Classification of motor imagery tasks for brain-computer interface using EEG signals

Lafiz Maruf, Zawad Alam, Md. Musta-E-Nur Rahman, Md Anisur Rahman, Mohammad Zavid Parvez, Peter Hough

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

The human brain is the most important and central organ of the body. The brain receives information from the environment through the sensory organs, processes, analyses and integrates the information and sends instructions to the rest of the organs. There is also communication between billions of neurons within the brain for emotion, thoughts and behaviour. Brain–computer interface (BCI) is a communication medium that translates neuronal activity into commands towards controlling of an external system. Electroencephalogram (EEG) records the electrical activity of the brain by evaluating voltage changes in regions of the skin by simply placing the electrodes on the skin.As there are many disabled people for whom this process may help by activating movement in their limbs. Thus, we decided to work on classifying the motor imagery tasks using EEG signals.This research presented the process of classifying three motor imagery tasks using EEG signals which can be further evolved into a BCI system that can remotely control external devices.Different bands are filtered from EEG signals in order to extract different frequency distributed features for seven subjects who participated in this experiment. Two sets of features are used to classify different motor imagery tasks based on Support Vector Machine (SVM), Artificial Neural Networks (ANN), Decision Tree, Logistic Regression and Naive Bayes. The experimental results show that SVM achieved higher accuracy compared to ANN. Decision Tree, Logistic Regression, and Naive Bayes classifiers. The accuracy of our proposed method is also shown to be better than two other existing Motor Imagery classification techniques.
Original languageEnglish
Title of host publication 2020 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)
PublisherIEEE Xplore
DOIs
Publication statusPublished - 28 Apr 2021
Event7th IEEE Asia-Pacific Conference on Computer Science and Data Engineering 2020: IEEE CSDE 2020 - Virtual conference
Duration: 16 Dec 202018 Dec 2020
https://ieee-csde.org/
https://ieee-csde.org/assets/images/7th%20IEEE%20CSDE%20CFP.pdf (call for papers)
https://web.archive.org/web/20210104201909/https://ieee-csde.org/assets/images/IEEE%20CSDE%20iCOSTE%202020%20Final%20Program.pdf (program)

Conference

Conference7th IEEE Asia-Pacific Conference on Computer Science and Data Engineering 2020
Period16/12/2018/12/20
OtherThis year The 7th IEEE CSDE 2020, the Asia-Pacific Conference on Computer Science and Data Engineering 2020 is being held virtually in the tourist center of Australia, Gold Coast. Australia’s Gold Coast is a leading tourism, business, and events city boasting arguably one of the best lifestyles in the world. Situated in the southeast corner of the state of Queensland, the Gold Coast stretches along 57 kilometers of coastline and is home to over half a million people. The Conference is hosted and sponsored by the IEEE, IEEE Computer Society, The University of the South Pacific, Fiji; Victoria University, Australia; CQUniversity, Australia; Massy University, New Zealand and NPS Australia.
Internet address

Fingerprint Dive into the research topics of 'Classification of motor imagery tasks for brain-computer interface using EEG signals'. Together they form a unique fingerprint.

Cite this