[Eeglablist] running CSP after cleaning data with ICA

Scott Makeig smakeig at gmail.com
Wed Sep 28 10:48:31 PDT 2011


Michele -  You are correct that data dimension is reduced by IC removal, and
should show up as null filters in CSP. I suggest you try Christian Kothe's
BCILAB toolbox (a plug-in into EEGLAB) for a complete set of BCI algorithms
with integrated cross-validation testing, etc. (and connecting to real-time
run environments). See http://sccn.ucsd.edu/wiki/BCILAB for a complete
description.

Scott Makeig

On Tue, Sep 27, 2011 at 6:41 AM, Michele Barsotti <nomeserio at gmail.com>wrote:

> Hello everyone,
>  I'm working on a BCI system. I have found useful to work with CSPs but to
> have good spatial filter the data must be cleaned.
> I clean data manually with ICA.
> When I run CSPs algorithm after ICA cleaning the last common spatial filter
> are all zero.
> I think that this happens because with ICA cleaning decrease the rank of
> matrix data.
> It's right?
>
> Other question: Can anyone tell me where I can find a good algorithm for
> CSPs?
>
> Thanks in advance
>
>   - Michele -
>
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to
> eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to
> eeglablist-request at sccn.ucsd.edu
>



-- 
Scott Makeig, Research Scientist and Director, Swartz Center for
Computational Neuroscience, Institute for Neural Computation; Prof. of
Neurosciences (Adj.), University of California San Diego, La Jolla CA
92093-0559, http://sccn.ucsd.edu/~scott
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20110928/0049a927/attachment.html>


More information about the eeglablist mailing list