Machine-Learning Applications to Gait Biomechanics using Inertial Sensor Signals

Santhiranayagam, Braveena K (2016) Machine-Learning Applications to Gait Biomechanics using Inertial Sensor Signals. PhD thesis, Victoria University.

Abstract

Minimum toe clearance (MTC) above the walking surface is a critical representation of toe-trajectory control related to tripping risk. Reliable and precise MTC measurements are obtained in the laboratory using 3D motion capture technology. Real-world gait monitoring using body-mounted sensors presents considerable data processing challenges when estimating kinematic parameters, including MTC. This Thesis represents the first study employing machine-learning to estimate young and older adults’ toe-height at MTC using inertial data captured from a foot-mounted sensor. Age-group specific Generalized Regression Neural Network (GRNN) models estimated MTC with root-mean-square-error (RMSE) of 6.6 mm with 9 optimum inertial-signal features for the young and 7.1 mm with 5 features for the older during treadmill walking. These RMSE values are approximately one third of the previously reported (Mariani et al., 2012; McGrath et al., 2011) and GRNN modeling also performed well as reflected in no significant difference between 3D measured reference and model estimated MTC_Height. The GRNN model specific to older adults showed good generalizability when applied to data from slower and dual task walking.

Item type Thesis (PhD thesis)
URI https://vuir.vu.edu.au/id/eprint/34110
Subjects Historical > FOR Classification > 0801 Artificial Intelligence and Image Processing
Historical > FOR Classification > 1106 Human Movement and Sports Science
Historical > Faculty/School/Research Centre/Department > Institute of Sport, Exercise and Active Living (ISEAL)
Current > Division/Research > College of Sports and Exercise Science
Keywords neural networks, sensors, falls, IMUs, intertial measurement units, ageing, models, modelling
Download/View statistics View download statistics for this item

Search Google Scholar

Repository staff login