[pymvpa] Spatiotemporal Feature Selection

Roberto Guidotti robbenson18 at gmail.com
Mon Jul 23 13:55:51 UTC 2012


Thank you for the responses!

It doesn't sound wrong ;-) However, I'm also not 100% sure want kind of
> feature selection you are aiming at. Do you want to select features that
> vary to a certain degress within an event, and come from the same voxel?
>

Exactly, I would like to have a feature selection based on an event, that
could be like the GLM-approach.



> There are many possible strategy (e.g. repeated random selection, ...).
> But, again, more information on your dataset would be helpful. You are
> saying that you have 100 volumes per that (per run) that you reduce into
> a single sample? Why is that?
>

My task is a meditation task thus I have few runs with many volumes per
runs and I would like to see the informations carried by the task from a
temporal point of view, so I have a huge amount of features vs very few
runs (six), do you think that repeated random selection could be useful?

Thank you very much,
RG
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20120723/3a21c3c6/attachment.html>


More information about the Pkg-ExpPsy-PyMVPA mailing list