Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis

Nagai, Kotaro; Kanemoto, Daisuke; Ohki, Makoto

doi:https://doi.org/10.1587/transfun.2020EAL2123

Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis

Nagai, Kotaro; Kanemoto, Daisuke; Ohki, Makoto

IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2021, E104A(9), 1375-1378

Number of Access:264（2025-08-15 06:45 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/97770

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
IEICETransFundElecComSci_E104A_9_1375	pdf	None	408 KB	44	2024.08.29

Item Information

Output File Export EndNote Basic Export Mendeley

Title	Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis
Creator	CreatorName Nagai, Kotaro
	NRID 1000090603332 1000090603332 researchmap permalink dkanemoto dkanemoto Scopus Author ID 6504308983 6504308983 ORCID 0009-0002-7564-6351 0009-0002-7564-6351 CreatorName Kanemoto, Daisuke
	NRID 1000050211785 1000050211785 CreatorName Ohki, Makoto
Subject	Compressed sensing
	EEG
	Independent component analysis
	K-SVD dictionary learning
	Outlier detection
Description	Nagai K., Kanemoto D., Ohki M.. Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E104A, 1375 (2021); https://doi.org/10.1587/transfun.2020EAL2123.
Abstract	This letter reports on the effectiveness of applying the K-singular value decomposition (SVD) dictionary learning to the electroencephalogram (EEG) compressed sensing framework with outlier detection and independent component analysis. Using the K-SVD dictionary matrix with our design parameter optimization, for example, at compression ratio of four, we improved the normalized mean square error value by 31.4% compared with that of the discrete cosine transform dictionary for CHB-MIT Scalp EEG Database.
Publisher	電子情報通信学会
Publisher	Institute of Electronics Information Communication Engineers
Source Title	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume (Issue)	E104A(9)
Page	1375-1378
Date of Issued	2021-09-01
Language	English
Handle URL	https://hdl.handle.net/11094/97770
PISSN	09168508
eISSN	17451337
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1587/transfun.2020EAL2123
Access Rights	open access
CopyRight	Copyright © 2021 The Institute of Electronics, Information and Communication Engineers
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. 2021, E104A(9), p. 1375-1378
DC.title	Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis
DC.creator	Nagai, Kotaro
	Kanemoto, Daisuke
	Ohki, Makoto
DC.publisher	電子情報通信学会
DC.publisher	Institute of Electronics Information Communication Engineers
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2021-09-01
DC.identifier	https://doi.org/10.1587/transfun.2020EAL2123
DC.subject	Compressed sensing
	EEG
	Independent component analysis
	K-SVD dictionary learning
	Outlier detection
DC.description	Nagai K., Kanemoto D., Ohki M.. Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E104A, 1375 (2021); https://doi.org/10.1587/transfun.2020EAL2123.
DCTERMS.abstract	This letter reports on the effectiveness of applying the K-singular value decomposition (SVD) dictionary learning to the electroencephalogram (EEG) compressed sensing framework with outlier detection and independent component analysis. Using the K-SVD dictionary matrix with our design parameter optimization, for example, at compression ratio of four, we improved the normalized mean square error value by 31.4% compared with that of the discrete cosine transform dictionary for CHB-MIT Scalp EEG Database.
DC.rights	Copyright © 2021 The Institute of Electronics, Information and Communication Engineers
DC.format	97770
citation_title	Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis
citation_author	Nagai, Kotaro
	Kanemoto, Daisuke
	Ohki, Makoto
citation_publisher	電子情報通信学会
citation_language	English
citation_date	2021-09-01
citation_journal_title	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
citation_volume	E104A
citation_issue	9
citation_firstpage	1375
citation_lastpage	1378
citation_doi	https://doi.org/10.1587/transfun.2020EAL2123
citation_public_url	https://hdl.handle.net/11094/97770

Applying K-SVD dictionary learning for EEG compressed sensing framework with outlier detection and independent component analysis

Link to primary information

Item Information

Show details