Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces
dc.contributor.author
Peterson, Victoria
dc.contributor.author
Nieto, Nicolás
dc.contributor.author
Wyser, Dominik
dc.contributor.author
Lambercy, Olivier
dc.contributor.author
Gassert, Roger
dc.contributor.author
Milone, Diego H.
dc.contributor.author
Spies, Rubén D.
dc.date.accessioned
2022-03-07T08:09:59Z
dc.date.available
2022-01-26T14:02:33Z
dc.date.available
2022-03-07T08:09:59Z
dc.date.issued
2022-02
dc.identifier.issn
0018-9294
dc.identifier.issn
1558-2531
dc.identifier.other
10.1109/tbme.2021.3105912
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/528899
dc.description.abstract
Objective: 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.
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.title
Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces
en_US
dc.type
Journal Article
dc.date.published
2021-08-18
ethz.journal.title
IEEE Transactions on Biomedical Engineering
ethz.journal.volume
69
en_US
ethz.journal.issue
2
en_US
ethz.journal.abbreviated
IEEE trans. biomed. eng.
ethz.pages.start
807
en_US
ethz.pages.end
817
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02070 - Dep. Gesundheitswiss. und Technologie / Dep. of Health Sciences and Technology::03827 - Gassert, Roger / Gassert, Roger
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02070 - Dep. Gesundheitswiss. und Technologie / Dep. of Health Sciences and Technology::03827 - Gassert, Roger / Gassert, Roger
en_US
ethz.date.deposited
2022-01-26T14:02:39Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2022-03-07T08:10:06Z
ethz.rosetta.lastUpdated
2023-02-07T00:19:22Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Transfer%20Learning%20Based%20on%20Optimal%20Transport%20for%20Motor%20Imagery%20Brain-Computer%20Interfaces&rft.jtitle=IEEE%20Transactions%20on%20Biomedical%20Engineering&rft.date=2022-02&rft.volume=69&rft.issue=2&rft.spage=807&rft.epage=817&rft.issn=0018-9294&1558-2531&rft.au=Peterson,%20Victoria&Nieto,%20Nicol%C3%A1s&Wyser,%20Dominik&Lambercy,%20Olivier&Gassert,%20Roger&rft.genre=article&rft_id=info:doi/10.1109/tbme.2021.3105912&
Files in this item
Files | Size | Format | Open in viewer |
---|---|---|---|
There are no files associated with this item. |
Publication type
-
Journal Article [130276]