Advertisement

Prediction by k-NN and MLP a New Approach Based on Fuzzy Similarity Quality Measure. A Case Study

  • Yaima FilibertoEmail author
  • Rafael Bello
  • Wilfredo Martinez
  • Dianne Arias
  • Ileana Cadenas
  • Mabel Frias
Chapter
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 377)

Abstract

In this paper the performance of k Nearest Neighbors (k-NN) and Multilayer Perceptron network (MLP) algorithms are used in a classical task in the branch of the Civil Engineering: prediction of the behavior before the stud corrosion of anchorage of the railways fixations. The use of fuzzy similarity quality measure method for calculating the weights of the features that combines the Univariant Marginals Distribution Algorithm (UMDA), allows to performance of k-NN and MLP in the case of mixed data (features with discrete or real domains). Experimental results show that this approach is better than other methods used to calculate the weight of the features.

References

  1. 1.
    Filiberto, Y., Bello, R., Caballero, Y., Larrua, R.: In: Proceedings of the 10th International Conference on Intelligent Systems Design and Applications ISDA 2010 IEEE, pp. 1314–1319. IEEE Press (2010)Google Scholar
  2. 2.
    Zadeh, L.A.: Inf. Control 8, 338 (1965)Google Scholar
  3. 3.
    Larrañaga, P., Etxeberria, R., Lozano, J.A., Pea, J.M.: Optimization by learning and simulation of bayesian and gaussian networks. Kzza-ik-4-99, Dept. of Computer Science and Artificial Intelligence, University of the Basque Country (1999)Google Scholar
  4. 4.
    Cover, T.M., Hart, P.E.: IEEE Trans. Inf. Theory, pp. 21–27 (1967)Google Scholar
  5. 5.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Cambridge (1995)zbMATHGoogle Scholar
  6. 6.
    Zadeh, L.A.: Inf. Sci. 3, 177 (1971)Google Scholar
  7. 7.
    Wang, W.: Fuzzy Sets Syst. 85, 305 (1997)CrossRefGoogle Scholar
  8. 8.
    Filiberto, Y., Bello, R., Caballero, Y., Larrua, R.: In: International Workshop on Nature Inspired Cooperative Strategies for Optimization, pp. 359–370. Springer, Berlin (2010)Google Scholar
  9. 9.
    Mitchell, T.: McGraw Hill, p. 414 (1997)Google Scholar
  10. 10.
    Fernandez, Y., Filiberto, Y., Bello, R.: In: 11th International Conference on Electrical Engineering, Computing Science and Automatic Control, 1-6, pp. 296–301. IEEE Press, Mexico (2014)Google Scholar
  11. 11.
    Duch, W., Grudzinski, K.: Intelligent Information Systems, pp. 32–36 (1999)Google Scholar
  12. 12.
    Filiberto, Y., Bello, R., Caballero, Y., Frias, M.: In: 4th International Workshop on Knowledge Discovery. Knowledge Management and Decision Support, pp. 130–139 (2013)Google Scholar
  13. 13.
    Rumelhart, D., Hilton, G., Williams, R.: Nature 323, 533 (1986)CrossRefGoogle Scholar
  14. 14.
    Fu, X., Zhang, S., Pang, Z.: A resource limited immune approach for evolving architecture and weights of multilayer neural network, part I. ICSI 2010, vol. 6145, pp. 328–337. Springer, Heidelberg (2010)Google Scholar
  15. 15.
    Adam, S., Alexios, D., Vrahatis, M.: Revisiting the problem of weight initialization for multi-layer perceptrons trained with back propagation. ICONIP 2008, vol. 5507, pp. 308–315. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  16. 16.
    Coello, L., Fernandez, Y., Filiberto, Y., Bello, R.: Computaci y Sistemas 19(2), 309 (2015)Google Scholar
  17. 17.
    Etxeberria, R., Lozano, J.A., Peña, J.M., Larrañaga, P.: In: Wu, A.S. (ed.) Proceeding of the Genetic and Evolutionary Computation Workshop Program. Morgan Kaufmann, Las Vegas, Nevada, USA, pp. 201–204 (2000)Google Scholar
  18. 18.
    Wettschereckd, D.: A description of the mutual information approach and the variable similarity metric. Technical Report, Artificial Intelligence Research Division, German National Research Center for Computer Science, Sankt Augustin, Germany (1995)Google Scholar
  19. 19.
    Kononenko, I.: In: European Conference on Machine Learning (1994)Google Scholar
  20. 20.
    Iman, R.L., Davenport, J.: Commun. Stat. 18, 571 (1980)Google Scholar
  21. 21.
    Holm, S.: A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6(2), 65–70 (1979)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yaima Filiberto
    • 1
    Email author
  • Rafael Bello
    • 2
  • Wilfredo Martinez
    • 3
  • Dianne Arias
    • 1
  • Ileana Cadenas
    • 3
  • Mabel Frias
    • 1
  1. 1.Department of Computer ScienceUniversity of CamagueyCamagueyCuba
  2. 2.Department of Computer ScienceUniversity of Las VillasSanta ClaraCuba
  3. 3.Department of Civil EngineerUniversity of CamagueyCamagueyCuba

Personalised recommendations