Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces
<p/> <p>Most EEG-based brain-computer interface (BCI) paradigms come along with specific electrode positions, for example, for a visual-based BCI, electrode positions close to the primary visual cortex are used. For new BCI paradigms it is usually not known where task relevant activity c...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2005-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1155/ASP.2005.3103 |
| _version_ | 1818453685455290368 |
|---|---|
| author | Lal Thomas Navin Hill N Jeremy Schölkopf Bernhard Hinterberger Thilo Birbaumer Niels Schröder Michael Bogdan Martin Rosenstiel Wolfgang |
| author_facet | Lal Thomas Navin Hill N Jeremy Schölkopf Bernhard Hinterberger Thilo Birbaumer Niels Schröder Michael Bogdan Martin Rosenstiel Wolfgang |
| author_sort | Lal Thomas Navin |
| collection | DOAJ |
| description | <p/> <p>Most EEG-based brain-computer interface (BCI) paradigms come along with specific electrode positions, for example, for a visual-based BCI, electrode positions close to the primary visual cortex are used. For new BCI paradigms it is usually not known where task relevant activity can be measured from the scalp. For individual subjects, Lal et al. in 2004 showed that recording positions can be found without the use of prior knowledge about the paradigm used. However it remains unclear to what extent their method of <it>recursive channel elimination</it> (RCE) can be generalized across subjects. In this paper we transfer channel rankings from a group of subjects to a new subject. For motor imagery tasks the results are promising, although cross-subject channel selection does not quite achieve the performance of channel selection on data of single subjects. Although the RCE method was not provided with prior knowledge about the mental task, channels that are well known to be important (from a physiological point of view) were consistently selected whereas task-irrelevant channels were reliably disregarded.</p> |
| first_indexed | 2024-12-14T21:42:55Z |
| format | Article |
| id | doaj.art-4dad5bea6aaf4eafb7aeab0b5aa52ac2 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-14T21:42:55Z |
| publishDate | 2005-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-4dad5bea6aaf4eafb7aeab0b5aa52ac22022-12-21T22:46:24ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802005-01-01200519174746Robust EEG Channel Selection across Subjects for Brain-Computer InterfacesLal Thomas NavinHill N JeremySchölkopf BernhardHinterberger ThiloBirbaumer NielsSchröder MichaelBogdan MartinRosenstiel Wolfgang<p/> <p>Most EEG-based brain-computer interface (BCI) paradigms come along with specific electrode positions, for example, for a visual-based BCI, electrode positions close to the primary visual cortex are used. For new BCI paradigms it is usually not known where task relevant activity can be measured from the scalp. For individual subjects, Lal et al. in 2004 showed that recording positions can be found without the use of prior knowledge about the paradigm used. However it remains unclear to what extent their method of <it>recursive channel elimination</it> (RCE) can be generalized across subjects. In this paper we transfer channel rankings from a group of subjects to a new subject. For motor imagery tasks the results are promising, although cross-subject channel selection does not quite achieve the performance of channel selection on data of single subjects. Although the RCE method was not provided with prior knowledge about the mental task, channels that are well known to be important (from a physiological point of view) were consistently selected whereas task-irrelevant channels were reliably disregarded.</p>http://dx.doi.org/10.1155/ASP.2005.3103brain-computer interfacechannel selectionfeature selectionrecursive channel eliminationsupport vector machineelectroencephalography |
| spellingShingle | Lal Thomas Navin Hill N Jeremy Schölkopf Bernhard Hinterberger Thilo Birbaumer Niels Schröder Michael Bogdan Martin Rosenstiel Wolfgang Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces EURASIP Journal on Advances in Signal Processing brain-computer interface channel selection feature selection recursive channel elimination support vector machine electroencephalography |
| title | Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces |
| title_full | Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces |
| title_fullStr | Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces |
| title_full_unstemmed | Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces |
| title_short | Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces |
| title_sort | robust eeg channel selection across subjects for brain computer interfaces |
| topic | brain-computer interface channel selection feature selection recursive channel elimination support vector machine electroencephalography |
| url | http://dx.doi.org/10.1155/ASP.2005.3103 |
| work_keys_str_mv | AT lalthomasnavin robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT hillnjeremy robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT sch246lkopfbernhard robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT hinterbergerthilo robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT birbaumerniels robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT schr246dermichael robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT bogdanmartin robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces AT rosenstielwolfgang robusteegchannelselectionacrosssubjectsforbraincomputerinterfaces |