Research on extraction and classification of EEG features for multi-class motor imagery

Aiming at solving the problems of low recognition accuracy and poor practicability caused by the small amount of data and insufficient training of the network weights when the deep neural network algorithm is directly used to classify the 4-class motor-imagery electroencephalogram signals(MI-EEG), W...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) Ročník 1; s. 693 - 697
Hlavní autori: Tang, Xuebin, Zhao, Jinchuang, Fu, Wenli
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.12.2019
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Aiming at solving the problems of low recognition accuracy and poor practicability caused by the small amount of data and insufficient training of the network weights when the deep neural network algorithm is directly used to classify the 4-class motor-imagery electroencephalogram signals(MI-EEG), We combine the one-versus-the-rest common spatial pattern (OVR-CSP) algorithm and a novel convolution neural networks (CNN) algorithm to extract features and classify 4-class MI-EEG signals. Firstly, the original EEG signal data is truncated and expanded by using a fixed-size overlapping window, the features of intercepted sub-signals are extracted by CSP algorithm and the obtained feature vectors are merged as the input sample matrix of CNN. Secondly, CNN algorithm performs second feature extraction and final classification on the input sample matrix. Finally, the validity of the proposed algorithm was verified by the datasets IIIa of the BCI2005 competition. The average recognition accuracy of the three subjects has reached 91.9%, this is an improvement over other algorithms in recent years.
AbstractList Aiming at solving the problems of low recognition accuracy and poor practicability caused by the small amount of data and insufficient training of the network weights when the deep neural network algorithm is directly used to classify the 4-class motor-imagery electroencephalogram signals(MI-EEG), We combine the one-versus-the-rest common spatial pattern (OVR-CSP) algorithm and a novel convolution neural networks (CNN) algorithm to extract features and classify 4-class MI-EEG signals. Firstly, the original EEG signal data is truncated and expanded by using a fixed-size overlapping window, the features of intercepted sub-signals are extracted by CSP algorithm and the obtained feature vectors are merged as the input sample matrix of CNN. Secondly, CNN algorithm performs second feature extraction and final classification on the input sample matrix. Finally, the validity of the proposed algorithm was verified by the datasets IIIa of the BCI2005 competition. The average recognition accuracy of the three subjects has reached 91.9%, this is an improvement over other algorithms in recent years.
Author Fu, Wenli
Zhao, Jinchuang
Tang, Xuebin
Author_xml – sequence: 1
  givenname: Xuebin
  surname: Tang
  fullname: Tang, Xuebin
  organization: Guangxi University,School of Computer, Electrics and Information
– sequence: 2
  givenname: Jinchuang
  surname: Zhao
  fullname: Zhao, Jinchuang
  organization: Guangxi University,School of Computer, Electrics and Information
– sequence: 3
  givenname: Wenli
  surname: Fu
  fullname: Fu, Wenli
  organization: Guangxi University,School of Computer, Electrics and Information
BookMark eNotj91KxDAUhCPoha77BF6YF2jNSdomuSylrgsLgiheLqfNiQb6I2kW3Ld3Wfdqho9hhrlj19M8EWOPIHIAYZ-2dVs3hVZa5lKAzY21RhT2iq2tNqClAbCisrfs840Wwth_83ni9Jsi9imcLE6O9wMuS_ChxzOaPW_bDfeE6RBp4X6OfDwMKWTnIB_ndCJhxC-Kx3t243FYaH3RFft4bt-bl2z3utk29S4LACZlaLqqUGQkadmVtnSiME57oVxJFhyQM4AgXWV6JZX3gBV1siNE22lpe7ViD_-9gYj2P_E0H4_7y131B2DRURk
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IAEAC47372.2019.8998049
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728119069
1728119073
1728119065
9781728119076
EndPage 697
ExternalDocumentID 8998049
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i118t-a8b643e82e72b595d048d7f03d5e91d1ed81a12d68c323ff1a6eb2beaa9b729c3
IEDL.DBID RIE
IngestDate Thu Jun 29 18:38:50 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-a8b643e82e72b595d048d7f03d5e91d1ed81a12d68c323ff1a6eb2beaa9b729c3
PageCount 5
ParticipantIDs ieee_primary_8998049
PublicationCentury 2000
PublicationDate 2019-Dec.
PublicationDateYYYYMMDD 2019-12-01
PublicationDate_xml – month: 12
  year: 2019
  text: 2019-Dec.
PublicationDecade 2010
PublicationTitle 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
PublicationTitleAbbrev IAEAC
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.713734
Snippet Aiming at solving the problems of low recognition accuracy and poor practicability caused by the small amount of data and insufficient training of the network...
SourceID ieee
SourceType Publisher
StartPage 693
SubjectTerms Brain modeling
brain-computer interface systems (BCI)
Classification algorithms
common spatial pattern (CSP)
Convolution
convolutional neural network (CNN)
Covariance matrices
Electroencephalography
Feature extraction
motor imagery EEG signals (MI-EEG)
Training
Title Research on extraction and classification of EEG features for multi-class motor imagery
URI https://ieeexplore.ieee.org/document/8998049
Volume 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8eBJpRXf5ODRtbub7iY5lrJVQUoPir2VbGYCPbgrfQj9906ytSJ48RaGQMhMHt8k38wwdotgtJNWRxoyRQ6Kg0inykSQxzJ1NocYQnb9ZzmZqNlMT1vsbh8Lg4iBfIb3vhn-8qG2G_9U1ve-ASHaNmtLKZtYrR1lK4l1_2lYDEcDX3bFM7ZoCTS9f5VNCbfG-Oh_4x2z3k_4HZ_uL5YT1sKqy96-OXK8rjidqMsmIoGbCrj1ENhzfoKaee14UTxwhyFp54oTLuWBOBiFjpysQ5LFu09fse2x13HxMnqMdlURogU5A-vIqJJQBKoUZVpmOgPagyBdLCBDnUCCoBKTpJArK1LhXGJy8p5LNEaXhKStOGWdqq7wjHGk2ZUkj5WTgzIVOgZMYiGQjKdtZs9Z1ytl_tEkvpjv9HHxt_iSHXq9N1yPK9ZZLzd4zQ7s53qxWt4Ea30BTcmZvQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61CnpSacW3OXh07Sb7So6lrLZYSw8VeyvZzAR6cFf6EPz3JtlaEbx4C0MgZCaPb5JvZgi5RVDSZFoGEhJhHRQDgeRCBZCGGTc6hRB8dv1hNhqJ6VSOG-RuGwuDiJ58hveu6f_yodJr91TWcb6BRbQ7ZDeJY87qaK0NaYuFsjPo5t1e7AqvOM6WXQR1_1-FU_y98XD4vxGPSPsnAI-Ot1fLMWlg2SKv3yw5WpXUnqmLOiaBqhKodiDYsX68omllaJ4_UoM-beeSWmRKPXUw8B2ptY-VzN9cAovPNnl5yCe9frCpixDMrTuwCpQoLI5AwTHjRSITsLsQMhNGkKBkwBAEU4xDKnTEI2OYSq3_XKBSsrBYWkcnpFlWJZ4SinZ2hZWHwmRxwSMZArIwitCaT-pEn5GWU8rsvU59Mdvo4_xv8Q3Z70-eh7PhYPR0QQ6cDWrmxyVprhZrvCJ7-mM1Xy6uveW-AHqBnQQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+IEEE+4th+Advanced+Information+Technology%2C+Electronic+and+Automation+Control+Conference+%28IAEAC%29&rft.atitle=Research+on+extraction+and+classification+of+EEG+features+for+multi-class+motor+imagery&rft.au=Tang%2C+Xuebin&rft.au=Zhao%2C+Jinchuang&rft.au=Fu%2C+Wenli&rft.date=2019-12-01&rft.pub=IEEE&rft.volume=1&rft.spage=693&rft.epage=697&rft_id=info:doi/10.1109%2FIAEAC47372.2019.8998049&rft.externalDocID=8998049