Reducing calibration time for brain-computer interfaces: A clustering approach

Matthias Krauledat, Michael Schröder, Benjamin Blankertz, Klaus Muller

Research output: Chapter in Book/Report/Conference proceedingConference contribution

45 Citations (Scopus)

Abstract

Up to now even subjects that are experts in the use of machine learning based BCI systems still have to undergo a calibration session of about 20-30 min. From this data their (movement) intentions are so far infered. We now propose a new paradigm that allows to completely omit such calibration and instead transfer knowledge from prior sessions. To achieve this goal we first define normalized CSP features and distances in-between. Second, we derive prototypical features across sessions: (a) by clustering or (b) by feature concatenationmethods. Finally, we construct a classifier based on these individualized prototypes and show that, indeed, classifiers can be successfully transferred to a new session for a number of subjects.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems
Pages753-760
Number of pages8
Publication statusPublished - 2007 Dec 1
Externally publishedYes
Event20th Annual Conference on Neural Information Processing Systems, NIPS 2006 - Vancouver, BC, Canada
Duration: 2006 Dec 42006 Dec 7

Other

Other20th Annual Conference on Neural Information Processing Systems, NIPS 2006
CountryCanada
CityVancouver, BC
Period06/12/406/12/7

Fingerprint

Brain computer interface
Classifiers
Calibration
Learning systems

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Krauledat, M., Schröder, M., Blankertz, B., & Muller, K. (2007). Reducing calibration time for brain-computer interfaces: A clustering approach. In Advances in Neural Information Processing Systems (pp. 753-760)

Reducing calibration time for brain-computer interfaces : A clustering approach. / Krauledat, Matthias; Schröder, Michael; Blankertz, Benjamin; Muller, Klaus.

Advances in Neural Information Processing Systems. 2007. p. 753-760.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krauledat, M, Schröder, M, Blankertz, B & Muller, K 2007, Reducing calibration time for brain-computer interfaces: A clustering approach. in Advances in Neural Information Processing Systems. pp. 753-760, 20th Annual Conference on Neural Information Processing Systems, NIPS 2006, Vancouver, BC, Canada, 06/12/4.
Krauledat M, Schröder M, Blankertz B, Muller K. Reducing calibration time for brain-computer interfaces: A clustering approach. In Advances in Neural Information Processing Systems. 2007. p. 753-760
Krauledat, Matthias ; Schröder, Michael ; Blankertz, Benjamin ; Muller, Klaus. / Reducing calibration time for brain-computer interfaces : A clustering approach. Advances in Neural Information Processing Systems. 2007. pp. 753-760
@inproceedings{9c7fbefc1b8c437ba6d20690788d403b,
title = "Reducing calibration time for brain-computer interfaces: A clustering approach",
abstract = "Up to now even subjects that are experts in the use of machine learning based BCI systems still have to undergo a calibration session of about 20-30 min. From this data their (movement) intentions are so far infered. We now propose a new paradigm that allows to completely omit such calibration and instead transfer knowledge from prior sessions. To achieve this goal we first define normalized CSP features and distances in-between. Second, we derive prototypical features across sessions: (a) by clustering or (b) by feature concatenationmethods. Finally, we construct a classifier based on these individualized prototypes and show that, indeed, classifiers can be successfully transferred to a new session for a number of subjects.",
author = "Matthias Krauledat and Michael Schr{\"o}der and Benjamin Blankertz and Klaus Muller",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9780262195683",
pages = "753--760",
booktitle = "Advances in Neural Information Processing Systems",

}

TY - GEN

T1 - Reducing calibration time for brain-computer interfaces

T2 - A clustering approach

AU - Krauledat, Matthias

AU - Schröder, Michael

AU - Blankertz, Benjamin

AU - Muller, Klaus

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Up to now even subjects that are experts in the use of machine learning based BCI systems still have to undergo a calibration session of about 20-30 min. From this data their (movement) intentions are so far infered. We now propose a new paradigm that allows to completely omit such calibration and instead transfer knowledge from prior sessions. To achieve this goal we first define normalized CSP features and distances in-between. Second, we derive prototypical features across sessions: (a) by clustering or (b) by feature concatenationmethods. Finally, we construct a classifier based on these individualized prototypes and show that, indeed, classifiers can be successfully transferred to a new session for a number of subjects.

AB - Up to now even subjects that are experts in the use of machine learning based BCI systems still have to undergo a calibration session of about 20-30 min. From this data their (movement) intentions are so far infered. We now propose a new paradigm that allows to completely omit such calibration and instead transfer knowledge from prior sessions. To achieve this goal we first define normalized CSP features and distances in-between. Second, we derive prototypical features across sessions: (a) by clustering or (b) by feature concatenationmethods. Finally, we construct a classifier based on these individualized prototypes and show that, indeed, classifiers can be successfully transferred to a new session for a number of subjects.

UR - http://www.scopus.com/inward/record.url?scp=84864042974&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864042974&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84864042974

SN - 9780262195683

SP - 753

EP - 760

BT - Advances in Neural Information Processing Systems

ER -