Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Estimation of lower extremity joint moments in Clinical Gait Analysis by using Artificial Neural Networks

Osateerakun, P (2022) Estimation of lower extremity joint moments in Clinical Gait Analysis by using Artificial Neural Networks. Doctoral thesis, Liverpool John Moores University.

2021phatcharapaphd.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial.

Download (7MB) | Preview


Gait analysis is typically conducted using an optoelectronic system which is known as the standard method for motion analysis. Despite advance development of instruments related to the optoelectronic approach, there are still a few limitations of the traditional gait analysis which limit the accessibility for individuals who would benefit from the investigation. A newly developed three-dimension motion capture system, known as Inertial Measurement Units (IMU) was introduced as an option for gait analysis. The IMU system is a transportable camera-free motion capture system. This also motivated the principle of out-of-the lab gait analysis. To broaden the use of the new system, this PhD project was conducted to examine whether the system should be used confidently for clinical gait analysis. The main purpose of this PhD project was to examine the feasibility of incorporating a machine learning method to estimate the kinetics of gait using the kinematics data obtained from an IMU system. Firstly, as pilot studies, an artificial neural network (ANN) was trained using gait data derived from the potential input signals which were signals of marker coordinates and joint angles obtained from an IMU system (Xsens) to predict joint moments of lower extremities. Promising findings were found as the ANN could reasonably predict the target joint moments. The results also showed the generalisation ability of the ANN to estimate the joint moment that it has not seen before, for instance, the ANN could fairly predict joint moments of the contralateral limb. The Xsens system was validated against the standard motion capture system before the main estimation study of the joint moment in gait began. The results revealed that joint angles obtained from the Xsens were comparable with the optoelectronic system in the sagittal plane and less comparable in the frontal plane according to the coefficient of multiple correlation and the linear fit methods. The results from the transverse plane were non-real numbers. The ANN was then trained using the joint angles derived from the Xsens system of three different walking speeds to predict the knee abduction moment (KAM). Gait data of 15 healthy volunteers were used to train the network. The ANN performed well, shown by small values of average normalised root mean square errors. Several methods were used to enhance the ANN performance. Due to the limited number of gait data used to train the network the randomisation of the input-target output data was performed. The results showed a remarkable improvement of the ANN performance. The best KAM estimation was found when the data of marker coordinates were used to train the ANN instead of joint angles. As few as three marker coordinates could provide sufficient information for the ANN to be trained and predict the KAM accurately. Principal component analysis was also used as input data manipulation and provided a reasonable KAM prediction. Overall, the kinematic gait data obtained from the Xsens could be used to train the ANN to predict the KAM in healthy gait. There is a possibility to combine machine learning methods with IMU data to produce a clinical gait analysis without the restriction of the traditional motion laboratory.

Item Type: Thesis (Doctoral)
Uncontrolled Keywords: Gait analysis, knee abduction moment, Artificial Neural Network, prediction joint moment
Subjects: Q Science > QA Mathematics > QA76 Computer software
R Medicine > RC Internal medicine > RC1200 Sports Medicine
Divisions: Sport & Exercise Sciences
Date Deposited: 22 Dec 2021 13:31
Last Modified: 22 Dec 2021 13:31
DOI or Identification number: 10.24377/LJMU.t.00015938
Supervisors: Barton, G
URI: https://researchonline.ljmu.ac.uk/id/eprint/15938

Actions (login required)

View Item View Item