Re: fuzzy clustering

From: christian (c.schulz@metafacts.de)
Date: Fri Nov 16 2001 - 23:16:03 MET

  • Next message: Phil Diamond: "Website for Linz 2002 Seminar is now up"

    Paolo,
    Perhaps you find interesting algorithm
    and functions in open source package R (Cran ) !

    http://www.r-project.org
    Here you find 2 packages , one is "cluster" which implement
    a fuzzy-clustering algorithm and the package "e1071" have some, too.

    It would be fine when we can discuss about cluster problems.
    My common problem is, what is the best strategy to cluster
    variables with different scales.

    At this time my stretegy is recode ordinal variables
    in binary variables and the ratio-scaled variables 1 do transform
    with z-transformation.

    >...and further i use fuzzy-clustering in a socila-science context,
    - my intention is to cluster (construct) lifestyles , but people
    have not 1 strong lifestyle ..........

    regards,christian

    Paolo Testi wrote:

    > Dear All,
    > during my M.A. thesis research i find an interesting problem
    > which i'd like to discuss because i don't know the possible solution.
    > The problem is that I have to cluster a datasets like this:
    >
    > A 1 1 1 1 0 0 0 2 2 2 0 0
    > B 0 0 0 2 0 0 0 1 1 1 1 2
    > C 1 1 1 0 0 0 1 1 1 1 0 3
    >
    > (Unfortunately the matrix is bigger than this!!)
    >
    > I found that the cityblovk distance give the best results to calculate
    > the distance between A and B but I don't know how I could modify the
    > fuzzy C-means Algorithm to make the correct clustering. Anyone have
    > got an idea?
    > But I found a paper [Bezdek, Hatharway] about NERF (Non Euclidean
    > Relational fuzzy clustering) but I have the same problem...Help!!!!
    >
    > Paolo
    >

    ############################################################################
    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 : Fri Nov 16 2001 - 23:17:51 MET