Abstract
A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session.
| Original language | English |
|---|---|
| Title of host publication | 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
| Place of Publication | Piscataway, NJ |
| Publisher | IEEE |
| Pages | 4600-4604 |
| Number of pages | 5 |
| ISBN (Electronic) | 978-1-4577-1589-1, 978-1-4244-4122-8 |
| ISBN (Print) | 978-1-4244-4121-1 |
| DOIs | |
| Publication status | Published - 3 Sep 2011 |
| Event | 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2011 - Boston Marriott Copley Place Hotel, Boston, United States Duration: 30 Aug 2011 → 3 Sep 2011 Conference number: 33 |
Publication series
| Name | Proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
|---|---|
| Publisher | IEEE |
| Volume | 2011 |
| ISSN (Print) | 1557-170X |
| ISSN (Electronic) | 1558-4615 |
Conference
| Conference | 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2011 |
|---|---|
| Abbreviated title | EMBC |
| Country | United States |
| City | Boston |
| Period | 30/08/11 → 3/09/11 |
Fingerprint
Keywords
- Machine learning
- Brain-Computer Interface (BCI)
- Training
- HMI-CI: Computational Intelligence
- Calibration
Cite this
}
A subject-independent brain-computer interface based on smoothed, second-order baselining. / Reuderink, B.; Farquhar, Jason; Poel, Mannes; Nijholt, Antinus.
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway, NJ : IEEE, 2011. p. 4600-4604 (Proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Vol. 2011).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
TY - GEN
T1 - A subject-independent brain-computer interface based on smoothed, second-order baselining.
AU - Reuderink, B.
AU - Farquhar, Jason
AU - Poel, Mannes
AU - Nijholt, Antinus
PY - 2011/9/3
Y1 - 2011/9/3
N2 - A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session.
AB - A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session.
KW - Machine learning
KW - Brain-Computer Interface (BCI)
KW - Training
KW - HMI-CI: Computational Intelligence
KW - Calibration
UR - http://www.scopus.com/inward/record.url?scp=84863605471&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2011.6091139
DO - 10.1109/IEMBS.2011.6091139
M3 - Conference contribution
C2 - 22255362
SN - 978-1-4244-4121-1
T3 - Proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society
SP - 4600
EP - 4604
BT - 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society
PB - IEEE
CY - Piscataway, NJ
ER -