Fuzzy logic & analog forecasting


Subject: Fuzzy logic & analog forecasting
forecaster@my-deja.com
Date: Fri Apr 14 2000 - 18:13:55 MET DST


Who has used fuzzy logic for analog forecasting? Fuzzy logic has often
been used for cluster detection, but who has exploited the existence of
spatiotemporal clusters in natural phenomena for analog forecasting?
And how?

Analog forecasting bases forecasts on the outcomes of analogous past
situations, or cases. Analog forecasting is a basic technique used in
weather prediction. For weather prediction, present and past cases are
described by spatiotemporal vectors, and forecasts for the present case
are based on the outcome of similar past cases. For the technique to
work, there are two requirements: 1) recorded analogous past cases, and
2) an effective similarity-measuring function. Recorded analogous past
cases large archives are contained in large archives of weather
observations (I suppose other application areas have similar rich
archives). An effective similarity-measuring function can be designed
using fuzzy methods. For example, the similarity of two vectors is
determined by sim(A, B) = min((A1^B1), (A2^B2), ... , (An^Bn)).
Similarity of temporal vectors is a simple extension of sim( ).

I have found a fuzzy k-nearest neighbor technique to be unusually
effective for weather prediction. The technique is described in the
paper: Hansen, B.K. (2000) Analog forecasting of ceiling and visibility
using fuzzy sets, Preprints of the 2nd Conference on Artificial
Intelligence, American Meteorological Society, 1-7. The paper is online
at http://chebucto.ns.ca/~bjarne/ams2000

Id like to learn about similar work.

Bjarne Hansen
School of Computer Science
Dalhousie University
Halifax, Canada

Sent via Deja.com http://www.deja.com/
Before you buy.

############################################################################
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 : Fri Apr 14 2000 - 18:45:19 MET DST