Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface
Common spatial pattern (CSP) is a method commonly used to enhance the effects of event-related desynchronization and event-related synchronization present in multichannel electroencephalogram-based brain-computer interface (BCI) systems. In the present study, a novel CSP sub-band feature selection h...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wolters Kluwer Medknow Publications
2015-01-01
|
Series: | Journal of Medical Signals and Sensors |
Subjects: | |
Online Access: | http://www.jmss.mui.ac.ir/article.asp?issn=2228-7477;year=2015;volume=5;issue=3;spage=156;epage=161;aulast=Jamaloo |
id |
doaj-89b461b11c9f4bbea4b6e51dcd2f554c |
---|---|
record_format |
Article |
spelling |
doaj-89b461b11c9f4bbea4b6e51dcd2f554c2020-11-25T01:39:48ZengWolters Kluwer Medknow PublicationsJournal of Medical Signals and Sensors2228-74772015-01-015315616110.4103/2228-7477.161482Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interfaceFatemeh JamalooMohammad MikaeiliCommon spatial pattern (CSP) is a method commonly used to enhance the effects of event-related desynchronization and event-related synchronization present in multichannel electroencephalogram-based brain-computer interface (BCI) systems. In the present study, a novel CSP sub-band feature selection has been proposed based on the discriminative information of the features. Besides, a distinction sensitive learning vector quantization based weighting of the selected features has been considered. Finally, after the classification of the weighted features using a support vector machine classifier, the performance of the suggested method has been compared with the existing methods based on frequency band selection, on the same BCI competitions datasets. The results show that the proposed method yields superior results on "ay" subject dataset compared against existing approaches such as sub-band CSP, filter bank CSP (FBCSP), discriminative FBCSP, and sliding window discriminative CSP.http://www.jmss.mui.ac.ir/article.asp?issn=2228-7477;year=2015;volume=5;issue=3;spage=156;epage=161;aulast=JamalooBrain-computer interfacecommon spatial patterndistinction sensitive learning vector quantization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fatemeh Jamaloo Mohammad Mikaeili |
spellingShingle |
Fatemeh Jamaloo Mohammad Mikaeili Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface Journal of Medical Signals and Sensors Brain-computer interface common spatial pattern distinction sensitive learning vector quantization |
author_facet |
Fatemeh Jamaloo Mohammad Mikaeili |
author_sort |
Fatemeh Jamaloo |
title |
Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
title_short |
Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
title_full |
Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
title_fullStr |
Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
title_full_unstemmed |
Discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
title_sort |
discriminative common spatial pattern sub-bands weighting based on distinction sensitive learning vector quantization method in motor imagery based brain-computer interface |
publisher |
Wolters Kluwer Medknow Publications |
series |
Journal of Medical Signals and Sensors |
issn |
2228-7477 |
publishDate |
2015-01-01 |
description |
Common spatial pattern (CSP) is a method commonly used to enhance the effects of event-related desynchronization and event-related synchronization present in multichannel electroencephalogram-based brain-computer interface (BCI) systems. In the present study, a novel CSP sub-band feature selection has been proposed based on the discriminative information of the features. Besides, a distinction sensitive learning vector quantization based weighting of the selected features has been considered. Finally, after the classification of the weighted features using a support vector machine classifier, the performance of the suggested method has been compared with the existing methods based on frequency band selection, on the same BCI competitions datasets. The results show that the proposed method yields superior results on "ay" subject dataset compared against existing approaches such as sub-band CSP, filter bank CSP (FBCSP), discriminative FBCSP, and sliding window discriminative CSP. |
topic |
Brain-computer interface common spatial pattern distinction sensitive learning vector quantization |
url |
http://www.jmss.mui.ac.ir/article.asp?issn=2228-7477;year=2015;volume=5;issue=3;spage=156;epage=161;aulast=Jamaloo |
work_keys_str_mv |
AT fatemehjamaloo discriminativecommonspatialpatternsubbandsweightingbasedondistinctionsensitivelearningvectorquantizationmethodinmotorimagerybasedbraincomputerinterface AT mohammadmikaeili discriminativecommonspatialpatternsubbandsweightingbasedondistinctionsensitivelearningvectorquantizationmethodinmotorimagerybasedbraincomputerinterface |
_version_ |
1725049097898950656 |