Re: Q. distinction between 'Tall' and 'Tallest' ?


Subject: Re: Q. distinction between 'Tall' and 'Tallest' ?
young@ncsu.edu
Date: Mon Jul 31 2000 - 21:49:35 MET DST


Jeff,
Consider that the concepts underlying the definition of "tall", "average"
and "short" (for example) map to fuzzy sets. This allows you to build an
application and take into account the relative heights within different
populations by changing out the underlying fuzzy sets without altering the
reasoning logic. Using this approach, you could do context-based reasoning
using McCarthy and Buvac's work in formalizing context-based reasoning (go
to McCarthy's website at Stanford University). An example of using this in
fuzzy reasoning can be found in the paper "A Distributed Fuzzy Constraint
Satisfaction System with Context-based Reasoning" by Ress & Young in the
In. J. of Human-Computer Studies, special issue on context-based reasoning
(1998), vol. 48, pp. 393-407.
Hope this helps,
R. Young

At 06:06 PM 7/31/2000 +0200, you wrote:
>Hi,
>
>The standard membership function for the ubiquitous 'Tall' takes no
>account of relative heights and the popululation size. Is there a
>standard solution for this type of problem ?
>
>E.G.
>
>m 1
> ^
> xb
>
> xa
> 0
>
> height >
>
>so a, and b give their own measures irrespective of their 'relative' heights
>
>But, say xa is 1,000 people all with very similar ht then xb is
>'exceptionally tall',
>or whatever as measured relative to the population - get it ?
>
>Any ideas of how to handle this 'relative' type domain (I'm no expert).
>Of course I suppose it could be viewed as the combination of several more
>fundamental
>domains taking some sort of account of variance, st dev and the like.
>
>Any (explicit) 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

=========================================================
Dr. Robert E. Young
Professor of Industrial Engineering
Department of Industrial Engineering, campus box 7906
North Carolina State University
Raleigh, NC 27695-7906 USA
personal site: www.ie.ncsu.edu/young
research site: www.ie.ncsu.edu/wisdem
Phone: [+1] 919/515-7201
FAX: [+1] 919/515-5281
email: young@ncsu.edu
=========================================================

############################################################################
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 : Mon Jul 31 2000 - 22:04:10 MET DST