Research Repository

Predicting the Internal Knee Abduction Impulse During Walking Using Deep Learning

Boukhennoufa, Issam and Altai, Zainab and Zhai, Xiaojun and Utti, Victor and McDonald-Maier, Klaus D and Liew, Bernard (2022) 'Predicting the Internal Knee Abduction Impulse During Walking Using Deep Learning.' Frontiers in Bioengineering and Biotechnology, 10. 877347-. ISSN 2296-4185

[img]
Preview
Text
fbioe-10-877347.pdf - Published Version
Available under License Creative Commons Attribution.

Download (830kB) | Preview

Abstract

Knee joint moments are commonly calculated to provide an indirect measure of knee joint loads. A shortcoming of inverse dynamics approaches is that the process of collecting and processing human motion data can be time-consuming. This study aimed to benchmark five different deep learning methods in using walking segment kinematics for predicting internal knee abduction impulse during walking. Three-dimensional kinematic and kinetic data used for the present analyses came from a publicly available dataset on walking (participants <jats:italic>n</jats:italic> = 33). The outcome for prediction was the internal knee abduction impulse over the stance phase. Three-dimensional (3D) angular and linear displacement, velocity, and acceleration of the seven lower body segment’s center of mass (COM), relative to a fixed global coordinate system were derived and formed the predictor space (126 time-series predictors). The total number of observations in the dataset was 6,737. The datasets were split into training (75%, <jats:italic>n</jats:italic> = 5,052) and testing (25%, <jats:italic>n</jats:italic> = 1685) datasets. Five deep learning models were benchmarked against inverse dynamics in quantifying knee abduction impulse. A baseline 2D convolutional network model achieved a mean absolute percentage error (MAPE) of 10.80%. Transfer learning with InceptionTime was the best performing model, achieving the best MAPE of 8.28%. Encoding the time-series as images then using a 2D convolutional model performed worse than the baseline model with a MAPE of 16.17%. Time-series based deep learning models were superior to an image-based method when predicting knee abduction moment impulse during walking. Future studies looking to develop wearable technologies will benefit from knowing the optimal network architecture, and the benefit of transfer learning for predicting joint moments.

Item Type: Article
Uncontrolled Keywords: gait biomechanics, knee joint moments, machine learning, neural network, time-series
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Faculty of Science and Health > Sport, Rehabilitation and Exercise Sciences, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 27 May 2022 10:40
Last Modified: 10 Jun 2022 23:31
URI: http://repository.essex.ac.uk/id/eprint/32915

Actions (login required)

View Item View Item