Advertisement

EFuNN Ensembles Construction Using a Clustering Method and a Coevolutionary Multi-objective Genetic Algorithm

  • Fernanda L. Minku
  • Teresa B. Ludermir
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4234)

Abstract

This paper presents the experiments which where made with the Clustering and Coevolution to Construct Neural Network Ensemble (CONE) approach on two classification problems and two time series prediction problems. This approach was used to create a particular type of Evolving Fuzzy Neural Network (EFuNN) ensemble and optimize its parameters using a Coevolutionary Multi-objective Genetic Algorithm. The results of the experiments reinforce some previous results which have shown that the approach is able to generate EFuNN ensembles with accuracy either better or equal to the accuracy of single EFuNNs generated without using coevolution. Besides, the execution time of CONE to generate EFuNN ensembles is lower than the execution time to produce single EFuNNs without coevolution.

Keywords

Execution Time Root Mean Square Error Test Pattern Fuzzy Neural Network Execution Time Average 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kasabov, N.: Evolving Connectionist Systems. Springer, Great Britain (2003)Google Scholar
  2. 2.
    Watts, M., Kasabov, N.: Dynamic optimisation of evolving connectionist system training parameters by pseudo-evolution strategy. In: CEC 2001, Seoul, vol. 2, pp. 1335–1342 (2001)Google Scholar
  3. 3.
    Watts, M., Kasabov, N.: Evolutionary optimisation of evolving connectionist systems. In: CEC 2002, Honolulu, Hawaii, vol. 1, pp. 606–610. IEEE Press, Los Alamitos (2002)Google Scholar
  4. 4.
    Kasabov, N., Song, Q., Nishikawa, I.: Evolutionary computation for dynamic parameter optimization of evolving connectionist systems for on-line prediction of time series with changing dynamics. In: IJCNN 2003, Oregon, vol. 1, pp. 438–443 (2003)Google Scholar
  5. 5.
    Minku, F.L., Ludermir, T.B.: Evolutionary strategies and genetic algorithms for dynamic parameter optimization of evolving fuzzy neural networks. In: CEC 2005, Edinburgh, Scotland, vol. 3, pp. 1951–1958 (2005)Google Scholar
  6. 6.
    Chandra, A., Yao, X.: Ensemble learning using multi-objective evolutionary algorithms. Journal of Mathematical Modelling and Algorithms (1) (2006)Google Scholar
  7. 7.
    Kasabov, N.: Ensembles of efunns: An architecture for a multimodule classifier. In: Proceedings of the International Conference on Fuzzy Systems, Australia, vol. 3, pp. 1573–1576 (2001)Google Scholar
  8. 8.
    Minku, F.L., Ludermir, T.B.: EFuNNs ensembles construction using a clustering method and a coevolutionary genetic algorithm. In: CEC 2006, Vancoucer, Canada (to appear, 2006)Google Scholar
  9. 9.
    Minku, F.L., Ludermir, T.B.: EFuNN ensembles construction using CONE with multi-objective GA. In: SBRN 2006, Ribeirao Preto, Brazil (to appear, 2006)Google Scholar
  10. 10.
    Kasabov, N.: Evolving fuzzy neural networks for supervised/unsupervised on-line, knowledge-based learning. IEEE Transactions on Systems, Man and Cybernetics 31(6), 902–918 (2001)CrossRefGoogle Scholar
  11. 11.
    Dietterich, T.G.: Machine-learning research: Four current directions. The AI Magazine 18(4), 97–136 (1998)Google Scholar
  12. 12.
    Fonseca, C.M., Fleming, P.J.: Multi-objective optimization and multiple constraint handling with evolutionary algorithms - part I: A unified formulation. IEEE Transactions on Systems, Man and Cybernetics - Part A 28(1), 26–37 (1998)CrossRefGoogle Scholar
  13. 13.
    Prechelt, L.: PROBEN1 - a set of neural network benchmark problems and benchmarking rules. Technical Report 21/94, Fakultät für Informatik, Universität Karlsruhe, Karlsruhe, Germany (1994)Google Scholar
  14. 14.
    Mackey, M.C., Glass, L.: Oscillation and chaos in physiological control systems. Science 197, 287–289 (1977)CrossRefGoogle Scholar
  15. 15.
    Box, G.E.P., Jenkins, G.M.: Time Series Analysis, Forecasting and Control, pp. 532–533. Holden Day, San Francisco (1970)MATHGoogle Scholar
  16. 16.
    Witten, I.H., Frank, E.: Data Mining - Pratical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann Publishers, San Francisco (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fernanda L. Minku
    • 1
  • Teresa B. Ludermir
    • 1
  1. 1.Informatics CenterFederal University of PernambucoRecife-PEBrazil

Personalised recommendations