Dear Mokoto,<br><br>Thank you for the interest. I'm not sure if I can enclose the plots here so I'm gonna use min and max values as a reconstruction criteria. <br>I have a data x (matrix size 4x1024; ranging <-<b>3.882;2,466</b>>)<br>
<br>When I apply following command line in matlab:<br><i>[icasig,A,W]=fastica(x,'numOfIC',<b>4</b>)</i><br>and when I reconstruct x with the formula:<br><i>x4=A*icasig</i><br>I get x4 (matrix size 4x1024; ranging <-<b>3.882;2,466</b>>) which presents the exact plot as x.<br>
<br>
Now, when I apply following command line in matlab:<br><i>
[icasig2,A2,W2]=fastica(x,'numOfIC',<b>3</b>)</i><br>
and then I reconstruct x with:<br><i>
x3=A2*icasig2</i><br>
I get x3 (matrix size 4x1024; ranging <<b>-4.453;2,469</b>>) which presents far more noise plots then x.<br><br>I'm not sure whether I'm not doing something wrong. But if the algorithm works this way why is it so?<br>
<br>Best regards,<br>Ewa<br><br><div class="gmail_quote">On 10 May 2012 21:47, Makoto Miyakoshi <span dir="ltr"><<a href="mailto:mmiyakoshi@ucsd.edu" target="_blank">mmiyakoshi@ucsd.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Dear Ewa,<br>
<br>
What do you mean by 'imprecisely'? Or how did you now it is imprecise?<br>
Please tell us more detail.<br>
<br>
Makoto<br>
<br>
2012/5/10 Ewa Beldzik <<a href="mailto:ewa.beldzik@gmail.com">ewa.beldzik@gmail.com</a>>:<br>
<div><div class="h5">> Dear all,<br>
><br>
> When applying fastICA algorithm in Matlab to a data consisting of 4 signals,<br>
> I have noticed that only when I choose 4 IC to be estimated, the formula<br>
> A*icasig =X actually works. After choosing 2 or 3 IC the data (X) is<br>
> reconstructed imprecisely.<br>
> Could you explain why? I wish to understand the methods fully.<br>
><br>
> Thank you in advance,<br>
> Ewa<br>
> PhD student from Cracow<br>
><br>
</div></div>> _______________________________________________<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<br>
> <a href="mailto:eeglablist-request@sccn.ucsd.edu">eeglablist-request@sccn.ucsd.edu</a><br>
<span class="HOEnZb"><font color="#888888"><br>
<br>
<br>
--<br>
Makoto Miyakoshi<br>
JSPS Postdoctral Fellow for Research Abroad<br>
Swartz Center for Computational Neuroscience<br>
Institute for Neural Computation, University of California San Diego<br>
</font></span></blockquote></div><br>