Dissertation/Thesis Abstract

Exploring Inertial Measurement Unit Based Position Estimation Method and Deep Learning Predictive Model for Virtual Reality Stroke Rehabilitation System
by Sable, Anurag, M.S., University of Colorado at Denver, 2019, 48; 13885808
Abstract (Summary)

Stroke is the third largest cause of fatalities in the United States, also causing long-term mobility disabilities in many patients. Every year, around 795,000 people suffer from stroke, out of which 185,000 are recurrent attacks. Hence, as the numbers indicate, quality post-stroke treatment and rehabilitation are necessary to avoid recurrent attacks and permanent disabilities. In this thesis, we contributed towards developing and implementing IMU based Position Estimation algorithm and Deep Learning based Predictor for VRInsole, an intuitive, smart and innovative method for home-based post-stroke rehabilitation, targeted at lower extremity mobility training. For this, we employ three key ideas: (i) SmartInsole, which is a smart wearable sensor for collecting motion data including linear acceleration, angular rate and magnetic force which are inherently time-series, (ii) Position Estimation algorithm which processes the collected data to estimate user activity in real world and (iii) Deep Learning Predictor, in order to make the system more intuitive to user input by detecting what activity is being performed. SmartInsole is an unobtrusive wearable sensor, which contains an onboard nine-axis Inertial Measurement Unit (IMU), which enables us to gather fine-grained information about user movement. For Deep Learning method, we designed a Long Short-Term Memory (LSTM) architecture, which is a class of Artificial Neural Networks, highly suitable for predicting time-series data. We demonstrate the performance of the proposed model by comparing its performance with state-of-the-art methods. Moreover, we developed an algorithm to estimate user activities based only on the displacement and orientation of their foot. We compared the results of this algorithm against real-world measurements to demonstrate higher estimation accuracy.

Indexing (document details)
Advisor: Lin, Feng
Commitee: Biswas, Ashis Kumer, Choi, Min-Hyung
School: University of Colorado at Denver
Department: Computer Science
School Location: United States -- Colorado
Source: MAI 58/06M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Computer science
Keywords: Deep learning, Inertial measurement unit, Long short term memory, Orientation estimation, Position estimation, Stroke rehabilitation
Publication Number: 13885808
ISBN: 978-1-392-18252-9
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest