Conference Paper: ICA-SVM combination algorithm for identification of motor imagery potentials

File Download Links for fulltext
(May Require Subscription)
Supplementary
  • Basic View
  • Metadata View
  • XML View
TitleICA-SVM combination algorithm for identification of motor imagery potentials
AuthorsMing, D2
Sun, C2
Cheng, L2
Bai, Y2
Liu, X2
An, X2
Qi, H2
Wan, B2
Hu, Y1
Luk, K1
KeywordsBrain-computer interface (BCI)
ERD/ERS coefficient
Event-related desynchronization/synchronous (ERD/ERS)
Independent component analysis (ICA)
Power spectral density (PSD)
Support vector machine (SVM)
Issue Date2010
PublisherIEEE.
CitationThe 2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA), Taranto, Apulia, Italy, 6-8 September 2010. In Proceedings of IEEE-CIMSA, 2010, p. 92-96 [How to Cite?]
DOI: http://dx.doi.org/10.1109/CIMSA.2010.5611755
AbstractMental tasks such as motor imagery in synchronization with a cue which result event related desynchronization (ERD) and event related synchronization (ERS) are usually studied in brain-computer interface (BCI) system. In this paper we analyze and classify the ERD/ERS response evoked by the motor imagery of left hand, right hand, foot and tongue. The signals were spatially filtered by Independent Component Analysis (ICA) before calculating the power spectral density (PSD) for related electrodes, and then the Support Vector Machine (SVM) was adopted to recognise the different imagery pattern according to ERD/ERS feature for the signals. The results showed that the combination of ICA-based signal extraction algorithm and SVM-based classification method was an effective tool for the identification of motor imagery potentials, with the highest accuracy rate of 91.4% and 77.6% for the lowest. © 2010 IEEE.
ISBN978-1-4244-7230-7
DOIhttp://dx.doi.org/10.1109/CIMSA.2010.5611755
ReferencesReferences in Scopus
DC Field
Value
dc.contributor.authorMing, D
dc.contributor.authorSun, C
dc.contributor.authorCheng, L
dc.contributor.authorBai, Y
dc.contributor.authorLiu, X
dc.contributor.authorAn, X
dc.contributor.authorQi, H
dc.contributor.authorWan, B
dc.contributor.authorHu, Y
dc.contributor.authorLuk, K
dc.date.accessioned2011-10-28T02:57:59Z
dc.date.available2011-10-28T02:57:59Z
dc.date.issued2010
dc.description.abstractMental tasks such as motor imagery in synchronization with a cue which result event related desynchronization (ERD) and event related synchronization (ERS) are usually studied in brain-computer interface (BCI) system. In this paper we analyze and classify the ERD/ERS response evoked by the motor imagery of left hand, right hand, foot and tongue. The signals were spatially filtered by Independent Component Analysis (ICA) before calculating the power spectral density (PSD) for related electrodes, and then the Support Vector Machine (SVM) was adopted to recognise the different imagery pattern according to ERD/ERS feature for the signals. The results showed that the combination of ICA-based signal extraction algorithm and SVM-based classification method was an effective tool for the identification of motor imagery potentials, with the highest accuracy rate of 91.4% and 77.6% for the lowest. © 2010 IEEE.
dc.description.naturepublished_or_final_version
dc.description.otherThe 2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA), Taranto, Apulia, Italy, 6-8 September 2010. In Proceedings of IEEE-CIMSA, 2010, p. 92-96
dc.identifier.citationThe 2010 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA), Taranto, Apulia, Italy, 6-8 September 2010. In Proceedings of IEEE-CIMSA, 2010, p. 92-96 [How to Cite?]
DOI: http://dx.doi.org/10.1109/CIMSA.2010.5611755
dc.identifier.doihttp://dx.doi.org/10.1109/CIMSA.2010.5611755
dc.identifier.epage96
dc.identifier.hkuros197089
dc.identifier.isbn978-1-4244-7230-7
dc.identifier.openurl
dc.identifier.scopuseid_2-s2.0-78649543244
dc.identifier.spage92
dc.identifier.urihttp://hdl.handle.net/10722/142879
dc.languageeng
dc.publisherIEEE.
dc.relation.ispartofCIMSA 2010 - IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Proceedings
dc.relation.referencesReferences in Scopus
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License
dc.rightsProceedings of the IEEE International Conference on Computational Intelligence for Measurement Systems and Applications. Copyright © IEEE.
dc.rights©2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
dc.subjectBrain-computer interface (BCI)
dc.subjectERD/ERS coefficient
dc.subjectEvent-related desynchronization/synchronous (ERD/ERS)
dc.subjectIndependent component analysis (ICA)
dc.subjectPower spectral density (PSD)
dc.subjectSupport vector machine (SVM)
dc.titleICA-SVM combination algorithm for identification of motor imagery potentials
dc.typeConference_Paper
Author Affiliations
  1. The University of Hong Kong
  2. Tianjin University