[Eeglablist] ICA for rejecting EOG

[Klados Manousos]

Hello Allen,

If i have understood what you meen that's impossible. ICA makes different
decomposition matricies for different data...So there is no mean if the data
are from the same person. It's possible to perform ICA two times in a
specific multichannel EEG and get different result in the mean of the above
example :

x1 =[ a1 a2 a3][s1 s2 s3]^T= [a2  p*a1 a3][s2 s1/p s3]^T= a1s1+a2s2+a3s3

I know extended-ICA which EEGLAB use as default is very slow procedure but
you have to run again and again the algorithm for different datasets....you
can try fast ICA

Manos

2008/2/29, qiweijingwx <qiweijingwx at 126.com>:
>
>  Hello,
>
> I use ICA to reject EOG.But there are several EEG files generated by one
> subject.
> I want to apply the weight of ICA in one file to the others of one
> subject. How could I realize it?
> Thank you for any information!
>
> Allen
>
> 2008-02-29
>
> _______________________________________________
> 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
>



-- 
Klados Manousos
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20080229/4a72a874/attachment.html>