighs. Modalities were discriminated with high accuracy in all three sensor locations, where the most accurate location was the sacrum. Future research will focus on optimising the data processing of information from sensor locations that are advantageous for practical reasons, e.g., shank for prosthetic and orthotic devices.

Item Type: Journal article
Publication Title: Sensors
Creators: Hughes, L.D., Bencsik, M., Bisele, M. and Barnett, C.T.
Publisher: MDPI
Date: 17 November 2023
Volume: 23
Number: 22
ISSN: 1424-8220
Identifiers:
Number
Type
10.3390/s23229241
DOI
1866165
Other
Rights: 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/).
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 27 Feb 2024 09:14
Last Modified: 27 Feb 2024 09:14
URI: https://irep.ntu.ac.uk/id/eprint/50947

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year