Skip to main content
SpringerLink
Log in

A New Ensemble Diversity Measure Applied to Thinning Ensembles

  • Conference paper
  • First Online:
Multiple Classifier Systems (MCS 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2709))

Included in the following conference series:

Abstract

We introduce a new way of describing the diversity of an ensemble of classifiers, the Percentage Correct Diversity Measure, and compare it against existing methods. We then introduce two new methods for removing classifiers from an ensemble based on diversity calculations. Empirical results for twelve datasets from the UC Irvine repository show that diversity is generally modeled by our measure and ensembles can be made smaller without loss in accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dietterich T., Ensemble methods in machine learning, Proceedings of the First International Workshop on Multiple Classifier Systems, pp. 1–15, 2000.

    Google Scholar 

  2. Breiman L., Bagging predictors, Machine Learning, Volume 24, No. 2, pp. 123–140, 1996.

    MATH  MathSciNet  Google Scholar 

  3. Breiman L., Pasting small votes for classification in large databases and on-line, Machine Learning, Volume 36, No. 1–2, pp. 85–103, 1999.

    Article  Google Scholar 

  4. Dietterich T., An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization, Machine Learning, Volume 40, No. 2, pp. 139–158, 2000.

    Article  Google Scholar 

  5. Breiman L., Random Forests, Machine Learning, Volume 45, No. 1, pp. 5–32, 2001.

    Article  MATH  Google Scholar 

  6. Freund Y. and Schapire R.E., Experiments with a new boosting algorithm, Proc. 13th International Conference on Machine Learning, pp 148–156, 1996.

    Google Scholar 

  7. Kuncheva L.I., Whitaker C.J., Measures of diversity in classifier ensembles, Machine Learning, Volume 51, pp. 181–207, 2003.

    Article  MATH  Google Scholar 

  8. Hansen L. and Salamon P., Neural network ensembles, IEEE Transactions on PAMI, 1990, V. 12, No. 10, pp. 993–1001.

    Google Scholar 

  9. Giacinto G. and Roli F., An approach to automatic design of multiple classifier systems, Pattern Recognition Letters, v. 22, pp. 25–33, 2001.

    Article  MATH  Google Scholar 

  10. Latinne P., Debeir O., and Decaestecker C., Limiting the number of trees in random forests, Second International Workshop on Multiple Classifier Systems, pp. 178–187, 2001.

    Google Scholar 

  11. Kuncheva L., Whitaker C., Shipp C., and Duin R., Is independence good for combining classifiers?, 15th International Conference on Pattern Recognition, pp. 168–171, 2000.

    Google Scholar 

  12. Merz C.J. and Murphy P.M., UCI Repository of Machine Learning Databases, Univ. of CA., Dept. of CIS, Irvine, CA., http://www.ics.uci.edu/~mlearn/MLRepository.html

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, University of South Florida, 4202 E. Fowler Ave, Tampa, Florida, 33620, USA

    Robert E. Banfield & Lawrence O. Hall

  2. Department of Computer Science and Engineering, University of Notre Dame, 384 Fitzpatrich Hall, Notre Dame, IN, 46556, USA

    Kevin W. Bowyer

  3. Biosystems Research Department, Sandia National Labs, PO Box 969, MS 9951, Livermore, CA, 94551-0969, USA

    W. Philip Kegelmeyer

Authors
  1. Robert E. Banfield
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lawrence O. Hall
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kevin W. Bowyer
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. W. Philip Kegelmeyer
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, Surrey, GU2 7XH, UK

    Terry Windeatt

  2. Dept. of Electrical and Electronic Engineering, University of Cagliari, Piazza D’Ami, 09123, Cagliari, Italy

    Fabio Roli

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Banfield, R.E., Hall, L.O., Bowyer, K.W., Kegelmeyer, W.P. (2003). A New Ensemble Diversity Measure Applied to Thinning Ensembles. In: Windeatt, T., Roli, F. (eds) Multiple Classifier Systems. MCS 2003. Lecture Notes in Computer Science, vol 2709. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44938-8_31

Download citation

  • DOI: https://doi.org/10.1007/3-540-44938-8_31

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40369-2

  • Online ISBN: 978-3-540-44938-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation