Re: References on the 'shape' of fuzzy sets?

Frederick W. Hegge (fhegge@paltech.com)
Mon, 5 Aug 1996 11:15:05 +0200


Have reached much the same conclusion myself in the case of iterative
fuzzy applications. If you are constantly updating a control function,
the robustness provided by firing a set of rules in parallel gives you a
smooth correction capability. You would be hard pressed to demonstrate a
difference between a trapezoidal and sigmoidal function. In fuzzy
consultation systems where you are trying to model human linguistic
variables and iterative correction is not practiced or perhaps not
possible, then, the shape of set functions may be critical. There is well
over 100 years of research in determining the shape of human fuzzy sets,
it is called psychophysics.
Fred

> ma@informatik.uni-kiel.de (Martin Ameskamp) wrote in article
<4tsgen$1h8@gutemine.informatik.uni-kiel.de>...
>
> Hi there,
>
> after reading various papers and books on fuzzy logic control, listening
to
> conference presentations, and making the odd experiment myself, I've
come to
> the conclusion that the exact 'shape' of a fuzzy set is much less
important .....