Re: Defuzzification - center of gravity

J. van den Berg (jvandenberg@few.eur.nl)
Thu, 15 Apr 1999 15:57:00 +0200 (MET DST)

This is a multi-part message in MIME format.
--------------C9AA1CCB5019578F6A11DD73
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit

Roland Osen wrote:

> I'm writing my dissertation work (or however that is called in english)
> about a fuzzy logic related topic and have a special question about the
> center-of-gravity method for the defuzzification.
> The influence of an area is big when its aera is big. The area is big
> when it is high and wide. But the wideness represents the uncertainty of
> the value. My question is: Isn't it wrong that uncertain fuzzy sets have
> more influence and fuzzy sets with a more or less exact value have only
> very little influence to the result?
>

Yes, Roland, I think you are right when saying that this is wrong.
(We once noticed the same in a footnote of the paper "Represenation and learning
capabilities of Addfitive Fuzzy Systems by Dennis Ettes and myself: downloadable
from http://www.few.eur.nl/few/people/jvandenberg/publ/index.htm).

You can also find a note in Bart Kosko's book "Fuzzy Engineering" ch 3, fig 3.14,

where special weigts are given to the fuzzy rules in order to give 'more weight
to
smaller and thus more certain rules'.

Jan van den Berg

--------------C9AA1CCB5019578F6A11DD73
Content-Type: text/x-vcard; charset=us-ascii; name="vcard.vcf"
Content-Transfer-Encoding: 7bit
Content-Description: Card for Berg, Jan van den
Content-Disposition: attachment; filename="vcard.vcf"

begin: vcard
fn: Jan van den Berg
n: Berg;Jan van den
org: Erasmus University Rotterdam
adr: Dept. of Comp. Science, P.O. Box 1738, room H9-32;;;Rotterdam;;3000 DR;The Netherlands
email;internet: jvandenberg@few.eur.nl
title: dr. ir.
tel;work: +31 10 4081342
tel;fax: +31 10 4089167
tel;home: +31 10 4612695
x-mozilla-cpt: ;-1
x-mozilla-html: FALSE
version: 2.1
end: vcard

--------------C9AA1CCB5019578F6A11DD73--

############################################################################
This message was posted through the fuzzy mailing list.
(1) To subscribe to this mailing list, send a message body of
"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
(2) To unsubscribe from this mailing list, send a message body of
"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
to listproc@dbai.tuwien.ac.at
(3) To reach the human who maintains the list, send mail to
fuzzy-owner@dbai.tuwien.ac.at
(4) WWW access and other information on Fuzzy Sets and Logic see
http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html