Advertisement

Construction of Radial Basis Function Networks with Diversified Topologies

  • X. Hong
  • S. Chen
  • C. J. Harris

Abstract

In this review we bring together some of our recent work from the angle of the diversified RBF topologies, including three different topologies; (i) the RBF network with tunable nodes; (ii) the Box-Cox output transformation based RBF network (Box-Cox RBF); and (iii) the RBF network with boundary value constraints (BVC-RBF). We show that the modified topologies have some advantages over the conventional RBF topology for specific problems. For each modified topology, the model construction algorithms have been developed. These proposed RBF topologies are respectively aimed at enhancing the modelling capabilities of; (i)flexible basis function shaping for improved model generalization with the minimal model;(ii) effectively handling some dynamical processes in which the model residuals exhibit heteroscedasticity; and (iii) achieving automatic constraints satisfaction so as to incorporate deterministic prior knowledge with ease. It is shown that it is advantageous that the linear learning algorithms, e.g. the orthogonal forward selection (OFS) algorithm based leave-one-out (LOO) criteria, are still applicable as part of the proposed algorithms.

Keywords

Radial Basis Function Radial Basis Function Neural Network Radial Basis Function Network Orthogonal Little Square Radial Basis Function Node 
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.
    Hong, X., Mitchell, R.J., Chen, S., Harris, C.J., Li, K., Irwin, G.W.: Model selection approaches for nonlinear system identification: a review. Int. J. Syst. Sci. 39(10), 925–946 (2008) MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    Harris, C.J., Hong, X., Gan, Q.: Adaptive Modelling, Estimation and Fusion from Data: A Neurofuzzy Approach. Springer, Berlin (2002) MATHCrossRefGoogle Scholar
  3. 3.
    Brown, M., Harris, C.J.: Neurofuzzy Adaptive Modelling and Control. Prentice Hall, Upper Saddle River (1994) Google Scholar
  4. 4.
    Ruano, A.E.: Intelligent Control Systems using Computational Intelligence Techniques. IEE Publishing, New York (2005) MATHCrossRefGoogle Scholar
  5. 5.
    Murray-Smith, R., Johansen, T.A.: Multiple Model Approaches to Modelling and Control. Taylor and Francis, London (1997) Google Scholar
  6. 6.
    Fabri, S.G., Kadirkamanathan, V.: Functional Adaptive Control: An Intelligent Systems Approach. Springer, Berlin (2001) MATHGoogle Scholar
  7. 7.
    Leonard, J.A., Kramer, M.A.: Radial basis function networks for classifying process faults. IEEE Control Syst. Mag. 11(3), 31–38 (1991) CrossRefGoogle Scholar
  8. 8.
    Caiti, A., Parisini, T.: Mapping ocean sediments by RBF networks. IEEE J. Ocean. Eng. 19(4), 577–582 (1994) CrossRefGoogle Scholar
  9. 9.
    Li, Y., Sundararajan, N., Saratchandran, P., Wang, Z.: Robust neuro-H controller design for aircraft auto-landing. IEEE Trans. Aerosp. Electron. Syst. 40(1), 158–167 (2004) CrossRefGoogle Scholar
  10. 10.
    Ng, S.X., Yee, M.S., Hanzo, L.: Coded modulation assisted radial basis function aided turbo equalization for dispersive Rayleigh-fading channels. IEEE Trans. Wirel. Commun. 3(6), 2198–2206 (2004) CrossRefGoogle Scholar
  11. 11.
    Stone, M.: Cross validatory choice and assessment of statistical predictions. J. R. Stat. Soc. B 36, 117–147 (1974) Google Scholar
  12. 12.
    Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. Control AC-19, 716–723 (1974) MathSciNetCrossRefGoogle Scholar
  13. 13.
    Chen, S., Billings, S.A., Luo, W.: Orthogonal least squares methods and their applications to non-linear system identification. Int. J. Control 50, 1873–1896 (1989) MathSciNetMATHCrossRefGoogle Scholar
  14. 14.
    Korenberg, M.J.: Identifying nonlinear difference equation and functional expansion representations: the fast orthogonal algorithm. Ann. Biomed. Eng. 16, 123–142 (1988) CrossRefGoogle Scholar
  15. 15.
    Wang, L., Mendel, J.M.: Fuzzy basis functions, universal approximation, and orthogonal least-squares learning. IEEE Trans. Neural Netw. 5, 807–814 (1992) CrossRefGoogle Scholar
  16. 16.
    Hong, X., Harris, C.J.: Neurofuzzy design and model construction of nonlinear dynamical processes from data. IEE Proc., Control Theory Appl. 148(6), 530–538 (2001) CrossRefGoogle Scholar
  17. 17.
    Zhang, Q.: Using wavelets network in nonparametric estimation. IEEE Trans. Neural Netw. 8(2), 1997 (1993) Google Scholar
  18. 18.
