Feature extraction and classification of EEG signal for different brain control machine

Sheikh Md Rabiul Islam, Ahosanullah Sajol, Xu Huang, Keng Liang Ou

研究成果: 書貢獻/報告類型會議貢獻

3 引文 (Scopus)

摘要

Brain computer interface is used for human and machine learning analysis. This paper represents the EEG datasets that are built with different cognitive task such as left, right, back and front imaginary movement with eye open. We have used different feature extraction method to classify these EEG signal using Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Artificial Neural Network (ANN). All these methods are compared with other work that have done with other datasets. The proposed work is obtained 95.21% accuracy 98.95% sensitivity for SVM and k-NN is 90.88% and ANN is 94.31%. The performance results have shown higher enough than all others.
原文英語
主出版物標題2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781509029068
DOIs
出版狀態已發佈 - 三月 6 2017
事件3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016 - Dhaka, 孟加拉国
持續時間: 九月 22 2016九月 24 2016

其他

其他3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016
國家孟加拉国
城市Dhaka
期間9/22/169/24/16

指紋

Electroencephalography
Support vector machines
Feature extraction
Brain
Neural networks
Brain computer interface
Learning systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Human-Computer Interaction
  • Signal Processing
  • Electrical and Electronic Engineering

引用此文

Islam, S. M. R., Sajol, A., Huang, X., & Ou, K. L. (2017). Feature extraction and classification of EEG signal for different brain control machine. 於 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016 [7873150] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEEICT.2016.7873150

Feature extraction and classification of EEG signal for different brain control machine. / Islam, Sheikh Md Rabiul; Sajol, Ahosanullah; Huang, Xu; Ou, Keng Liang.

2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7873150.

研究成果: 書貢獻/報告類型會議貢獻

Islam, SMR, Sajol, A, Huang, X & Ou, KL 2017, Feature extraction and classification of EEG signal for different brain control machine. 於 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016., 7873150, Institute of Electrical and Electronics Engineers Inc., 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016, Dhaka, 孟加拉国, 9/22/16. https://doi.org/10.1109/CEEICT.2016.7873150
Islam SMR, Sajol A, Huang X, Ou KL. Feature extraction and classification of EEG signal for different brain control machine. 於 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7873150 https://doi.org/10.1109/CEEICT.2016.7873150
Islam, Sheikh Md Rabiul ; Sajol, Ahosanullah ; Huang, Xu ; Ou, Keng Liang. / Feature extraction and classification of EEG signal for different brain control machine. 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{0fdf64367afc49229ef9b039b2fc0ee2,
title = "Feature extraction and classification of EEG signal for different brain control machine",
abstract = "Brain computer interface is used for human and machine learning analysis. This paper represents the EEG datasets that are built with different cognitive task such as left, right, back and front imaginary movement with eye open. We have used different feature extraction method to classify these EEG signal using Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Artificial Neural Network (ANN). All these methods are compared with other work that have done with other datasets. The proposed work is obtained 95.21{\%} accuracy 98.95{\%} sensitivity for SVM and k-NN is 90.88{\%} and ANN is 94.31{\%}. The performance results have shown higher enough than all others.",
keywords = "Acuraccy, ANN, EEG datasets, k-NN, SVM",
author = "Islam, {Sheikh Md Rabiul} and Ahosanullah Sajol and Xu Huang and Ou, {Keng Liang}",
year = "2017",
month = "3",
day = "6",
doi = "10.1109/CEEICT.2016.7873150",
language = "English",
booktitle = "2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Feature extraction and classification of EEG signal for different brain control machine

AU - Islam, Sheikh Md Rabiul

AU - Sajol, Ahosanullah

AU - Huang, Xu

AU - Ou, Keng Liang

PY - 2017/3/6

Y1 - 2017/3/6

N2 - Brain computer interface is used for human and machine learning analysis. This paper represents the EEG datasets that are built with different cognitive task such as left, right, back and front imaginary movement with eye open. We have used different feature extraction method to classify these EEG signal using Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Artificial Neural Network (ANN). All these methods are compared with other work that have done with other datasets. The proposed work is obtained 95.21% accuracy 98.95% sensitivity for SVM and k-NN is 90.88% and ANN is 94.31%. The performance results have shown higher enough than all others.

AB - Brain computer interface is used for human and machine learning analysis. This paper represents the EEG datasets that are built with different cognitive task such as left, right, back and front imaginary movement with eye open. We have used different feature extraction method to classify these EEG signal using Support Vector Machine (SVM), k-Nearest Neighbor (k-NN) and Artificial Neural Network (ANN). All these methods are compared with other work that have done with other datasets. The proposed work is obtained 95.21% accuracy 98.95% sensitivity for SVM and k-NN is 90.88% and ANN is 94.31%. The performance results have shown higher enough than all others.

KW - Acuraccy

KW - ANN

KW - EEG datasets

KW - k-NN

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85016957777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016957777&partnerID=8YFLogxK

U2 - 10.1109/CEEICT.2016.7873150

DO - 10.1109/CEEICT.2016.7873150

M3 - Conference contribution

AN - SCOPUS:85016957777

BT - 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -