Fuzzy Evolutionary Probabilistic Neural Networks

  • V. L. Georgiou
  • Ph. D. Alevizos
  • M. N. Vrahatis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5064)

Abstract

One of the most frequently used models for classification tasks is the Probabilistic Neural Network. Several improvements of the Probabilistic Neural Network have been proposed such as the Evolutionary Probabilistic Neural Network that employs the Particle Swarm Optimization stochastic algorithm for the proper selection of its spread (smoothing) parameters and the prior probabilities. To further improve its performance, a fuzzy class membership function has been incorporated for the weighting of its pattern layer neurons. For each neuron of the pattern layer, a fuzzy class membership weight is computed and it is multiplied to its output in order to magnify or decrease the neuron’s signal when applicable. Moreover, a novel scheme for multi–class problems is proposed since the fuzzy membership function can be incorporated only in binary classification tasks. The proposed model is entitled Fuzzy Evolutionary Probabilistic Neural Network and is applied to several real-world benchmark problem with promising results.

Keywords

Particle Swarm Optimization Probabilistic Neural Network Fuzzy Membership Function Pattern Layer Kernel Discriminant Analysis 
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.

References

  1. 1.
    Georgiou, V.L., Pavlidis, N.G., Parsopoulos, K.E., Alevizos, Ph.D., Vrahatis, M.N.: New self–adaptive probabilistic neural networks in bioinformatic and medical tasks. International Journal on Artificial Intelligence Tools 15(3), 371–396 (2006)CrossRefGoogle Scholar
  2. 2.
    Georgiou, V.L., Alevizos, Ph.D., Vrahatis, M.N.: Novel approaches to probabilistic neural networks through bagging and evolutionary estimating of prior probabilities. Neural Processing Letters 27, 153–162 (2008)CrossRefGoogle Scholar
  3. 3.
    Specht, D.F.: Probabilistic neural networks. Neural Networks 1(3), 109–118 (1990)CrossRefGoogle Scholar
  4. 4.
    Ganchev, T., Tasoulis, D.K., Vrahatis, M.N., Fakotakis, N.: Locally recurrent probabilistic neural networks with application to speaker verification. GESTS International Transaction on Speech Science and Engineering 1(2), 1–13 (2004)Google Scholar
  5. 5.
    Ganchev, T., Tasoulis, D.K., Vrahatis, M.N., Fakotakis, N.: Generalized locally recurrent probabilistic neural networks with application to text-independent speaker verification. Neurocomputing 70(7–9), 1424–1438 (2007)CrossRefGoogle Scholar
  6. 6.
    Guo, J., Lin, Y., Sun, Z.: A novel method for protein subcellular localization based on boosting and probabilistic neural network. In: Proceedings of the 2nd Asia-Pacific Bioinformatics Conference (APBC 2004), Dunedin, New Zealand, pp. 20–27 (2004)Google Scholar
  7. 7.
    Huang, C.J.: A performance analysis of cancer classification using feature extraction and probabilistic neural networks. In: Proceedings of the 7th Conference on Artificial Intelligence and Applications, Wufon, Taiwan, pp. 374–378 (2002)Google Scholar
  8. 8.
    Hand, J.D.: Kernel Discriminant Analysis. Research Studies Press, Chichester (1982)MATHGoogle Scholar
  9. 9.
    Parzen, E.: On the estimation of a probability density function and mode. Annals of Mathematical Statistics 3, 1065–1076 (1962)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings IEEE International Conference on Neural Networks, Piscataway, NJ, vol. IV, pp. 1942–1948. IEEE Service Center, Los Alamitos (1995)CrossRefGoogle Scholar
  11. 11.
    Parsopoulos, K.E., Vrahatis, M.N.: Recent approaches to global optimization problems through particle swarm optimization. Natural Computing 1(2–3), 235–306 (2002)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Delgosha, F., Menhaj, M.B.: Fuzzy probabilistic neural networks: A practical approach to the implementation of bayesian classifier. In: Reusch, B. (ed.) Fuzzy Days 2001. LNCS, vol. 2206, pp. 76–85. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  13. 13.
    Zadeh, L.A.: Fuzzy sets. Information and Control 8(3), 338–353 (1965)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Zadeh, L.A.: Fuzzy logic. IEEE Computer 21(4), 83–93 (1988)Google Scholar
  15. 15.
    Keller, J.M., Hunt, D.J.: Incorporating fuzzy membership functions into the perceptron algorithm. IEEE Trans. Pattern Anal. Machine Intell. 7(6), 693–699 (1985)CrossRefGoogle Scholar
  16. 16.
    Chen, J., Chen, C.: Fuzzy kernel perceptron. IEEE Transactions on Neural Networks 13(6), 1364–1373 (2002)CrossRefGoogle Scholar
  17. 17.
    Kaufman, L., Rousseeuw, P.J.: Finding Groups in Data: An Introduction to Cluster Analysis. John Wiley and Sons, New York (1990)Google Scholar
  18. 18.
    Parsopoulos, K.E., Vrahatis, M.N.: On the computation of all global minimizers through particle swarm optimization. IEEE Transactions on Evolutionary Computation 8(3), 211–224 (2004)CrossRefMathSciNetGoogle Scholar
  19. 19.
    Clerc, M., Kennedy, J.: The particle swarm–explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation 6(1), 58–73 (2002)CrossRefGoogle Scholar
  20. 20.
    Trelea, I.C.: The particle swarm optimization algorithm: Convergence analysis and parameter selection. Information Processing Letters 85, 317–325 (2003)CrossRefMathSciNetMATHGoogle Scholar
  21. 21.
    Prechelt, L.: Proben1: A set of neural network benchmark problems and benchmarking rules. Technical Report 21/94, Fakultät für Informatik, Universität Karlsruhe (1994)Google Scholar
  22. 22.
    Newman, D.J., Hettich, S., Blake, C.L., Merz, C.J.: UCI repository of machine learning databases (1998)Google Scholar
  23. 23.
    Mangasarian, O.L., Wolberg, W.H.: Cancer diagnosis via linear programming. SIAM News 23, 1–18 (1990)Google Scholar
  24. 24.
    Gorunescu, F., Gorunescu, M., Revett, K., Ene, M.: A hybrid incremental/monte carlo searching technique for the smoothing parameter of probabilistic neural networks. In: Proceedings of the International Conference on Knowledge Engineering, Principles and Techniques, KEPT 2007, Cluj-Napoca, Romania, pp. 107–113 (2007)Google Scholar
  25. 25.
    Kanji, G.K.: 100 Statistical Tests. Sage Publications, Thousand Oaks (1999)Google Scholar
  26. 26.
    Bouckaert, R.R., Frank, E.: Evaluating the replicability of significance tests for comparing learning algorithms. In: Dai, H., Srikant, R., Zhang, C. (eds.) PAKDD 2004. LNCS (LNAI), vol. 3056, pp. 3–12. Springer, Heidelberg (2004)Google Scholar
  27. 27.
    Nadeau, C., Bengio, Y.: Inference for the generalization error. Machine Learning 52(3), 239–281 (2003)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • V. L. Georgiou
    • 1
  • Ph. D. Alevizos
    • 1
  • M. N. Vrahatis
    • 1
  1. 1.Computational Intelligence Laboratory (CI Lab), Department of MathematicsUniversity of Patras Artificial Intelligence Research Center (UPAIRC), University of PatrasPatrasGreece

Personalised recommendations