[FieldTrip] Clustering algorithm used in sourcestatistics (montecarlo)

Michał Komorowski michak at is.umk.pl
Tue Feb 28 11:39:06 CET 2017


Hey,

Not exactly.
Function 'clusterstat' takes advantage of 'spm_bwlabel' function to
clusterize data, then it computes a cluster-level statistic.

I want to know what algorithm is used: k-means? DBSCAN? Other ?

Thank you for your fast reply.

2017-02-28 11:13 GMT+01:00 Maité Crespo García <maity_winky at yahoo.es>:

> Hi Michal,
>
> The 'ft_statistics_montecarlo' uses as default the maxsum statistic and
> the algorithms for clustering are in the 'clusterstat' function, inside the
> private folder. Is that what you mean?
>
> Best wishes,
> Maité
>
>
> El Martes 28 de febrero de 2017 1:40, Michał Komorowski <michak at is.umk.pl>
> escribió:
>
>
>
>
> Dear Fieldtrippers,
>
> Does anybody know what clustering algorithm is used
> in ft_statistics_montecarlo (ft_sourcestatistics with cfg.correctm =
> 'cluster') when analysing data from ft_sourceanalysis?
>
> It seems like spm_bwlabel function is used, but I have not found an open
> source.
>
> Any help would be greatly appreciated.
>
> --
> Michał Komorowski, MSc
> Nicolaus Copernicus University in Toruń
> Faculty of Physics, Astronomy and Informatics
> Department of Informatics
>
> _______________________________________________
> fieldtrip mailing list
> fieldtrip at donders.ru.nl
> https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
>
>
> _______________________________________________
> fieldtrip mailing list
> fieldtrip at donders.ru.nl
> https://mailman.science.ru.nl/mailman/listinfo/fieldtrip
>



-- 
Michał Komorowski, MSc
Nicolaus Copernicus University in Toruń
Faculty of Physics, Astronomy and Informatics
Department of Informatics
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.science.ru.nl/pipermail/fieldtrip/attachments/20170228/58b5ff0c/attachment.html>


More information about the fieldtrip mailing list