Deakin University
Browse

File(s) not publicly available

An algorithm for the optimization of multiple classifiers in data mining based on graphs

conference contribution
posted on 2009-11-01, 00:00 authored by A Kelarev, J Ryan, John YearwoodJohn Yearwood
This article develops an efficient combinatorial algorithm based on labeled directed graphs and motivated by applications in data mining for designing multiple classifiers. Our method originates from the standard approach described in [37]. It defines a representation of a multiclass classifier in terms of several binary classifiers. We are using labeled graphs to introduce additional structure on the classifier. Representations of this sort are known to have serious advantages. An important property of these representations is their ability to correct errors of individual binary classifiers and produce correct combined output. For every representation like this we develop a combinatorial algorithm with quadratic running time to compute the largest number of errors of individual binary classifiers which can be corrected by the combined multiple classifier. In addition, we consider the question of optimizing the classifiers of this type and find all optimal representations for these multiple classifiers.

History

Volume

71

Pagination

65-85

Location

Newcastle, N.S.W.

Start date

2007-11-05

End date

2007-11-09

ISSN

0835-3026

Publication classification

EN.1 Other conference paper

Title of proceedings

18th International Workshop on Combinatorial Algorithms

Publisher

College Publications

Place of publication

London, Eng.

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC