<div dir="ltr"><div><div>Dear Norbert,<br><br></div>The reason the ICA gives different results from run to run is, that it uses a random sampling. You can simply reset the seed of the random generator to get equal ICs on the same signal.<br><br></div>You can read more about selecting ICA components (for artifact rejection) here: <a href="http://www.nbtwiki.net/doku.php?id=tutorial:compute_independent_component_analysis#.VIeMEabEht0">http://www.nbtwiki.net/doku.php?id=tutorial:compute_independent_component_analysis#.VIeMEabEht0</a><br><div><div><div><div><div class="gmail_extra"><br clear="all"><div><div class="gmail_signature"><div dir="ltr">Best wishes,<br>Simon-Shlomo Poil, Dr.<br>LinkedIn profile: <a href="http://ch.linkedin.com/in/simonshlomopoil/" target="_blank">http://ch.linkedin.com/in/simonshlomopoil/</a><br><br></div></div></div>
<br><div class="gmail_quote">2014-12-09 14:46 GMT+01:00 Norbert Franke <span dir="ltr"><<a href="mailto:nfranke@uni-bonn.de" target="_blank">nfranke@uni-bonn.de</a>></span>:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Dear Collegues,<br>
<br>
I have a question about reliability.<br>
<br>
Fiorenzo Artoni has sent me his article:<br>
<br>
<a href="http://www.sciencedirect.com/science/article/pii/S1053811914007526" target="_blank">http://www.sciencedirect.com/science/article/pii/S1053811914007526</a><br>
<br>
When I repeat an ICA run, the result differs.<br>
<br>
My question to the developers of EEGLAB is: Fiorenzo<br>
Artori talked about introducing a RELICA toolbox in<br>
EEGLAB. When? Will it be a plugin or an additional tool?<br>
<br>
And a question to the collegues: What do You do when the<br>
results differ after simply repeating an ICA run? If You<br>
try to delete a component after the first run, it would be<br>
another after the next run. How can You decide which<br>
component has to be deleted? How much variation is<br>
acceptable? What do You do when a 2d image of a component<br>
is exactly the same but the polarity is inverted?<br>
<br>
I am courious to Your experience, it is important for me.<br>
<br>
Yours,<br>
<br>
Norbert Franke<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<a href="mailto:nfranke@uni-bonn.de">nfranke@uni-bonn.de</a><br>
Praxis: <a href="tel:0049%20%280%29228%20-%20364663" value="+49228364663">0049 (0)228 - 364663</a><br>
_______________________________________________<br>
Eeglablist page: <a href="http://sccn.ucsd.edu/eeglab/eeglabmail.html" target="_blank">http://sccn.ucsd.edu/eeglab/eeglabmail.html</a><br>
To unsubscribe, send an empty email to <a href="mailto:eeglablist-unsubscribe@sccn.ucsd.edu">eeglablist-unsubscribe@sccn.ucsd.edu</a><br>
For digest mode, send an email with the subject "set digest mime" to <a href="mailto:eeglablist-request@sccn.ucsd.edu">eeglablist-request@sccn.ucsd.edu</a><br>
</blockquote></div><br></div></div></div></div></div></div>