Graduation Semester and Year

2015

Language

English

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science and Engineering

First Advisor

Manfred Huber

Abstract

Gait analysis is the investigation of an individual pattern of walking. Based on studies in Psychophysics, it has been shown that the human gait contains unique information that is useful for the evaluation of foot and gait pathologies. The goal of this project is to use a floor mounted pressure sensor system capable of measuring a significant number of parameters relevant to gait to predict and detect anomalous behavior. The system consists of an array of pressure sensors mounted under floor tiles and computer hardware responsible for data collection. The method used in this project is unique since most systems that perform similar functions are “on-body” systems using leg attached sensors, body tags or “off-body” systems using vision (camera). Our approach uses floor mounted pressure sensor which are designed to collect data unobtrusively, over long periods of time, and without interfering with gait or inconveniencing the user. The core of this thesis is aimed at the design of algorithms capable of differentiating parameter values that could be considered normal or abnormal for an individual and from these values draw further conclusions. To achieve this, data obtained from the floor mounted pressure sensor were calibrated and analyzed to extract information about the gait of a user. From this analyzed data, the center of pressure trajectories for each phase of the user’s gait cycle was obtained as well as the user’s weight, and dynamic characteristics of balance and step impact. With this information we intend to provide a new way for gait analysis, in order to predict fall risk and health issues and to improve elder care by constant monitoring and by reducing the white-coat syndrome that inhibits clinical examinations.

Disciplines

Computer Sciences | Physical Sciences and Mathematics

Comments

Degree granted by The University of Texas at Arlington

Download

Share

COinS