The classification of EEG signal processing using different machine learning techniques for BCI application

Rashid, Mamunur and Norizam, Sulaiman and Mahfuzah, Mustafa and Sabira, Khatun and Bari, Bifta Sama (2019) The classification of EEG signal processing using different machine learning techniques for BCI application. In: RiTA 2018: Robot Intelligence Technology and Applications , 16-18 December 2018 , Putrajaya, Selangor, Malaysia. pp. 207-221.. ISBN 978-981-13-7779-2

	Pdf 29. The classification of EEG signal processing using different.pdf Restricted to Repository staff only Download (967kB) | Request a copy
Preview	Pdf 29.1 The classification of EEG signal processing using different.pdf Download (87kB) | Preview

Abstract

Brain-Computer Interface (BCI) or Human-Machine Interface is now becoming vital in biomedical engineering and technology field which applying EEG technologies to provide assistive device technology (AT) to humans. Hence, this paper presents the results of analyzing EEG signals from various human cognitive states to extract the suitable EEG features that can be em-ployed to control BCI devices which can be used by disabled or paralyzed people. The EEG features in term of power spectral density, spectral centroids, standard deviation and entropy are selected and investigated from two different mental exercises; i) quick solving math and ii) relax (do nothing). Then the se-lected features are classified using Linear Discriminant Analysis (LDA), Sup-port Vector Machine (SVM) and K-Nearest Neighbors (k-NN) classifier. Among all these features, the best accuracy has been achieved by the power spectral density. The accuracies of this feature are 95%, 100%, 100% with LDA, SVM and K-NN respectively. Finally, the translation algorithm will be con-structed using selected and classified EEG features to control the BCI devices.

Item Type:	Conference or Workshop Item (Lecture)
Uncontrolled Keywords:	EEG signal; Machine learning; BCI application
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division:	Faculty of Electrical & Electronic Engineering
Depositing User:	Pn. Hazlinda Abd Rahman
Date Deposited:	08 Oct 2019 08:02
Last Modified:	20 Jan 2020 02:25
URI:	http://umpir.ump.edu.my/id/eprint/24498
Download Statistic:	View Download Statistics

Actions (login required)

View Item