suitable inference for classification with fuzzy rule ensembles?

From: C. Setzkorn (C.Setzkorn@csc.liv.ac.uk)
Date: Mon Oct 08 2001 - 12:21:52 MET DST

  • Next message: Vijay Patil: "ANFIS + Reinforcement Learning"

    Dear all,

    I am using evolutionary algorithms to infer fuzzy rule prediction
    systems from data. There are a number of questions, which I have been
    trying to answer for quite a while now. Hopefully I will get some
    feedback from you.

    Lets say we predict a dichotomous attribute. Using Mamdami inference we
    would obtain values between zero and one for each case presented to a
    rules system. By imposing decision thresholds we could decide to which
    class a case belongs (similar to logistic regression). We would thus be
    able to compute accuracy measurements for a particular fuzzy rule
    system. Accuracy measurements could be sensitivity, specificity etc.

    Does the Mamdami inference mechanism actually make sense for the task of

    classification?

    Do the ‘evolved’ rules within a rule system actually mirror patterns
    within a presented data set? (Since we treat the rule system more or
    less like a black box.)

    Does Mamdami inference presuppose that the domain of the attribute to be

    controlled/predicted is actually continuous?

    Are there more appropriated inference mechanisms for the task of
    classification, especially when I try to predict categorical attributes
    (not necessarily dichotomous)?

    Are there better ways to classify a presented case rather than deploying

    particular inference mechanisms?

    I am looking forward to any replies that may be of assistance. Many
    thanks for your help.

    All the best

    Chris

    --
    All the best
    Chris
    

    ***********************************************************

    Mr. C. Setzkorn (PhD Student) Department of Computer Science University of Liverpool Chadwick Building, room G45a Peach Street, Liverpool L69 7ZF United Kingdom

    Email: chris@csc.liv.ac.uk Phone: 0044 151 794 3694 Fax: 0044 151 794 3715 homepage: http://www.csc.liv.ac.uk/~chris

    ############################################################################ 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 2b30 : Mon Oct 08 2001 - 12:41:45 MET DST