Skip to main content
Springer Nature Link
Log in

The Role of Early Stopping and Population Size in XCS for Intrusion Detection

  • Conference paper
Simulated Evolution and Learning (SEAL 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4247))

Included in the following conference series:

Abstract

Evolutionary Learning Classifier Systems (LCSs) are rule based systems that have been used effectively in concept learning. XCS is a prominent LCS that uses genetic algorithms and reinforcement learning techniques. In traditional machine learning (ML), early stopping has been investigated extensively to the extent that it is now a default mechanism in many systems. However, there has been a belief that EC methods are more resilient to overfitting. Therefore, this topic is under-investigated in the evolutionary computation literature and has not been investigated in LCS. In this paper, we show that it is necessary to stop evolution in LCS using a stopping criteria other than a maximum number of generations and that evolution may suffer from overfitting similar to other ML methods.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Bacardit, J., Butz, M.V.: Data Mining in Learning Classifier Systems: Comparing XCS with GAssist. Illinois Genetic Algorithms Laboratory, University of Illinois at Urbana-Champaign, IlliGAL Report No. 2004030 (June 2004)

    Google Scholar 

  2. Bernadó, E., Llorà, X., Garrell, J.M.: XCS and GALE: a comparative study of two learning classifier systems with six other learning algorithms on classification tasks. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2001. LNCS (LNAI), vol. 2321, pp. 337–341. Springer, Heidelberg (2002)

    Google Scholar 

  3. Elkan, C.: Results of the kdd 1999 classifier learning. SIGKDD Explor. Newsl. 1(2), 63–64 (2000)

    Article  Google Scholar 

  4. Greenyer, A.: CoIL Challenge 2000. The use of a learning classifier system JXCS. Technical Report LIACS Technical Report 2000-09, Sentient Machine Research, Amsterdam and Leiden Institute of Advanced Computer Science, Leiden (June 22, 2000)

    Google Scholar 

  5. Hettich, S., Bay, S.D.: The UCI KDD Archive (1999), http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html

  6. N. S. Inc. Online available at http://www.nutechsolutions.com/ (2003)

  7. Kovacs, T., Kerber, M.: High classification accuracy does not imply effective genetic search. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3102, Springer, Heidelberg (2004)

    Google Scholar 

  8. Wilson, S.W.: Get Real! XCS with Continuous-Valued Inputs. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 1999. LNCS (LNAI), vol. 1813, pp. 209–219. Springer, Heidelberg (2000)

    Chapter  Google Scholar 

  9. Shafi, K., Abbass, H., Zhu, W.: The role of early stopping and population size in XCS for intrusion detection. Technical Report TR-ALAR-200604006, Defence and Security Applications Research Centre, University of New South Wales ADFA, Canberra, Australia (2006)

    Google Scholar 

  10. Wilson, S.W.: Classifier fitness based on accuracy. Evolutionary Computation 3(2), 149–175 (1995)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Defence and Security Applications Research Centre, Univ. of New South Wales @ ADFA, Canberra, ACT, 2600, Australia

    Kamran Shafi, Hussein A. Abbass & Weiping Zhu

Authors
  1. Kamran Shafi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hussein A. Abbass
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weiping Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Industrial Engineering and Management, Cheng Shiu University, Kaohsiung County Taiwan, ROC

    Tzai-Der Wang

  2. School of Computer Science and information Technology, RMIT University, VIC 3001, Melbourne, Australia

    Xiaodong Li

  3. AI-ECON Research Center, Department of Economics, National Chengchi University, 11623, Taipei, Taiwan

    Shu-Heng Chen

  4. Department of Computer Science and Technology, University of Sci. & Tech. of China, 230026, Hefei, Anhui, P.R. China

    Xufa Wang

  5. School of Information Technology and Electrical Engineering, University of New South Wales, Australian Defence Force Academy, Canberra, Australia

    Hussein Abbass

  6. The Univertity of Tokyo, Japan

    Hitoshi Iba

  7. Department of Computer, University of Science and Technology of China, 230027, Hefei, China

    Guo-Liang Chen

  8. University of Birmingham, Birmingham, UK

    Xin Yao

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Shafi, K., Abbass, H.A., Zhu, W. (2006). The Role of Early Stopping and Population Size in XCS for Intrusion Detection. In: Wang, TD., et al. Simulated Evolution and Learning. SEAL 2006. Lecture Notes in Computer Science, vol 4247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11903697_7

Download citation

  • DOI: https://doi.org/10.1007/11903697_7

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-47331-2

  • Online ISBN: 978-3-540-47332-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics