Detecting EEG outliers for BCI on the Riemannian manifold using spectral clustering

Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference Jg. 2020; S. 438 - 441
Hauptverfasser: Yamamoto, Maria Sayu, Sadatnejad, Khadijeh, Tanaka, Toshihisa, Islam, Rabiul, Tanaka, Yuichi, Lotte, Fabien
Format: Tagungsbericht Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.07.2020
ISSN:2694-0604, 1558-4615, 2694-0604
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection methods run the risk of erroneously rejecting some samples as outliers, even if there is no outlier, due to the detection being based on a reference matrix and a threshold. To address this limitation, our method, Riemannian Spectral Clustering (RiSC), detects outliers by clustering SCMs into non-outliers and outliers, based on a proposed similarity measure. This considers the Riemannian geometry of the space and magnifies the similarity within the non-outlier cluster and weakens it between non-outlier and outlier clusters, instead of setting a threshold. To assess RiSC performance, we generated artificial EEG datasets contaminated by different outlier strengths and numbers. Comparing Hit-False (HF) difference between RiSC and existing outlier detection methods confirmed that RiSC could detect outliers significantly better (p < 0.001). In particular, RiSC improved HF difference the most for datasets with the most severe outlier contamination.
AbstractList Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection methods run the risk of erroneously rejecting some samples as outliers, even if there is no outlier, due to the detection being based on a reference matrix and a threshold. To address this limitation, our method, Riemannian Spectral Clustering (RiSC), detects outliers by clustering SCMs into non-outliers and outliers, based on a proposed similarity measure. This considers the Riemannian geometry of the space and magnifies the similarity within the non-outlier cluster and weakens it between non-outlier and outlier clusters, instead of setting a threshold. To assess RiSC performance, we generated artificial EEG datasets contaminated by different outlier strengths and numbers. Comparing Hit-False (HF) difference between RiSC and existing outlier detection methods confirmed that RiSC could detect outliers significantly better (p < 0.001). In particular, RiSC improved HF difference the most for datasets with the most severe outlier contamination.
Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection methods run the risk of erroneously rejecting some samples as outliers, even if there is no outlier, due to the detection being based on a reference matrix and a threshold. To address this limitation, our method, Riemannian Spectral Clustering (RiSC), detects outliers by clustering SCMs into non-outliers and outliers, based on a proposed similarity measure. This considers the Riemannian geometry of the space and magnifies the similarity within the non-outlier cluster and weakens it between non-outlier and outlier clusters, instead of setting a threshold. To assess RiSC performance, we generated artificial EEG datasets contaminated by different outlier strengths and numbers. Comparing Hit-False (HF) difference between RiSC and existing outlier detection methods confirmed that RiSC could detect outliers significantly better (p < 0.001). In particular, RiSC improved HF difference the most for datasets with the most severe outlier contamination.Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we propose a novel outlier detection method that works on the Riemannian manifold of sample covariance matrices (SCMs). Existing outlier detection methods run the risk of erroneously rejecting some samples as outliers, even if there is no outlier, due to the detection being based on a reference matrix and a threshold. To address this limitation, our method, Riemannian Spectral Clustering (RiSC), detects outliers by clustering SCMs into non-outliers and outliers, based on a proposed similarity measure. This considers the Riemannian geometry of the space and magnifies the similarity within the non-outlier cluster and weakens it between non-outlier and outlier clusters, instead of setting a threshold. To assess RiSC performance, we generated artificial EEG datasets contaminated by different outlier strengths and numbers. Comparing Hit-False (HF) difference between RiSC and existing outlier detection methods confirmed that RiSC could detect outliers significantly better (p < 0.001). In particular, RiSC improved HF difference the most for datasets with the most severe outlier contamination.
Author Tanaka, Toshihisa
Lotte, Fabien
Yamamoto, Maria Sayu
Sadatnejad, Khadijeh
Tanaka, Yuichi
Islam, Rabiul
Author_xml – sequence: 1
  givenname: Maria Sayu
  surname: Yamamoto
  fullname: Yamamoto, Maria Sayu
  organization: Inria,Talence Cedex,France,33405
– sequence: 2
  givenname: Khadijeh
  surname: Sadatnejad
  fullname: Sadatnejad, Khadijeh
