Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Evaluation of Machine Learning Methods to Predict Knee Loading from the Movement of Body Segments

Aljaaf, A, Hussain, A, Fergus, P, Przybyla, A and Barton, GJ (2016) Evaluation of Machine Learning Methods to Predict Knee Loading from the Movement of Body Segments. In: Neural Networks (IJCNN) . (IEEE World Congress on Computational Intelligence, 24 July 2016 - 29 July 2016, Canada).

[img] Text
Evaluation of Machine Learning Methods to Predict Knee Loading from the Movement of Body Segments-final copy.pdf - Accepted Version
Restricted to Repository staff only

Download (726kB)

Abstract

Abnormal joint moments during gait are validated predictors of knee pain in osteoarthritis. Calculation of moments necessitates measurement of forces and moment arms about joints during walking. Dynamically changing moment arms can be calculated from motion trackers either optically or with wireless inertia sensing units, but the measurement of forces is more problematic. Either the patient has to walk over a force platform or a force sensing device has to be built into the sole of the shoes. One possible means of registering abnormal join moments without the restrictions due to force measurements is to predict moments from the movement of body segments using advanced machine learning techniques. To test the viability of this approach, we aimed to predict the frontal plane internal knee abduction moment form 3D Euler angles of the ankle, knee, hip and pelvis during a single gait cycle of 31 patients with alkaptonuria. Four machine learning algorithms were used in our experiment to predict moments namely: Decision Tree, Random Forest, Linear Regression and Multilayer Perceptron neural network. Based on performance measures of prediction (R2, root mean squared error and area under the recall curve), the random forest algorithm performed best but this was also the slowest by a factor of 10. Considering both performance and speed, the Multilayer Perceptron neural network method was superior with R2, root mean square of error, area under the recall curve and required training time of 0.8616, 0.0743, 0.874 and 730 ms, respectively.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Computer software
R Medicine > RC Internal medicine > RC1200 Sports Medicine
Divisions: Computer Science & Mathematics
Sport & Exercise Sciences
Publisher: IEEE
Date Deposited: 16 Mar 2016 15:58
Last Modified: 13 Apr 2022 15:14
URI: https://researchonline.ljmu.ac.uk/id/eprint/3279
View Item View Item