Electronic Theses and Dissertations

Identifier

6461

Sharmin Afroz

Date

2019

Document Type

Thesis

Degree Name

Master of Science

Major

Electrical and Computer Engr

Concentration

Computer Engineering

Committee Chair

Bashir Morshed

Committee Member

Hasan Ali

Committee Member

Aaron L. Robinson

Abstract

Smart and Connected Community (SCC) will use health data of the community members for knowledge generation beyond mobile health (mHealth). Current mHealth only assists individual users to monitor their health status, but do not allow integration and interpretation of collective health data. The objective of this thesis is to exhibit the continuous health status of the community members through a framework of visualization including spatial and temporal plots, such as anonymous user health severity graph, severity flow plot, a severity map view, the cumulative and segmented animation. The framework composes of physiological data collection with smartphones and sharing of anonymous data to SCC health server. Physiological data is sent from the smartphone app in JSON (JavaScript Object Notation) format and stored in the server database. Temporal visualization is presented as graph and flow, whereas spatial visualization utilizes Google Map overlay to display the severity distribution through the color code of severity. Furthermore, an animation mode is developed that displays combined spatiotemporal data over the selected duration in either cumulative or segmented at specified intervals. To implement this, a web-based dynamic server is used. The front end of the server is built with JavaScript JQuery and Ajax, whereas the backend of the server is managed by Hypertext Preprocessor, i.e. PHP, a server-side scripting language. The phpMyAdmin (administration tool for MySQL) stores the JSON data that comes from the smartphone app. To assess the framework, we utilized the MIT-BIH database with pre-recorded data from Arrhythmia patients. We assume each dataset record as a community member (subject). From these records, we classified arrhythmia and measure severity ranging from 0 to 100 considering various severity of arrhythmia (e.g. ventricular tachycardia is the most severe). These data are then randomized to a different location and fed to the visualization tool for functionally verify and assess the performance of the visualization tool. Furthermore, a survey was conducted to collect feedback about the visualization tool that shows that 81.4% participants in pre-session and 84.75% in post-session provided positive feedback about the visualization of health data. By using this framework, community members can generate collective knowledge that might assist community stakeholders such as the Health Department to improve community health by identifying health issues, developing strategies, and resource allocation.

Comments

Data is provided by the student.

Library Comment

Dissertation or thesis originally submitted to the local University of Memphis Electronic Theses & dissertation (ETD) Repository.

Download

Share

COinS