[Eeglablist] Clustering / ICA sign ambiguity

[David Groppe]

Hi Ralf,
  I've dealt with ICA sign ambiguity a couple ways for clustering:

1. Only use clustering features that are independent of component sign.  
For example, localize each component with Dipfit and use the dipole 
location and orientation (I don't believe EEGLAB's clustering software can 
let you use dipole orientation as a cluster feature yet, but the info is 
there).  Component spectra is independent of sign.  And you can take the 
absolute value of ERPs.

2. Set the sign of each IC so that its maximal absolute topography weight 
is positive.  In my experience, most of the reliable, non-artifact ICs have a 
rather focal distribution with a clear maximum.  If that's the case for 
you, this strategy could also work.
   cheers,
     -David

dgroppe at cogsci.ucsd.edu



On Fri, 16 Feb 2007, Ralf Schmälzle wrote:

> Hi EEGLAB-users,
> currently I am testing the clustering-program and ran into a problem
> regarding the ICA-sign-ambiguity. I have learned (and found many examples)
> that the ICA algorithm has a sign ambiguity (because of the random starting
> parameters), that is the signs  of the IC-timecourse and
> scalp-projection-map are arbitrary in that only the product (=EEG.data) has
> fixed sign. This can be reached either by (ScalpMap*ICtimecourse) or by
> ((-1)*ScalpMap)*((-1)*ICtimecourse) since the (-1) cancels out. 
> It seems to me that this may cause a problem when it comes to clustering
> since there - according to my understanding of the clustering process - a
> sign ambiguity e.g. in the ComponentERP or CompScalpMap would cause
> corresponding Components to lie on opposite ends of the to-be-clustered
> dimension. At least when doing the grandaverage of a componentERP this
> information is essential, isn't it? 
> Is that correct and how could I deal with this? 
> In principle it should be allowed to flip the results (Map and TimeCourse)
> but how do I know in advance (before clustering) whether one special
> component must be flipped or not.
> 
> Many thanks, Ralf.
> ______________________________________________________
>  
> Ralf Schmaelzle
> Rheingasse 6
> 78462 Konstanz
> Germany
> Tel. +49 (0) 7531 367501
> Ralf_Schmaelzle at web.de
>  
>  o      o     o    o     o    <o     <o>    o>    o
> .|.    \|.   \|/   //    X     \      |    <|    <|> 
>  /\     >\   /<    >\   /<     >\    /<     >\   /< 
>  
> Ralf Schmaelzle
> Allgemeine Psychologie
> Universität Konstanz
> Fach D 36
> D-78457 Konstanz
> Germany
>  
> Raum: C 528
> Tel: +49 (0) 7531 88 2449
> Fax: +49 (0) 7531 88 2971
> Ralf.Schmaelzle at uni-konstanz.de
> www.uni-konstanz.de/psychologie/ag-schupp
> ______________________________________________________
> 
> 
> 
> _______________________________________________
> eeglablist mailing list eeglablist at sccn.ucsd.edu
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> 

--