On the robustness of EEG tensor completion methods

Autores
Duan, Feng; Jia, Hao; Zhang, Zhiwen; Feng, Fan; Tan, Ying; Dai, Yang Yang; Cichocki, Andrzej; Zhenglu, Yang; Caiafa, César Federico; Zhe, Sun; Solé Casals, Jordi
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
During the acquisition of electroencephalographic (EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor (multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method (TCM). However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were designed. Firstly, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion (STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or not a completion method is useful enough to complete EEG signals.
Fil: Duan, Feng. Nankai University; China
Fil: Jia, Hao. Nankai University; China
Fil: Zhang, Zhiwen. Nankai University; China
Fil: Feng, Fan. Nankai University; China
Fil: Tan, Ying. Nankai University; China
Fil: Dai, Yang Yang. Nankai University; China
Fil: Cichocki, Andrzej. Skolkowo Institute of Science and Technology; Rusia. Hangzhou Dianzi University; China. Polish Academy of Sciences; Polonia. Nicolaus Copernicus University; Polonia
Fil: Zhenglu, Yang. Nankai University; China
Fil: Caiafa, César Federico. Nankai University; China. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Zhe, Sun. Nankai University; China. Riken. Information Systems and Cybersecurity; Japón
Fil: Solé Casals, Jordi. Nankai University; China. University of Cambridge; Estados Unidos. Universidad Central de Cataluña; España
Materia
EEG
Tensor completion
BCI
tensor decomposition
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/137569

id CONICETDig_3271a713ab350d45c75251ed02174d4e
oai_identifier_str oai:ri.conicet.gov.ar:11336/137569
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling On the robustness of EEG tensor completion methodsDuan, FengJia, HaoZhang, ZhiwenFeng, FanTan, YingDai, Yang YangCichocki, AndrzejZhenglu, YangCaiafa, César FedericoZhe, SunSolé Casals, JordiEEGTensor completionBCItensor decompositionhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1During the acquisition of electroencephalographic (EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor (multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method (TCM). However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were designed. Firstly, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion (STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or not a completion method is useful enough to complete EEG signals.Fil: Duan, Feng. Nankai University; ChinaFil: Jia, Hao. Nankai University; ChinaFil: Zhang, Zhiwen. Nankai University; ChinaFil: Feng, Fan. Nankai University; ChinaFil: Tan, Ying. Nankai University; ChinaFil: Dai, Yang Yang. Nankai University; ChinaFil: Cichocki, Andrzej. Skolkowo Institute of Science and Technology; Rusia. Hangzhou Dianzi University; China. Polish Academy of Sciences; Polonia. Nicolaus Copernicus University; PoloniaFil: Zhenglu, Yang. Nankai University; ChinaFil: Caiafa, César Federico. Nankai University; China. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Zhe, Sun. Nankai University; China. Riken. Information Systems and Cybersecurity; JapónFil: Solé Casals, Jordi. Nankai University; China. University of Cambridge; Estados Unidos. Universidad Central de Cataluña; EspañaSpringer Verlag Berlín2021-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/137569Duan, Feng; Jia, Hao; Zhang, Zhiwen; Feng, Fan; Tan, Ying; et al.; On the robustness of EEG tensor completion methods; Springer Verlag Berlín; Science China Technological Sciences; 64; 4-2021; 1-291869-1900CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.sciengine.com/publisher/scp/journal/SCTS/doi/10.1007/s11431-020-1839-5?slug=fulltextinfo:eu-repo/semantics/altIdentifier/doi/10.1007/s11431-020-1839-5info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:56:16Zoai:ri.conicet.gov.ar:11336/137569instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:56:16.519CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv On the robustness of EEG tensor completion methods
title On the robustness of EEG tensor completion methods
spellingShingle On the robustness of EEG tensor completion methods
Duan, Feng
EEG
Tensor completion
BCI
tensor decomposition
title_short On the robustness of EEG tensor completion methods
title_full On the robustness of EEG tensor completion methods
title_fullStr On the robustness of EEG tensor completion methods
title_full_unstemmed On the robustness of EEG tensor completion methods
title_sort On the robustness of EEG tensor completion methods
dc.creator.none.fl_str_mv Duan, Feng
Jia, Hao
Zhang, Zhiwen
Feng, Fan
Tan, Ying
Dai, Yang Yang
Cichocki, Andrzej
Zhenglu, Yang
Caiafa, César Federico
Zhe, Sun
Solé Casals, Jordi
author Duan, Feng
author_facet Duan, Feng
Jia, Hao
Zhang, Zhiwen
Feng, Fan
Tan, Ying
Dai, Yang Yang
Cichocki, Andrzej
Zhenglu, Yang
Caiafa, César Federico
Zhe, Sun
Solé Casals, Jordi
author_role author
author2 Jia, Hao
Zhang, Zhiwen
Feng, Fan
Tan, Ying
Dai, Yang Yang
Cichocki, Andrzej
Zhenglu, Yang
Caiafa, César Federico
Zhe, Sun
Solé Casals, Jordi
author2_role author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv EEG
Tensor completion
BCI
tensor decomposition
topic EEG
Tensor completion
BCI
tensor decomposition
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv During the acquisition of electroencephalographic (EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor (multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method (TCM). However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were designed. Firstly, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion (STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or not a completion method is useful enough to complete EEG signals.
Fil: Duan, Feng. Nankai University; China
Fil: Jia, Hao. Nankai University; China
Fil: Zhang, Zhiwen. Nankai University; China
Fil: Feng, Fan. Nankai University; China
Fil: Tan, Ying. Nankai University; China
Fil: Dai, Yang Yang. Nankai University; China
Fil: Cichocki, Andrzej. Skolkowo Institute of Science and Technology; Rusia. Hangzhou Dianzi University; China. Polish Academy of Sciences; Polonia. Nicolaus Copernicus University; Polonia
Fil: Zhenglu, Yang. Nankai University; China
Fil: Caiafa, César Federico. Nankai University; China. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Zhe, Sun. Nankai University; China. Riken. Information Systems and Cybersecurity; Japón
Fil: Solé Casals, Jordi. Nankai University; China. University of Cambridge; Estados Unidos. Universidad Central de Cataluña; España
description During the acquisition of electroencephalographic (EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor (multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method (TCM). However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were designed. Firstly, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion (STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or not a completion method is useful enough to complete EEG signals.
publishDate 2021
dc.date.none.fl_str_mv 2021-04
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/137569
Duan, Feng; Jia, Hao; Zhang, Zhiwen; Feng, Fan; Tan, Ying; et al.; On the robustness of EEG tensor completion methods; Springer Verlag Berlín; Science China Technological Sciences; 64; 4-2021; 1-29
1869-1900
CONICET Digital
CONICET
url http://hdl.handle.net/11336/137569
identifier_str_mv Duan, Feng; Jia, Hao; Zhang, Zhiwen; Feng, Fan; Tan, Ying; et al.; On the robustness of EEG tensor completion methods; Springer Verlag Berlín; Science China Technological Sciences; 64; 4-2021; 1-29
1869-1900
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.sciengine.com/publisher/scp/journal/SCTS/doi/10.1007/s11431-020-1839-5?slug=fulltext
info:eu-repo/semantics/altIdentifier/doi/10.1007/s11431-020-1839-5
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer Verlag Berlín
publisher.none.fl_str_mv Springer Verlag Berlín
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269394489573376
score 13.13397