Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets

Numerous investigations have been conducted to enhance the motor imagery-based brain–computer interface (BCI) classification performance on various aspects. However, there are limited studies comparing their proposed feature selection framework performance on both objective and subjective datasets....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Minh Tran Duc Nguyen, Nhi Yen Phan Xuan, Bao Minh Pham, Trung-Hau Nguyen, Quang-Linh Huynh, Quoc Khai Le
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	brain–computer interface motor imagery discriminative filter banks common spatial pattern fisher mutual information Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/f2d154038dec4130adfe7d205f77312b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f2d154038dec4130adfe7d205f77312b
record_format	dspace
spelling	oai:doaj.org-article:f2d154038dec4130adfe7d205f77312b2021-11-11T15:23:56ZEvaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets10.3390/app1121103882076-3417https://doaj.org/article/f2d154038dec4130adfe7d205f77312b2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10388https://doaj.org/toc/2076-3417Numerous investigations have been conducted to enhance the motor imagery-based brain–computer interface (BCI) classification performance on various aspects. However, there are limited studies comparing their proposed feature selection framework performance on both objective and subjective datasets. Therefore, this study aims to provide a novel framework that combines spatial filters at various frequency bands with double-layered feature selection and evaluates it on published and self-acquired datasets. Electroencephalography (EEG) data are preprocessed and decomposed into multiple frequency sub-bands, whose features are then extracted, calculated, and ranked based on Fisher’s ratio and minimum-redundancy-maximum-relevance (mRmR) algorithm. Informative filter banks are chosen for optimal classification by linear discriminative analysis (LDA). The results of the study, firstly, show that the proposed method is comparable to other conventional methods through accuracy and F1-score. The study also found that hand vs. feet classification is more discriminable than left vs. right hand (4–10% difference). Lastly, the performance of the filter banks common spatial pattern (FBCSP, without feature selection) algorithm is found to be significantly lower (<i>p</i> = 0.0029, <i>p</i> = 0.0015, and <i>p</i> = 0.0008) compared to that of the proposed method when applied to small-sized data.Minh Tran Duc NguyenNhi Yen Phan XuanBao Minh PhamTrung-Hau NguyenQuang-Linh HuynhQuoc Khai LeMDPI AGarticlebrain–computer interfacemotor imagerydiscriminative filter bankscommon spatial patternfishermutual informationTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10388, p 10388 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	brain–computer interface motor imagery discriminative filter banks common spatial pattern fisher mutual information Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	brain–computer interface motor imagery discriminative filter banks common spatial pattern fisher mutual information Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Trung-Hau Nguyen Quang-Linh Huynh Quoc Khai Le Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
description	Numerous investigations have been conducted to enhance the motor imagery-based brain–computer interface (BCI) classification performance on various aspects. However, there are limited studies comparing their proposed feature selection framework performance on both objective and subjective datasets. Therefore, this study aims to provide a novel framework that combines spatial filters at various frequency bands with double-layered feature selection and evaluates it on published and self-acquired datasets. Electroencephalography (EEG) data are preprocessed and decomposed into multiple frequency sub-bands, whose features are then extracted, calculated, and ranked based on Fisher’s ratio and minimum-redundancy-maximum-relevance (mRmR) algorithm. Informative filter banks are chosen for optimal classification by linear discriminative analysis (LDA). The results of the study, firstly, show that the proposed method is comparable to other conventional methods through accuracy and F1-score. The study also found that hand vs. feet classification is more discriminable than left vs. right hand (4–10% difference). Lastly, the performance of the filter banks common spatial pattern (FBCSP, without feature selection) algorithm is found to be significantly lower (<i>p</i> = 0.0029, <i>p</i> = 0.0015, and <i>p</i> = 0.0008) compared to that of the proposed method when applied to small-sized data.
format	article
author	Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Trung-Hau Nguyen Quang-Linh Huynh Quoc Khai Le
author_facet	Minh Tran Duc Nguyen Nhi Yen Phan Xuan Bao Minh Pham Trung-Hau Nguyen Quang-Linh Huynh Quoc Khai Le
author_sort	Minh Tran Duc Nguyen
title	Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
title_short	Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
title_full	Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
title_fullStr	Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
title_full_unstemmed	Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets
title_sort	evaluating the motor imagery classification performance of a double-layered feature selection on two different-sized datasets
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f2d154038dec4130adfe7d205f77312b
work_keys_str_mv	AT minhtranducnguyen evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets AT nhiyenphanxuan evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets AT baominhpham evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets AT trunghaunguyen evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets AT quanglinhhuynh evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets AT quockhaile evaluatingthemotorimageryclassificationperformanceofadoublelayeredfeatureselectionontwodifferentsizeddatasets
_version_	1718435404981469184

Evaluating the Motor Imagery Classification Performance of a Double-Layered Feature Selection on Two Different-Sized Datasets

Ejemplares similares