English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Classifying Event-Related Desynchronization in EEG, ECoG and MEG Signals

Hill, N., Lal, T., Schröder, M., Hinterberger, T., Widman, G., Elger, C., et al. (2006). Classifying Event-Related Desynchronization in EEG, ECoG and MEG Signals. In K. Franke, K.-R. Müller, B. Nickolay, & R. Scäfer (Eds.), Pattern Recognition: 28th DAGM Symposium, Berlin, Germany, September 12-14, 2006 (pp. 404-413). Berlin, Germany: Springer.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0004-99B0-8 Version Permalink: http://hdl.handle.net/21.11116/0000-0004-99B1-7
Genre: Conference Paper

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Hill, NJ1, 2, Author              
Lal, TN1, 2, Author              
Schröder, M, Author
Hinterberger, T, Author
Widman, G, Author
Elger, CE, Author
Schölkopf, B1, 2, Author              
Birbaumer, N, Author
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: We employed three different brain signal recording methods to perform Brain-Computer Interface studies on untrained subjects. In all cases, we aim to develop a system that could be used for fast, reliable preliminary screening in clinical BCI application, and we are interested in knowing how long screening sessions need to be. Good performance could be achieved, on average, after the first 200 trials in EEG, 75–100 trials in MEG, or 25–50 trials in ECoG. We compare the performance of Independent Component Analysis and the Common Spatial Pattern algorithm in each of the three sensor types, finding that spatial filtering does not help in MEG, helps a little in ECoG, and improves performance a great deal in EEG. In all cases the unsupervised ICA algorithm performed at least as well as the supervised CSP algorithm, which can suffer from poor generalization performance due to overfitting, particularly in ECoG and MEG.

Details

show
hide
Language(s):
 Dates: 2006-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 10.1007/11861898_41
 Degree: -

Event

show
hide
Title: 28th Annual Symposium of the German Association for Pattern Recognition (DAGM 2006)
Place of Event: Berlin, Germany
Start-/End Date: 2006-09-12 - 2006-09-14

Legal Case

show

Project information

show

Source 1

show
hide
Title: Pattern Recognition: 28th DAGM Symposium, Berlin, Germany, September 12-14, 2006
Source Genre: Proceedings
 Creator(s):
Franke, K, Editor
Müller, K-R1, Editor            
Nickolay, B, Editor
Scäfer, R, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 404 - 413 Identifier: ISBN: 978-3-540-44412-1

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 4174 Sequence Number: - Start / End Page: - Identifier: -