Re: FUZZY LOGIC (Wang & Mendel algorithm)

WSiler (wsiler@aol.com)
Wed, 8 Jul 1998 04:52:04 +0200 (MET DST)

>You might find some help in:
>
>http://www.infm.ulst.ac.uk/~jgc/papers/fz1094.a but be careful to avoid
>my attempts to link fuzzy rule-bases with classical propositional logic
>-- it's not all that helpful, is probably wrong, and the diagrams for,
>e.g., relations, are impossible to read.
>
>
I have scanned your Web page with great interest, and find it quite
informative. Good job.

I do have one complaint about your Chapter 5 on classification. Fuzzy
classification has been my main interest for over 12 years now. You are quite
correct in pointing out that in problems of classification we are dealing with
a discrete fuzzy set of possible classifications. However, it is quite
unnecessary for your labels to be numeric. A typical fuzzy set of
classifications for us is: fuzzy set Diagnosis, with members {major depression,
Manic-depressive psychosis, paranoid disorder, schizophrenia disorganized type,
..}. If your expert system shell permits input and output of discrete fuzzy
sets, as it should if it is to deal with classification problems, then the
output could be (as it is in the diagnosis problem) the grades of membership of
the various diagnoses in the fuzzy set Diagnosis.

My Web page is nowhere near as complete as yours on the math of fuzzy systems,
but it does go into more detail on dealing with problems of classifications,
and in doing approximate comparisons corresponding to the conventional Boolean
operators <, <=, = and so forth. You might find it interesting. The Web site is

http://users.aol.com/wsiler/.

Because of the great importance of discrete fuzzy sets in classification work,
we do NOT assume (as it is done in control) that a fuzzy set is a membership
function or a fuzzy number.

Thanks for the pointer to your very interesting document.

William Siler

############################################################################
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