Transfer learning with large-scale data in brain-computer interfaces

Wei, CS; Lin, YP; Wang, YT; Lin, CT; Jung, TP

Transfer learning with large-scale data in brain-computer interfaces

Wei, CS Lin, YP Wang, YT Lin, CT

Jung, TP

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016, 2016-October pp. 4666 - 4669
Issue Date:: 2016-10-13

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted ManuscriptAdobe PDF (720.2 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wei, CS	en_US
dc.contributor.author	Lin, YP	en_US
dc.contributor.author	Wang, YT	en_US
dc.contributor.author	Lin, CT https://orcid.org/0000-0001-8371-8197	en_US
dc.contributor.author	Jung, TP	en_US
dc.date.issued	2016-10-13	en_US
dc.identifier.citation	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016, 2016-October pp. 4666 - 4669	en_US
dc.identifier.isbn	9781457702204	en_US
dc.identifier.issn	1557-170X	en_US
dc.identifier.uri	http://hdl.handle.net/10453/113464
dc.description.abstract	© 2016 IEEE. Human variability in electroencephalogram (EEG) poses significant challenges for developing practical real-world applications of brain-computer interfaces (BCIs). The intuitive solution of collecting sufficient user-specific training/calibration data can be very labor-intensive and time-consuming, hindering the practicability of BCIs. To address this problem, transfer learning (TL), which leverages existing data from other sessions or subjects, has recently been adopted by the BCI community to build a BCI for a new user with limited calibration data. However, current TL approaches still require training/calibration data from each of conditions, which might be difficult or expensive to obtain. This study proposed a novel TL framework that could nearly eliminate requirement of subject-specific calibration data by leveraging large-scale data from other subjects. The efficacy of this method was validated in a passive BCI that was designed to detect neurocognitive lapses during driving. With the help of large-scale data, the proposed TL approach outperformed the within-subject approach while considerably reducing the amount of calibration data required for each individual (∼1.5 min of data from each individual as opposed to a 90 min pilot session used in a standard within-subject approach). This demonstration might considerably facilitate the real-world applications of BCIs.	en_US
dc.relation.ispartof	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS	en_US
dc.relation.isbasedon	10.1109/EMBC.2016.7591768	en_US
dc.subject.mesh	Brain	en_US
dc.subject.mesh	Humans	en_US
dc.subject.mesh	Electroencephalography	en_US
dc.subject.mesh	Calibration	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Brain-Computer Interfaces	en_US
dc.title	Transfer learning with large-scale data in brain-computer interfaces	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2016-October	en_US
utslib.for	0903 Biomedical Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US
pubs.volume	2016-October	en_US

Abstract:

© 2016 IEEE. Human variability in electroencephalogram (EEG) poses significant challenges for developing practical real-world applications of brain-computer interfaces (BCIs). The intuitive solution of collecting sufficient user-specific training/calibration data can be very labor-intensive and time-consuming, hindering the practicability of BCIs. To address this problem, transfer learning (TL), which leverages existing data from other sessions or subjects, has recently been adopted by the BCI community to build a BCI for a new user with limited calibration data. However, current TL approaches still require training/calibration data from each of conditions, which might be difficult or expensive to obtain. This study proposed a novel TL framework that could nearly eliminate requirement of subject-specific calibration data by leveraging large-scale data from other subjects. The efficacy of this method was validated in a passive BCI that was designed to detect neurocognitive lapses during driving. With the help of large-scale data, the proposed TL approach outperformed the within-subject approach while considerably reducing the amount of calibration data required for each individual (∼1.5 min of data from each individual as opposed to a 90 min pilot session used in a standard within-subject approach). This demonstration might considerably facilitate the real-world applications of BCIs.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/113464