nick Wrote:
-------------------------------------------------------
> kentman234 Wrote:
> --------------------------------------------------
>
> > Next, I need to choose a part of
> > the ICs (15 for example) for training and to
> test
> > the rest.
>
> I don't understand the logic here. It seems that
> if you decompose your data in components that are
> 'independent' that means that data in one
> component have no (or little, if they are not
> truly independent) information on the other
> components, and thus I don't see how you would be
> able to classify anything.
>

Why not! Many studies have been done on how ICA can classify fMRI data. Each component indicates one of the two conditions and has characteristics different than that of the component of the other condition. In this sense we need to know how the components can be classified, when we know the general metric with certain parameters used to define each condition.