Bagging and Boosting for the Nearest Mean Classifier: Effects of Sample Size on Diversity and Accuracy

M Skurichina, LI Kuncheva, RPW Duin

    Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

    35 Citations (Scopus)


    In combining classifiers, it is believed that diverse ensembles perform better than non-diverse ones. In order to test this hypothesis, we study the accuracy and diversity of ensembles obtained in bagging and boosting applied to the nearest mean classifier. In our simulation study we consider two diversity measures: the statistic and the disagreement measure. The experiments, carried out on four data sets have shown that both diversity and the accuracy of the ensembles depend on the training sample size. With exception of very small training sample sizes, both bagging and boosting are more useful when ensembles consist of diverse classifiers. However, in boosting the relationship between diversity and the efficiency of ensembles is much stronger than in bagging.
    Original languageUndefined/Unknown
    Title of host publicationMultiple Classifier Systems, Proceedings
    EditorsF Roli, J Kittler
    Place of PublicationBerlin
    Number of pages10
    ISBN (Print)3-540-43818-1
    Publication statusPublished - 2002
    EventThird International Workshop MCS 2002 (Cagliari, Italy) - Berlin
    Duration: 24 Jun 200226 Jun 2002

    Publication series

    PublisherSpringer Verlag
    NameLecture Notes in Computer Science
    ISSN (Print)0302-9743


    ConferenceThird International Workshop MCS 2002 (Cagliari, Italy)

    Bibliographical note

    ISSN 0302-9743, phpub 16


    • conference contrib. refereed
    • ZX CWTS JFIS < 1.00

    Cite this