[Eeglablist] Feature extraction using activation matrix

[Makoto Miyakoshi]

Dear VAdlamani,

> 1. After multiplying icaweight and icasphere we were told to remove mean
of the raw EEG data to get activation matrix .. but there is already a
EEG.icaact by default . Which one do we use ? The default one or do we
compute the multiplication and subtraction explicitly??

They should be the same. To remove mean, EEG.data (/icaact) = EEG.data
(/icaact) - mean(EEG.data (/icaact),2);

> 2. features that were used are mean,power and energy of the activation
matrix . How do we compute these features for an activation matrix ??

I don't know this, sorry.

Makoto

On Tue, Aug 9, 2016 at 3:10 AM, Vadlamani Samhitha <
vadlamani.samhitha at gmail.com> wrote:

> Hello list .we were trying to replicate a paper on motor imagery and I've
> got the following queries regarding feature extraction of eeglab :
> 1. After multiplying icaweight and icasphere we were told to remove mean
> of the raw EEG data to get activation matrix .. but there is already a
> EEG.icaact by default . Which one do we use ? The default one or do we
> compute the multiplication and subtraction explicitly??
> 2. features that were used are mean,power and energy of the activation
> matrix . How do we compute these features for an activation matrix ??
> Thank you.
>
> _______________________________________________
> 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/20160818/2263ee81/attachment.html>