A Randomised Ensemble Learning Approach for Multiclass Motor Imagery Classification Using Error Correcting Output Coding

Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG sub...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Ročník 2018; s. 5081 - 5084
Hlavní autori: Bera, Sutanu, Roy, Rinku, Sikdar, Debdeep, Kar, Aupendu, Mukhopadhyay, Rupsha, Mahadevappal, Manjunatha
Médium: Konferenčný príspevok.. Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.07.2018
Predmet:
ISSN:1557-170X, 2694-0604, 1558-4615, 2694-0604
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands α (8-12Hz) and β (12-30Hz) along with HG (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98% and 84% in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.
AbstractList Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands α (8-12Hz) and β (12-30Hz) along with HG (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98% and 84% in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.
Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands $\alpha$ (8-12Hz) and $\beta$ (12-30Hz) along with $HG$ (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98ȥ and 84ȥ in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.
Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands $\alpha$ (8-12Hz) and $\beta$ (12-30Hz) along with $HG$ (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98ȥ and 84ȥ in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification of from this featureset has been a challenging job. Different approaches have been proposed to be applied on featureset of different EEG subbands to achieve significant classification accuracy. Ensemble learning is very effective in this context to achieve higher accuracy in Brain-Computer Interface (BCI) domain. In this study, we have proposed enhanced classification algorithms to achieve higher classification accuracies. The methods were evaluated against the motor imagery data from Dataset 2a of the publicly available BCI Competition IV (2008). This dataset consists of 22 channels EEG data of 9 subjects for four different movements. A tree based ensemble approach for supervised classification, Extra-Trees algorithm, has been proposed in this paper and also evaluated for its efficacy on this dataset to classify between left hand and right hand movement imaginations. Moreover, this classifier has its inherent capability to select optimum features. Furthermore, in this paper an extension of the binary classification into multiclass domain is also implemented with error correcting output codes (ECOC) approach using the same dataset. Subject-specific frequency bands $\alpha$ (8-12Hz) and $\beta$ (12-30Hz) along with $HG$ (70-100Hz) were considered to extract CSP features. We have achieved an individual peak accuracy of 98ȥ and 84ȥ in binary class and multiclass classification respectively. Furthermore, the results yielded a mean kappa value of 0.58 across all the subjects. This kappa value is higher than of the winner of competition and also from the most of the other approaches applied in this dataset.
Author Kar, Aupendu
Bera, Sutanu
Roy, Rinku
Sikdar, Debdeep
Mukhopadhyay, Rupsha
Mahadevappal, Manjunatha
Author_xml – sequence: 1
  givenname: Sutanu
  surname: Bera
  fullname: Bera, Sutanu
  email: sutanu.bera@iitkgp.ac.in
  organization: Sch. of Med. Sci. & Technol., Indian Inst. of Technol., Kharagpur, Kharagpur, India
– sequence: 2
  givenname: Rinku
  surname: Roy
  fullname: Roy, Rinku
  email: rinku.roy@iitkgp.ac.in
  organization: Adv. Technol. Dev. Centre, Indian Inst. of Technol., Kharagpur, Kharagpur, India
– sequence: 3
  givenname: Debdeep
  surname: Sikdar
  fullname: Sikdar, Debdeep
  email: deep@iitkgp.ac.in
  organization: Sch. of Med. Sci. & Technol., Indian Inst. of Technol., Kharagpur, Kharagpur, India
– sequence: 4
  givenname: Aupendu
  surname: Kar
  fullname: Kar, Aupendu
  email: aupendukar@iitkgp.ac.in
  organization: Electr. Eng., Indian Inst. of Technol., Kharagpur, Kharagpur, India
– sequence: 5
  givenname: Rupsha
  surname: Mukhopadhyay
  fullname: Mukhopadhyay, Rupsha
  email: rupsha.mukhopadhyay@gmail.com
  organization: Sch. of Med. Sci. & Technol., Indian Inst. of Technol., Kharagpur, Kharagpur, India
– sequence: 6
  givenname: Manjunatha
  surname: Mahadevappal
  fullname: Mahadevappal, Manjunatha
  email: mmaha2@smst.iitkgp.ac.in
  organization: Sch. of Med. Sci. & Technol., Indian Inst. of Technol., Kharagpur, Kharagpur, India
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30441483$$D View this record in MEDLINE/PubMed
BookMark eNo9kVlPGzEQx92Kiqt8AIRU-ZGXTT3rY53HsAqHlAipKlLfIq89BqM9gr0rwbfHKYGnmfnPb0ZznJCDfuiRkHNgMwA2_71cX9WzkoGeaQlclPCNnM0rDZJrxZVQ6js5Bil1IRTIg_9-VUDF_h2Rk5SeGSsZk3BIjjgTAoTmx-R1Qf-Y3g1dSOjosk_YNS3SFZrYh_6RLrbbOBj7RP0Q6Xpqx2BbkxJdD2MW7jrziPGN1jst-GDNGIaePqRd6TLGjNRDjGjHnXA_jdtpzIrL0U_yw5s24dnenpKH6-Xf-rZY3d_c1YtVEUoOY2GFcXls5QGcbriVpUZhFKBvgEvdNMw3ujTOoarAe8vQodfcSzuHSqDlp-Tyo2_e42XCNG7yqhbb1vQ4TGlT5jZQcsWqjP7ao1PTodtsY-hMfNt8XisDFx9AQMSv9P4X_B0w_Hw0
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
NPM
7X8
DOI 10.1109/EMBC.2018.8513421
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList
PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781538636466
1538636468
EISSN 1558-4615
2694-0604
EndPage 5084
ExternalDocumentID 30441483
8513421
Genre orig-research
Journal Article
GroupedDBID 6IE
6IF
6IH
AAJGR
ACGFS
AFFNX
ALMA_UNASSIGNED_HOLDINGS
CBEJK
M43
RIE
RIO
RNS
29F
29G
6IK
6IM
IPLJI
NPM
7X8
ID FETCH-LOGICAL-i231t-c4ad0206f11d8b3c528e4a61efb1358bb0fb82adde671ffc0edef83f5c9174ec3
IEDL.DBID RIE
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000596231905132&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1557-170X
2694-0604
IngestDate Thu Oct 02 12:02:47 EDT 2025
Thu Jan 02 23:10:37 EST 2025
Wed Aug 27 02:50:00 EDT 2025
IsPeerReviewed true
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i231t-c4ad0206f11d8b3c528e4a61efb1358bb0fb82adde671ffc0edef83f5c9174ec3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 30441483
PQID 2135123607
PQPubID 23479
PageCount 4
ParticipantIDs proquest_miscellaneous_2135123607
ieee_primary_8513421
pubmed_primary_30441483
PublicationCentury 2000
PublicationDate 2018-Jul
PublicationDateYYYYMMDD 2018-07-01
PublicationDate_xml – month: 07
  year: 2018
  text: 2018-Jul
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
PublicationTitleAbbrev EMBC
PublicationTitleAlternate Conf Proc IEEE Eng Med Biol Soc
PublicationYear 2018
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020051
ssj0061641
ssib061542107
ssib053545923
ssib042469959
Score 1.7997926
Snippet Common Spectral Pattern (CSP) algorithm remains predominant for feature extraction from multichannel EEG motor imagery data. However, multiclass classification...
