File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: ICA-SVM combination algorithm for identification of motor imagery potentials
  • 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 FieldValue
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
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Ming, D</contributor.author>
<contributor.author>Sun, C</contributor.author>
<contributor.author>Cheng, L</contributor.author>
<contributor.author>Bai, Y</contributor.author>
<contributor.author>Liu, X</contributor.author>
<contributor.author>An, X</contributor.author>
<contributor.author>Qi, H</contributor.author>
<contributor.author>Wan, B</contributor.author>
<contributor.author>Hu, Y</contributor.author>
<contributor.author>Luk, K</contributor.author>
<date.accessioned>2011-10-28T02:57:59Z</date.accessioned>
<date.available>2011-10-28T02:57:59Z</date.available>
<date.issued>2010</date.issued>
<identifier.citation>The 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</identifier.citation>
<identifier.isbn>978-1-4244-7230-7</identifier.isbn>
<identifier.uri>http://hdl.handle.net/10722/142879</identifier.uri>
<description.abstract>Mental 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. &#169; 2010 IEEE.</description.abstract>
<language>eng</language>
<publisher>IEEE.</publisher>
<relation.ispartof>CIMSA 2010 - IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Proceedings</relation.ispartof>
<rights>Creative Commons: Attribution 3.0 Hong Kong License</rights>
<rights>Proceedings of the IEEE International Conference on Computational Intelligence for Measurement Systems and Applications. Copyright &#169; IEEE.</rights>
<rights>&#169;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.</rights>
<subject>Brain-computer interface (BCI)</subject>
<subject>ERD/ERS coefficient</subject>
<subject>Event-related desynchronization/synchronous (ERD/ERS)</subject>
<subject>Independent component analysis (ICA)</subject>
<subject>Power spectral density (PSD)</subject>
<subject>Support vector machine (SVM)</subject>
<title>ICA-SVM combination algorithm for identification of motor imagery potentials</title>
<type>Conference_Paper</type>
<identifier.openurl>http://library.hku.hk:4550/resserv?sid=HKU:IR&amp;issn=978-1-4244-7230-7&amp;volume=&amp;spage=92&amp;epage=&amp;date=2010&amp;atitle=ICA-SVM+combination+algorithm+for+identification+of+motor+imagery+potentials</identifier.openurl>
<description.nature>published_or_final_version</description.nature>
<identifier.doi>10.1109/CIMSA.2010.5611755</identifier.doi>
<identifier.scopus>eid_2-s2.0-78649543244</identifier.scopus>
<identifier.hkuros>197089</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-78649543244&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.spage>92</identifier.spage>
<identifier.epage>96</identifier.epage>
<description.other>The 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</description.other>
<bitstream.url>http://hub.hku.hk/bitstream/10722/142879/1/Content.pdf</bitstream.url>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Tianjin University