Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces

dc.creatorPeterson, Victoria
dc.creatorNieto, Nicolás
dc.creatorWyser, Dominik
dc.creatorLambercy, Olivier
dc.creatorGassert, Roger
dc.creatorMilone, Diego Humberto
dc.creatorSpies, Ruben Daniel
dc.date2022-02-01
dc.date.accessioned2023-08-30T23:49:13Z
dc.date.available2023-08-30T23:49:13Z
dc.identifierhttp://hdl.handle.net/11336/173138
dc.identifierPeterson, Victoria; Nieto, Nicolás; Wyser, Dominik; Lambercy, Olivier; Gassert, Roger; et al.; Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces; Institute of Electrical and Electronics Engineers; Ieee Transactions On Bio-medical Engineering; 69; 2; 1-2-2022; 807-817
dc.identifier0018-9294
dc.identifierCONICET Digital
dc.identifierCONICET
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8542818
dc.descriptionObjective: This paper tackles the cross-sessions variability of electroencephalography-based brain-computer interfaces (BCIs) in order to avoid the lengthy recalibration step of the decoding method before every use. Methods: We develop a new approach of domain adaptation based on optimal transport to tackle brain signal variability between sessions of motor imagery BCIs. We propose a backward method where, unlike the original formulation, the data from a new session are transported to a calibration session, and thereby avoiding model retraining. Several domain adaptation approaches are evaluated and compared. We simulated two possible online scenarios: i) block-wise adaptation and ii) sample-wise adaptation. In this study, we collect a dataset of 10 subjects performing a hand motor imagery task in 2 sessions. A publicly available dataset is also used. Results: For the first scenario, results indicate that classifier retraining can be avoided by means of our backward formulation yielding to equivalent classification performance as compared to retraining solutions. In the second scenario, classification performance rises up to 90.23% overall accuracy when the label of the indicated mental task is used to learn the transport. Adaptive time is between 10 and 80 times faster than the other methods. Conclusions: The proposed method is able to mitigate the cross-session variability in motor imagery BCIs. Significance: The backward formulation is an efficient retraining-free approach built to avoid lengthy calibration times. Thus, the BCI can be actively used after just a few minutes of setup. This is important for practical applications such as BCI-based motor rehabilitation.
dc.descriptionFil: Peterson, Victoria. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Matemática Aplicada del Litoral. Universidad Nacional del Litoral. Instituto de Matemática Aplicada del Litoral; Argentina
dc.descriptionFil: Nieto, Nicolás. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Matemática Aplicada del Litoral. Universidad Nacional del Litoral. Instituto de Matemática Aplicada del Litoral; Argentina
dc.descriptionFil: Wyser, Dominik. No especifíca;
dc.descriptionFil: Lambercy, Olivier. No especifíca;
dc.descriptionFil: Gassert, Roger. No especifíca;
dc.descriptionFil: Milone, Diego Humberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional. Universidad Nacional del Litoral. Facultad de Ingeniería y Ciencias Hídricas. Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional; Argentina
dc.descriptionFil: Spies, Ruben Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Santa Fe. Instituto de Matemática Aplicada del Litoral. Universidad Nacional del Litoral. Instituto de Matemática Aplicada del Litoral; Argentina
dc.formatapplication/pdf
dc.formatapplication/pdf
dc.languageeng
dc.publisherInstitute of Electrical and Electronics Engineers
dc.relationinfo:eu-repo/semantics/reference/url/https://ri.conicet.gov.ar/admin/retrieve/2f94849f-84de-4184-9ffb-f71012198614/CONICET_Digital_Nro.039ad8b3-65f1-4328-a288-3d83813a3f5a_B.pdf
dc.relationinfo:eu-repo/semantics/altIdentifier/doi/10.1109/TBME.2021.3105912
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.rightshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subjectBRAIN-COMPUTER INTERFACES
dc.subjectDOMAIN ADAPTATION
dc.subjectMOTOR IMAGERY
dc.subjectOPTIMAL TRANSPORT
dc.subjectTRANSFER LEARNING
dc.subjecthttps://purl.org/becyt/ford/1.1
dc.subjecthttps://purl.org/becyt/ford/1
dc.titleTransfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:ar-repo/semantics/artículo
dc.typeinfo:eu-repo/semantics/publishedVersion


Este ítem pertenece a la siguiente institución