  organization: Inria,Talence Cedex,France,33405
– sequence: 3
  givenname: Toshihisa
  surname: Tanaka
  fullname: Tanaka, Toshihisa
  organization: Tokyo University of Agriculture and Technology,Koganei-shi, Tokyo,Japan,184-8588
– sequence: 4
  givenname: Rabiul
  surname: Islam
  fullname: Islam, Rabiul
  organization: Tokyo University of Agriculture and Technology,Koganei-shi, Tokyo,Japan,184-8588
– sequence: 5
  givenname: Yuichi
  surname: Tanaka
  fullname: Tanaka, Yuichi
  organization: Tokyo University of Agriculture and Technology,Koganei-shi, Tokyo,Japan,184-8588
– sequence: 6
  givenname: Fabien
  surname: Lotte
  fullname: Lotte, Fabien
  organization: Inria,Talence Cedex,France,33405
BookMark eNotkE9LAzEUxKNUsK1-AkFy9LI12fw_6rrWQkXQ3pc0fauRbbYm2YPf3pX2NI9hfo9hZmgS-gAI3VKyoJSY-_r1seJ8vBYlKcnCUCW4kGdoRlWpKTWG0HM0pULogksqJmhaSsMLIgm_RLOUvsmIEUGn6OMJMrjswyeu6yXuh9x5iAm3fcSP1Qr3AecvwO8e9jYEbwMe1bd9t8ND-qfSYcSj7bDrhpQhjt4Vumhtl-D6pHO0ea431Uuxfluuqod14ZkgubAtaMWUZmMZw7VzShImmbVuK7k2TreCKKP0VlmjWmMEYWBaJonbCS0Um6O749tD7H8GSLnZ--Sg62yAfkhNybnWnKlSjtGbY9QDQHOIfm_jb3Oajf0BaWtggw
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
ESBDL
RIE
RIO
7X8
DOI 10.1109/EMBC44109.2020.9175456
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
Open Access资源_IEL Journals
IEEE/IET Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1728119901
9781728119908
EISSN 1558-4615
2694-0604
EndPage 441
ExternalDocumentID 9175456
Genre orig-research
GroupedDBID 6IE
6IF
6IH
AAJGR
ACGFS
AFFNX
ALMA_UNASSIGNED_HOLDINGS
CBEJK
ESBDL
M43
RIE
RIO
RNS
7X8
ID FETCH-LOGICAL-i350t-afe873783002948cc760363aacb6489c8f507978b7a97f99503e9f360cd58573
IEDL.DBID RIE
ISICitedReferencesCount 7
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000621592200107&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2694-0604
IngestDate Thu Oct 02 20:56:41 EDT 2025
Wed Aug 27 02:33:48 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i350t-afe873783002948cc760363aacb6489c8f507978b7a97f99503e9f360cd58573
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://ieeexplore.ieee.org/document/9175456
PQID 2448843726
PQPubID 23479
PageCount 4
ParticipantIDs proquest_miscellaneous_2448843726
ieee_primary_9175456
PublicationCentury 2000
PublicationDate 2020-07-01
PublicationDateYYYYMMDD 2020-07-01
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-01
  day: 01
PublicationDecade 2020
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
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020051
ssib061542107
ssib053545923
ssib042469959
Score 2.1798887
Snippet Automatically detecting and removing Electroencephalogram (EEG) outliers is essential to design robust brain-computer interfaces (BCIs). In this paper, we...
SourceID proquest
ieee
SourceType Aggregation Database
Publisher
StartPage 438
Title Detecting EEG outliers for BCI on the Riemannian manifold using spectral clustering
URI https://ieeexplore.ieee.org/document/9175456
https://www.proquest.com/docview/2448843726
Volume 2020
WOSCitedRecordID wos000621592200107&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/eLvHCXMwlV1LSwMxEA5t8aAXH61YHyWCR7fdd5Jra6uClqJFeivZ7EQKdVf68Pc7s12roBdvYSGwzITMN_nmm2HsCsIwVSpJHJH6ChMUTztJ6CeO8b1EpxhQbPGg__IghkM5mahRhV1vtTAAUBSfQZuWBZef5mZNT2UdTC0o4FdZVQix0Wptkys6XaUC2HNVp__Y7WGkd0mL4rvtcmc5QuXXvVsEk8H-_37jgDW-VXl8tI03h6wC2RHb-9FQsM6eb4BIAVzzfv-WU7UPjbrmiEx5t3fP84wj4ONPM3ijWUU649T-wubzlFMB_CsvhJcLPedmvqYWCvitwcaD_rh355RjE5xZELkrR1uQIhAyIMYtlMaImNharU0Sh1IZaREDYvKYCK2EVSpyA1A2iF2TYu4ggmNWy_IMThgHhAcBRNp4CJsCRCKptr4FsBAlUehBk9XJOtP3TWOMaWmYJrv8Mu8UDysxEDqDfL2cIpaQkpjC-PTvrWdsl_y1qYc9Z7XVYg0XbMd8rGbLRQv9PpGtwu-fp8OtNQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qFdSLj1aszwge3Xbfu7m2trbYlqJFeluy2YkU6q704e83s12roBdvIRAIk5D5Jt98MwC36LoJ53FsBInNdYBiCSN27diQthWLRDsUlX_ov_SD4TCcTPioBHcbLQwi5slnWKdhzuUnmVzRV1lDhxbk8Ldg23Nd21qrtTbhFd2vQgNsmbzRHjRb2tebpEaxzXqxtmii8uvlzd1J5-B_GzmE6rcuj402HucISpgew_6PkoIVeL5HogX0mLXbD4zyfajZNdPYlDVbPZalTEM-9jTFN-pWJFJGBTBUNksYpcC_slx6ORczJmcrKqKg56ow7rTHra5RNE4wpo5nLg2hMAycIHSIc3NDKQOf-FohZOy7IZeh0ihQh49xIHigOPdMB7lyfFMmOnoInBMop1mKp8BQAwQHPSEtDZwcjUUSoWyFqNCLPdfCGlTIOtH7ujRGVBimBjdf5o30dSUOQqSYrRaRRhNhSFyhf_b30mvY7Y4H_ajfGz6ewx6d3To79gLKy_kKL2FHfiyni_lVfvqfv5WvlA
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%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+the+annual+international+conference+of+the+IEEE+Engineering+in+Medicine+and+Biology+Society&rft.atitle=Detecting+EEG+outliers+for+BCI+on+the+Riemannian+manifold+using+spectral+clustering&rft.au=Yamamoto%2C+Maria+Sayu&rft.au=Sadatnejad%2C+Khadijeh&rft.au=Tanaka%2C+Toshihisa&rft.au=Islam%2C+Rabiul&rft.date=2020-07-01&rft.pub=IEEE&rft.eissn=1558-4615&rft.spage=438&rft.epage=441&rft_id=info:doi/10.1109%2FEMBC44109.2020.9175456&rft.externalDocID=9175456
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2694-0604&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2694-0604&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2694-0604&client=summon