[FieldTrip] Support Vector Machine (SVM) for classification of EEG data

["Jörn M. Horschig"]

Dear Alan,

you should probably start off with going through our tutorials:
http://fieldtrip.fcdonders.nl/tutorial/

And for you especially 
http://fieldtrip.fcdonders.nl/tutorial/multivariateanalysis

There are lots of different approaches for feature extraction or reduce 
feature space, but what works wors best for your data is something you 
have to test yourself. When you've read the tutorials you probably got a 
pretty got overview of what is possible in FieldTrip and that you can 
easily test what you asked for yourself without having others send you 
their code (you just have to replace a few keywords from the tutorial to 
test a different method). If you have more specific questions, feel free 
to ask again.

Best,
Jörn


On 2/15/2013 1:58 AM, Leggitt, Alan wrote:
> Hello,
>
> I'm new to field trip and I am interested in using a support vector 
> machine to classify EEG data. I see that field trip has svm code 
> through the DLMT toolbox. Has anyone had any experience with this and 
> would be willing to share their code for adapting EEG data to use as 
> inputs to the svm class? My current understanding is that others use 
> ICA to extract features to use in the svm. Are there other techniques 
> for feature extraction?
>
> Thanks very much.
>
> Regards,
> Alan
>
>
> _______________________________________________
> fieldtrip mailing list
> fieldtrip at donders.ru.nl
> http://mailman.science.ru.nl/mailman/listinfo/fieldtrip


-- 
Jörn M. Horschig
PhD Student
Donders Institute for Brain, Cognition and Behaviour
Centre for Cognitive Neuroimaging
Radboud University Nijmegen
Neuronal Oscillations Group
FieldTrip Development Team

P.O. Box 9101
NL-6500 HB Nijmegen
The Netherlands

Contact:
E-Mail: jm.horschig at donders.ru.nl
Tel:    +31-(0)24-36-68493
Web: http://www.ru.nl/donders

Visiting address:
Trigon, room 2.30
Kapittelweg 29
NL-6525 EN Nijmegen
The Netherlands

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20130215/178a0fa0/attachment-0002.html>