    Billings, S.A., Wei, H.L.: The wavelet-narmax representation: a hybrid model structure combining polynomial models with multiresolution wavelet decompositions. Int. J. Syst. Sci. 36(3), 137–152 (2005) MathSciNetMATHCrossRefGoogle Scholar
  19. 19.
    Hong, X., Sharkey, P.M., Warwick, K.: Automatic nonlinear predictive model construction using forward regression and the PRESS statistic. IEE Proc., Control Theory Appl. 150(3), 245–254 (2003) CrossRefGoogle Scholar
  20. 20.
    Chen, S., Hong, X., Harris, C.J.: Construction of tunable radial basis function networks using orthogonal forward selection. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 39(2), 457–466 (2009) MathSciNetCrossRefGoogle Scholar
  21. 21.
    Hong, X.: Modified radial basisfunction neural networks using output transformation. IEE Proc., Control Theory Appl. 1(1), 1–8 (2007) MATHCrossRefGoogle Scholar
  22. 22.
    Hong, X., Chen, S.: A new RBF neural network with boundary value constraints. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 39(1), 298–303 (2009) CrossRefGoogle Scholar
  23. 23.
    Vapnik, V.: The Nature of Statictical Learning Theory. Springer, New York (1995) Google Scholar
  24. 24.
    Gunn, S.R.: Support vector machine for classification and regression. Technical Report, ISIS Research Group, Dept of Electronics and Computer Science, University of Southampton (1998) Google Scholar
  25. 25.
    Chen, S.S., Donoho, D.L., Saunders, M.A.: Atomic decomposition by basis pursuit. SIAM J. Sci. Comput. 20(1), 33–61 (1998) MathSciNetCrossRefGoogle Scholar
  26. 26.
    Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 1, 211–244 (2001) MathSciNetMATHGoogle Scholar
  27. 27.
    Chen, S., Hong, X., Harris, C.J., Sharkey, P.M.: Sparse modelling using orthogonal forward regression with PRESS statistic and regularization. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 34(2), 898–911 (2004) CrossRefGoogle Scholar
  28. 28.
    Myers, R.H.: Classical and Modern Regression with Applications, 2nd edn. PWS-KENT, Boston (1990) Google Scholar
  29. 29.
    Chen, S., Wang, X.X., Harris, C.J.: Experiments with repeating weighted boosting search for optimization signal processing applications. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 35(4), 682–693 (2005) CrossRefGoogle Scholar
  30. 30.
  31. 31.
    Chen, S., Hong, X., Luk, B.L., Harris, C.J.: Nonlinear system identification using particle swarm optimization tuned radial basis function models. Int. J. Bio-Inspired Comput. 1(4), 246–258 (2009) CrossRefGoogle Scholar
  32. 32.
    Box, G.E.P., Cox, D.R.: An analysis of transformation. J. R. Stat. Soc. B 26(2), 211–252 (1964) MathSciNetMATHGoogle Scholar
  33. 33.
    Carroll, R.J., Ruppert, D.: Transformation and Weighting in Regression. Chapman and Hall, London (1988) MATHGoogle Scholar
  34. 34.
    Ding, A.A., He, X.: Backpropagation of pseudoerrors: neural networks that are adaptive to heterogeneous noise. IEEE Trans. Neural Netw. 14(2), 253–262 (2003) CrossRefGoogle Scholar
  35. 35.
    Chen, S., Wu, Y., Luk, B.L.: Combined genetic algorithm optimization and regularized orthogonal least squares learning for radial basis function networks. IEEE Trans. Neural Netw. 10, 1239–1243 (1999) CrossRefGoogle Scholar
  36. 36.
    Hong, X., Harris, C.J.: Nonlinear model structure design and construction using orthogonal least squares and D-optimality design. IEEE Trans. Neural Netw. 13(5), 1245–1250 (2002) CrossRefGoogle Scholar
  37. 37.
    Chen, S.: Locally regularised orthogonal least squares algorithm for the construction of sparse kernel regression models. In: Proceedings of 6th Int. Conf. Signal Processing, Beijing, China, pp. 1229–1232 (2002) Google Scholar
  38. 38.
    Powell, M.J.D.: Problems related to unconstrained optimization. In: Murray, W. (ed.) Numerical Methods for Unconstrained Optimization, pp. 29–55. Academic Press, London (1972) Google Scholar
  39. 39.
    Hipel, K.W., Mcleod, A.I.: Time Series Modelling of Water Resources and Environmental Systems. Elsevier, Amsterdam (1994) Google Scholar
  40. 40.
    Atkinson, A.C., Donev, A.N.: Optimum Experimental Designs. Clarendon Press, Oxford (1992) MATHGoogle Scholar
  41. 41.
    Hong, X., Harris, C.J.: Experimental design and model construction algorithms for radial basis function networks. Int. J. Syst. Sci. 34(14–15), 733–745 (2003) MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2012

Authors and Affiliations

  1. 1.School of Systems EngineeringUniversity of ReadingReadingUK
  2. 2.School of Electronics and Computer ScienceUniversity of SouthamptonSouthamptonUK

Personalised recommendations