EEG signal classification for wheelchair control application

Abu Hassan, Rozi Roslinda (2015) EEG signal classification for wheelchair control application. Masters thesis, Universiti Tun Hussein Onn Malaysia.

[img] Text (Copyright Declaration)
ROZI ROSLINDA ABU HASSAN COPYRIGHT DECLARATION.pdf
Restricted to Repository staff only
Download (312kB) | Request a copy
[img]
Preview
 Text (24 pages)
24p ROZI ROSLINDA ABU HASSAN.pdf
Download (2MB) | Preview
[img] Text (Full Text)
ROZI ROSLINDA ABU HASSAN WATERMARK.pdf
Restricted to Registered users only
Download (5MB) | Request a copy

Abstract

Brain–Computer Interface (BCI) requires generating control signals for external device by analyzing and processing the internal brain signal. Person with severe impairment or spinal cord injury has loss of ability to do anything. This project about the EEG signals classification for wheelchair control application. In this project, the movement of wheelchair (left, right, forward and reverse) will classified by user focusing based on four visible picture in various shape and colour also four non-visible picture (used thought image) that represent the movement. EEG signal were analyzed to find out the features by using Fast Fourier Transform (FFT). This project used alpha and beta band to collect the data. The analysis have made based on the peak and average value which then be compared to define the most significant differentiation between signals. From the result, shows that the visible colour model meet the most significant value based on the higher percentage than the other two models.

Item Type: Thesis (Masters)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering
Depositing User: Mrs. Nur Nadia Md. Jurimi
Date Deposited: 03 Oct 2021 07:24
Last Modified: 03 Oct 2021 07:24
URI: http://eprints.uthm.edu.my/id/eprint/1448

Actions (login required)

View Item View Item