Re: Getting output values to the "edges"


Subject: Re: Getting output values to the "edges"
From: Pramit Sarma (pramits@vsnl.com)
Date: Tue Sep 05 2000 - 12:06:01 MET DST


Clearly what you have at least resembles a TISO fuzzy logic controller (FLC)
and of the Mamdani type with both input/antecedent & output/consequent
nominally fuzzy. Given the basal information provided, clearly rescaling,
or equivalently altering the non-unity scaling gain at the output would
force such a change.

It appears that there is very significant missing information in the problem
statement - ie. the Fuzzy Rule-Base (FRB). For adequate full-span
inferencing by the FLC, one must have a sufficiently well-defined FRB, which
is the kernel of the entire FLC. Assuming the Fuzzy Linguistic Variables
(FLV) are themselves full-spanned [if they are not then it is essential
they be], the solution remains in heuristic or automatic adjustment of the
rule-set in the FRB.

Pramit

-----Original Message-----
From: Peter Immarco <me@nospam.net>
To: Multiple recipients of list <fuzzy-mail@dbai.tuwien.ac.at>
Date: Sunday, September 03, 2000 10:15 AM
Subject: Getting output values to the "edges"

>Hello, I have a fuzzy logic system that take two inputs, and maps them
>to a single output. The range of the output variable is 0 - 1, however,
>the effective range is 0.2 - 0.8. The problem is trying to achieve
>values at the limits of the output range, because the centroid mechanism
>takes the centroid of a fuzzy set that is near the limit of the range,
>which naturally "pulls" it away from the edge. I thought of making the
>fuzzy sets at the limit of the output range singleton sets, but won't
>they lose badly then in a centroid defuzzification with a neighboring
>larger fuzzy set?
>
>Of course I could simply rescale the range to 0 - 1, but I am wondering
>if there is a "standard" technique for achieving what I want to achieve
>here. Any ideas?
>
>Thanks.
>
>
>
>###########################################################################
#
>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
>
>

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



This archive was generated by hypermail 2b25 : Tue Sep 05 2000 - 12:21:49 MET DST