Mobile Sensor Data Measurements and Analysis for Fall Detection in Elderly Health Care
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2017-12-11
Department
Major/Subject
Signal Processing
Mcode
ELEC3031
Degree programme
CCIS - Master’s Programme in Computer, Communication and Information Sciences (TS2013)
Language
en
Pages
54 + 8
Series
Abstract
In recent years, increased life expectancy in Finland and other parts of the world have led to an aging population. Accidental falls can cause severe injuries to elderly people, thereby, negatively impacting their quality of life and in some cases resulting in death. Accidental falls is a major public health care challenge. Real time monitoring of human activity can provide insight into an individual’s functional ability and gives an indication of their ability to live independently. Automatic detection of falls enables us to provide timely medical attention, thereby, reducing the negative consequences of falls. This paradigm of home based health promotes independent living and reduces the burden on caregivers. The aim of the thesis is to log real world sensory data from multiple sensors on board mobile devices and develop suitable algorithms to extract information from the data to solve the problem of detecting when elderly people fall down. In order to log the data, an Android application is developed that collects data from the various onboard sensors and stores it in a text file. The developed application is used to take measurements of sensor data pertaining to various human activities. Then patterns in the data are then analysed and exploited to distinguish between normal day-to-day activities and people falling down. To detect falls, we develop two algorithms based on statistical detection theory and convex optimization, respectively and also analyze the efficacy of these methods.Description
Supervisor
Skyttä, JormaThesis advisor
Haneda, KatsuyukiKeywords
elderly health care, fall detection, mobile sensors, android application development, convex optimization, machine learning