Committee Chair

Sartipi, Mina

Committee Member

Liang, Yu; Wu, Dalei

Department

Dept. of Computer Science and Engineering

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

Stokes are the leading cause of disability in adults in the United States. Falls are preve- lant at all stages of recovery among post-stroke patients, and falls can cause serious or life threatening injuries. In this thesis, multiple fall detections methods are explored in order to minimize the faller’s wait time. This research is an extension to our research on mStroke, a reall-time and automatic mobile health system for post stroke recovery and rehabilitation. The proposed system consists of an application (mobile app) that is paired with bluetooth low energy (BLE) modular sensor devices. The sensors provide real-time accerlation, and gyroscopic data to the mobile application. This data is used to classify fall and non-fall activites performed by the user. The focus of mStroke has been on front-end development of application features. To address back-end long-term storage, a data storage solution for mStroke is investigated.

Acknowledgments

First and foremost, I want to first thank all of family who have shown me support throughout my time as a graduate student. I want to acknowledge my committee members, Dr. Yu Liang and Dr. Dalei Wu. Finally, I want to express my appreciation to my advisor and mentor, Dr. Mina Sartipi. Her guidence over the past years has been invalueable.

Degree

M. S.; A thesis submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Master of Science.

Date

12-2017

Subject

Biomedical engineering; Brain-computer interfaces

Keyword

Fall detection; Machine learning; Threshold based

Document Type

Masters theses

Extent

viii, 38 leaves

Language

English

Rights

Under copyright.

License

http://creativecommons.org/licenses/by-nc-nd/3.0/

Share

COinS