Re: Data mining with Rough Sets

Frank Hoffmann (fhoffman@cs.berkeley.edu)
Fri, 27 Aug 1999 11:53:09 +0200 (MET DST)

*********************************************************************
Berkeley Initiative in Soft Computing (BISC)
*********************************************************************
----- Forwarded message from T.Y. Lin -----

From: "T.Y. Lin" <tylin@mathcs.sjsu.edu>
Subject: Re: Data mining with Rough Sets
Date: Thu, 26 Aug 1999 10:26:54 -0700 (PDT)

=====
Dear Dante

1. N. Cercone and I edited a book called RS and DM by Kluwer Academic, 1997
which is based on a workshop "Rough Sets and Database Mining"
organized by myself at 1995 ACM CSC Conference.

2. There is a software commerically available in Canada called REDUCT
that applies RS idea to do data mining

3. I must say that RS is not exactly Data Mining.
It is more of Data Reduction.

Roughly,
Suppose we are given a relation(to be precise a relation instance).
If we name some attributes(such as symptoms in a medical database)
as conditional attributes, and some attributes(such as diseases)
as decision attributes.
The collection of data in such attributes forms a view instance.
RS people call it decision table.

4. If you think of Decision Table as a set of "if-then-rule"
the Rough Set theory provides you
a minimal set of "simplest" if-then-rules .

Such a minimal set is called a REDUCT (may have many recucts)

You can think of this REDUCT as
a set of Rules "mined from the given relation".

Please note that REDUCT and DECISION Table is logically equivalent.

5. One can "fuzzify" the situation by allowing some exceptions
(That is Ziarko's Variable precision Model or
My presentation
at EXPO 93 that held at Sanata Clara
using Fuzzy set theroy)

6. The fuzzified versions are very simliar to Association Rules

In this sense RS is a Data Mining tool, but RS has its own life.

Sincerely Yours

T. Y. Lin

===========================================================
T. Y. Lin (Tsau Young) Ph. D. Yale University
Professor of Computer Science
Department of Mathematics and Computer Science
San Jose State University
The Metropolitan University of Silicon Valley

Postal Address; 129S 10th St, San Jose, California 95192-0103 USA
Tel: 408-924-5121, Fax: 408-924-5080
e-mail: tylin@cs.sjsu.edu, tylin@cs.berkeley.edu
http://www.mathcs.sjsu.edu/faculty/tylin; http://www.mathcs.sjsu.edu/GrC

===========================================================

----- End of forwarded message from T.Y. Lin -----

-- 
---------------------------------------------------------------------------
Frank Hoffmann                               UC Berkeley
Computer Science Division                    Department of EECS
Email: fhoffman@cs.berkeley.edu              phone: 1-510-642-8282
URL: http://http.cs.berkeley.edu/~fhoffman   fax:  1-510-642-5775
---------------------------------------------------------------------------
If you ever want to remove yourself from this mailing list,
you can send mail to <Majordomo@EECS.Berkeley.EDU> with the following
command in the body of your email message:
unsubscribe bisc-group
or from another account,
unsubscribe bisc-group <your_email_adress>
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Do NOT send unsubscribe requests to bisc-group@cs.berkeley.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