EEG analysis on actual and imaginary left and right hand lifting using Support Vector Machine (SVM) / Nabilah Hamzah .. [et al.]

Hamzah, Nabilah and Zaini, Norliza and Sani, Maizura and Ismail, Nurlaila (2017) EEG analysis on actual and imaginary left and right hand lifting using Support Vector Machine (SVM) / Nabilah Hamzah .. [et al.]. Journal of Electrical & Electronic Systems Research (JEESR), 10. ISSN 1985-5389

Abstract

Brain Computer Interface or BCI is a technology that creates new communication channel where human brain (via Electroencephalography) can communicate with electronic devices.EEG signal is produced by the neurons, where every thought, emotion and movement can generate different patterns of EEG signal. There are two objectives defined for this research. The first objective is to compare the EEG data generated for actual and imaginary motor movement when lifting the left and right hand by using Support Vector Machine (SVM).The second objective is to find the correlation in EEG pattern between the actual motor movement and imaginary motor movement data, which is also based on SVM classification analysis. From the classification analysis, the accuracy for actual left and right-hand lifting movement is obtained at 90%. Meanwhile, the accuracy for classifying EEG data of imaginary left and right-hand lifting movement is obtained at 75%. In finding the correlation between the actual and imaginary EEG data, a classification analysis is also done by combining the actual and imaginary data. In this experiment, the accuracy in classifying the left and right-hand lifting activities is obtained at 78.8%. The significant accuracy measures obtained means that there is some correlation in EEG patterns between the actual motor movement and imaginary motor movement of lifting either left or right hand.

Metadata

Item Type: Article
Creators:
CreatorsID Num. / Email
Hamzah, NabilahUNSPECIFIED
Zaini, NorlizaUNSPECIFIED
Sani, MaizuraUNSPECIFIED
Ismail, NurlailaUNSPECIFIED
Subjects: T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electronics > Computer engineering. Computer hardware
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Electrical Engineering
Journal or Publication Title: Journal of Electrical & Electronic Systems Research (JEESR)
Journal: UiTM Journal > Journal of Electrical & Electronic Systems Research
ISSN: 1985-5389
Volume: 10
Item ID: 29587
Uncontrolled Keywords: EEG, Power Spectral Density, Support Vector Machine
URI: http://ir.uitm.edu.my/id/eprint/29587

Download

[img] Text
29587.pdf

Download (812kB)

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year