Empirical Inference Conference Paper 2006

Time-Dependent Demixing of Task-Relevant EEG Signals

Given a spatial filtering algorithm that has allowed us to identify task-relevant EEG sources, we present a simple approach for monitoring the activity of these sources while remaining relatively robust to changes in other (task-irrelevant) brain activity. The idea is to keep spatial *patterns* fixed rather than spatial filters, when transferring from training to test sessions or from one time window to another. We show that a fixed spatial pattern (FSP) approach, using a moving-window estimate of signal covariances, can be more robust to non-stationarity than a fixed spatial filter (FSF) approach.

Author(s): Hill, NJ. and Farquhar, J. and Lal, TN. and Schölkopf, B.
Book Title: Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course 2006
Journal: Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course 2006
Pages: 20-21
Year: 2006
Month: September
Day: 0
Editors: GR M{\"u}ller-Putz and C Brunner and R Leeb and R Scherer and A Schl{\"o}gl and S Wriessnegger and G Pfurtscheller
Publisher: Verlag der Technischen Universit{\"a}t Graz
Bibtex Type: Conference Paper (inproceedings)
Address: Graz, Austria
Event Name: 3rd International Brain-Computer Interface Workshop and Training Course 2006
Event Place: Graz, Austria
Digital: 0
Electronic Archiving: grant_archive
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik
Links:

BibTex

@inproceedings{4244,
  title = {Time-Dependent Demixing of Task-Relevant EEG Signals},
  journal = {Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course 2006},
  booktitle = {Proceedings of the 3rd International Brain-Computer Interface Workshop and Training Course 2006},
  abstract = {Given a spatial filtering algorithm that has allowed us to identify task-relevant EEG sources, we present a simple approach
  for monitoring the activity of these sources while remaining relatively robust to changes in other (task-irrelevant) brain activity. The idea is to keep spatial *patterns* fixed rather than spatial filters, when transferring from
  training to test sessions or from one time window to another. We show that a fixed spatial pattern (FSP)
  approach, using a moving-window estimate of signal covariances, can be more robust to non-stationarity than a fixed spatial filter (FSF) approach.},
  pages = {20-21},
  editors = {GR M{\"u}ller-Putz and C Brunner and R Leeb and R Scherer and A Schl{\"o}gl and S Wriessnegger and G Pfurtscheller},
  publisher = {Verlag der Technischen Universit{\"a}t Graz},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Graz, Austria},
  month = sep,
  year = {2006},
  slug = {4244},
  author = {Hill, NJ. and Farquhar, J. and Lal, TN. and Sch{\"o}lkopf, B.},
  month_numeric = {9}
}