[Eeglablist] generalized EVD in CSP ?

[Makoto Miyakoshi]

Dear Luca,

When you have time, could you comment on this? I've never used it myself.

Makoto

On Tue, Oct 18, 2016 at 4:09 AM, Vadlamani Samhitha <
vadlamani.samhitha at gmail.com> wrote:

> Hi list , I am performing CSP on EEG data . I have computed covariance
> matrices for class 1 and class 2 ( C1 and C2 ) . Now while obtaining
>  filter coefficients , I  have been suggested to perform generalized
> eigenvalue decomposition to get filter coefficients such that W^T C1 W =
> D and W^T(C1+C2) W = I .(Identity matrix )
> So , I have used [W,D]=eig(C1,C1+C2) ; where W is my filter matrix , D is
> the  eigenvalue matrix for C1 .
> after doing so , when I manually try to check if the above two conditions
> are satisfied , they don't seem so . I have been struggling to find out
> what went wrong . I would be really grateful if someone could  suggest what
> I am missing here . Thank you in advance .
>
> _______________________________________________
> 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
>



-- 
Makoto Miyakoshi
Swartz Center for Computational Neuroscience
Institute for Neural Computation, University of California San Diego
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20161019/b0c7a5ac/attachment.html>