Main content

Activity and Gait Phase Recognition for Walking, Stair Ascent, and Stair Descent

Show full item record

Title: Activity and Gait Phase Recognition for Walking, Stair Ascent, and Stair Descent
Author: Bauman, Valerie
Department: School of Engineering
Program: Engineering
Advisor: Brandon, Scott
Abstract: Activity and gait phase recognition algorithms are used in powered motion assistive devices to inform control of motorized parts. This thesis includes the development and evaluation of two independent recognition algorithms for walking, stair ascent, and stair descent activities. The first algorithm detected foot-contact and foot-off gait events within these activities and detected these events within 0.04s of a force plate. The second algorithm was machine learning-based and was developed using inertial measurement data from 80 participants. It simultaneously detected activity and gait phase with 91.2% accuracy and 22.9% of perfectly classified strides. Results from this thesis support the use of FSRs for data labelling for machine learning-based recognition models, the use of machine learning to detect activity and gait phase for walking, stair ascent, and stair descent, as well as the use of proportion of perfectly classified strides as a metric to evaluate activity and gait phase recognition algorithms.
URI: https://hdl.handle.net/10214/26320
Date: 2021-08
Rights: Attribution 4.0 International


Files in this item

Files Size Format View
Bauman_Valerie_202108_MASc.pdf 1.896Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International