We should carefully evaluate what IDRISI has on
offer and then develop sth. better 
From what I have seen, there are some very useful
modules for handling uncertainty in IDRISI and
some rather questionable/experimental stuff.
What I admire most is there implementation of
Dempster-Shafer Theory of Evidence. I have been
spending a lot of time recently to try and implement
sth. just a bit more powerful than that. For raster
maps, the functionality is basically complete, but
I still need to add support for vector maps as
sources of evidence.
Yes, the idea is to create a suite of programs like r.le
and distribute them as a sort of extension the same style
ESRI ArcGIS does it, so that you can install the modules
into a running installation of GRASS and the code does
not have to be maintained in the orginal source tree.
This can be done with a little program I am developing at the
moment.
What exactly are your research interests? Maybe you could
contribute to the program documentation and create some
good example data sets.
----- Originalnachricht -----
Von: Doc Robinson <vbr@eratos.erin.utoronto.ca>
Datum: Donnerstag, 21. Juli 2005 5:05 pm
Betreff: [GRASS5] Evidential reasoning classifier
Benjamin,
are u suggesting developing modules along similar lines as those in
IDRISI? I would imagine it would be suite of programs like r.lelet me know if u need any advice/thoughts especially on the fuzzy sets
end of things. unfortunately at this time i am unable to offer
programming time ... I and my ugrad+grad students would USE such a
module if it existed and had the functionality required for some of
our problems.> From: benducke@compuserve.de
> Date: July 19, 2005 7:19:27 EDT (CA)
> To: Sajith VK <sajithvk@gmail.com>, grass5@grass.itc.it
> Subject: Re: [GRASS5] Evidential reasoning classifier
>
>
> That's interesting.
> I have been working on an implementation of Dempster
> Shafer Theory as well (albeit for purposes of spatial
> prediction). I am a big fan of it and pleased to see
> that others find it useful, as well.
>
> It seems to me that uncertainty management and decision
> support is something where GRASS 6 currently lacks in comparison
> with IDRISI. Things needed, that have been mentioned on this
> list before include neural networks, fuzzy logics and
> Bayes models.
>
> As you may know, if you have been reading this mailing
> list lately, I am also currently developing a program
> that allows to install extensions into a running version
> of GRASS 6 including menu entries, HTML docs and the
> modules themselves. That program is about 95% finished now.
> My own Dempster-Shafer modules are about 80% done.
>
> So maybe it would be about time to join forces and create
> a "Decision Support" extension that includes, DST, Bayes,
> fuzzy logics, NNs in one neat package along with good
> documentation on the mathematical background and practical
> uses?
>
> Benjamin--
Regards,
Doc--------------------------------------------------------------------
Vincent B. Robinson |
Department of Geography | E-Mail: doc.robinson@utoronto.ca
University of Toronto | Voice: (905)828-5299
at Mississauga | Fax: (905)828-5273
Mississauga, Ontario |
Canada L5L 1C6 |