University of Twente Student Theses


Determining the rate of small gestures unobtrusively

Reefman, K.H.A. (2021) Determining the rate of small gestures unobtrusively.

[img] PDF
Abstract:The number of elderly people with Alzheimer’s disease is projected to double in the next three decades, thus increasing the pressure on the available care system. The quality of healthcare could greatly be improved by using unobtrusive sensing to detect anomalies in regular behaviours, such as an agitated mood in elderly people. If a caregiver knows in advance that someone is agitated, the person could be approached in a different way. One of the more interesting unobtrusive sensing solutions is with the use of Channel State Information (CSI). This paper uses CSI data in order to first identify deviant behaviour and then estimate the rate at which a movement, in this case sitting and standing up, is performed. This paper will discuss signal denoising techniques as well as several machine learning techniques which are used to classify human movement and calculate the rate at which they occur. This paper finds that the best way to determine the rate of human movements is by first using a Savitzky-Golay filter, then feeding the data into a Support Vector Machine and finally count the number of peaks in the prediction graph to get the rate.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:44 medicine, 54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page