SourceID proquest
pubmed
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 5081
SubjectTerms Classification algorithms
Covariance matrices
Electroencephalography
Feature extraction
Matrix decomposition
Training
Vegetation
Title A Randomised Ensemble Learning Approach for Multiclass Motor Imagery Classification Using Error Correcting Output Coding
URI https://ieeexplore.ieee.org/document/8513421
https://www.ncbi.nlm.nih.gov/pubmed/30441483
https://www.proquest.com/docview/2135123607
Volume 2018
WOSCitedRecordID wos000596231905132&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELYAMcDCozzKozISI4EkdhxnhKoIhkKFQOpWOc4ZIdGkahME_x6fEwIDDGxRFEfW3Sn-LvfdfYScRkkCoWC-F0JiPM7TyFOhBo8rqTBd0CI2TmwivruT43EyWiJnbS8MADjyGZzjpavlZ4Wu8FfZhUUHjGPX-HIci7pXq02uMLqaqmXgJxeD4VUfiVvyvFnUqKf8DSTdgXK98b-tbJKd7848OmrPnC2yBPk2Wf8xVLBD3i_pg8qzwjoQMjrIFzBNX4E2g1Sf6WUzRZxauEpd_61GBE2HhU2_6e0Uh1p8UCeWiTQi5znqmAV0MJ_bR_oo6KGRLk3vq3JWlfYO7maHPF0PHvs3XqOv4L1YVFd6mqvMGk6YIMhkynQUSuBKBGDSgEUyTX2TyhA_gCIOjNE-ZGAkM5G2OR4HzXbJSl7ksE9oGKmMJzICafFVKqTC1E5beGkSEWW-3yUdtOFkVo_QmDTm65KTL29MrFWwVqFyKKrFJETlwJAJP-6SvdpN7WLmWwzHJTv4_aWHZA0dX3Nqj8hKOa_gmKzqt_JlMe_Z2BnLnoudT5fkxbs
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0hikS5lK-221JqpB4bcPyRdY50tQgEu6CKStwixxlXSCVBuwmCf1-PN116oIfeoiiOrJlR_CbzZh7AF53nKDLJE4G5T5QqdWKFw0RZYyldcNnQR7GJ4XRqbm7yqxX4uuyFQcRIPsNDuoy1_KpxHf0qOwroQCrqGn-llRJ80a21TK8ovvq6Zcrzo_Hk24ioW-awX9brp_wbSsYj5eTN_21mE3afe_PY1fLU2YIVrLdh46-xgjvweMy-27pqgguxYuN6jnflL2T9KNWf7LifI84CYGWxA9cRhmaTJiTg7OyOxlo8sSiXSUSi6DsWuQVsPJuFR0Yk6eGIMM0uu_a-a8Md2s0u_DgZX49Ok15hIbkNuK5NnLJVMFzm07QypXRaGFQ2S9GXqdSmLLkvjaBPYDZMvXccK_RGeu1ClqfQybewWjc1vgcmtK1UbjSagLDKzFhK7lwAmD7PdMX5AHbIhsX9YohG0ZtvAAd_vFEEq1C1wtbYdPNCkHagkBkfDuDdwk3LxZIHFKeM_PDySz_D-un15KK4OJuef4TXFAQLhu0erLazDj_Bmntob-ez_RhBvwFat8ga
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=Proceedings+of+the+annual+international+conference+of+the+IEEE+Engineering+in+Medicine+and+Biology+Society&rft.atitle=A+Randomised+Ensemble+Learning+Approach+for+Multiclass+Motor+Imagery+Classification+Using+Error+Correcting+Output+Coding&rft.au=Bera%2C+Sutanu&rft.au=Roy%2C+Rinku&rft.au=Sikdar%2C+Debdeep&rft.au=Kar%2C+Aupendu&rft.date=2018-07-01&rft.pub=IEEE&rft.eissn=1558-4615&rft.spage=5081&rft.epage=5084&rft_id=info:doi/10.1109%2FEMBC.2018.8513421&rft.externalDocID=8513421
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1557-170X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1557-170X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1557-170X&client=summon