Abstract
This paper proposes Box-Cox transformation-based annealing robust fuzzy neural networks (ARFNNs) that can be used effectively for function approximated problem with skewness noises. In order to overcome the skewness noises problem, the Box-Cox transformation that its object is usually to make residuals more homogeneous in regression, or transform data to be normally distributed has been added to the annealing robust fuzzy neural networks. That is, the proposed approach uses Box-Cox transformation for skewness noises problem and support vector regression (SVR) for the number of rule in the simplified fuzzy inference systems. After the initialization, an annealing robust learning algorithm (ARLA) is then applied to adjust the parameters of the Box-Cox transformation-based annealing robust fuzzy neural networks. Simulation results show that the proposed approach has a fast convergent speed and more generalization capability for the function approximated problem with skewness noises.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Box, G.E.P., Cox, D.R.: An Analysis of Transformation. Journal of the Royal Statistical Society, Series B 26, 211–252 (1964)
Purwar, S., Kar, I.N., Jha, A.N.: On-line System Identification of Complex Systems Using Chebyshev Neural Networks. Applied Soft Computing 7, 364–372 (2007)
Trabelsi, A., Lafont, F., Kamoun, M., Enea, G.: Fuzzy Identification of a Greenhouse. Applied Soft Computing 7, 1092–1101 (2007)
Jeng, J.T., Chuang, C.C.: New Fuzzy Modeling Based on Input-Output Pseudolinearization and Its Digital Approximation Via Walsh Functions. International Journal of Fuzzy Systems 3, 503–511 (2001)
Leu, Y.G., Lee, T.T., Wang, W.Y.: On-line Tuning of Fuzzy-Neural Network for Adaptive Control of Nonlinear Dynamical Systems. IEEE Transactions on Systems Man and Cybernet 27, 1034–1043 (1997)
Chuang, C.C., Su, S.F., Hsiao, C.C.: The Annealing Robust Backpropagation (BP) Learning Algorithm. IEEE Transactions on Neural Networks 11, 1067–1077 (2000)
Hong, X.: A Fast Identification Algorithm for Box-Cox Transformation Based Radial Basis Function Neural Network. IEEE Transactions on Neural Networks 17, 1064–1069 (2006)
Hong, Y.P., Pan, C.T.: Rank-revealing QR Factorizations and the Singular Value Decomposition. Mathematics of Computation 58, 213–232 (1992)
Jeng, J.T., Chuang, C.C.: Selection of Initial Structures with Support Vector Regression for Fuzzy Neural Networks. International Journal of Fuzzy Systems 6, 63–70 (2004)
Jang, J.S., Sun, C.T., Mizutani, E.: Neuro-Fuzzy and Soft Computing. Prentice-Hall, Englewood Cliffs (1997)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Berlin (1995)
Vapnik, V.N., Golowich, S., Smola, A.J.: Support Vector Method for Function Approximation, Regression Estimation and Signal Processing. Neural Information Processings Systems 9, 281–287 (1997)
Liu, Y.S., Su, S.F., Chuang, C.C., Jeng, J.T.: Box-Cox Transformation-based Annealing Robust Radial Basis Function Networks for Skewness Noises. In: 2010 International Conference on System Science and Engineering (ICSSE), pp. 537–541 (2010)
Chuang, C.C., Jeng, J.T., Lin, P.T.: Annealing Robust Radial Basis Function Networks for Function Approximation with Outliers. Neurocomputing 56, 123–139 (2004)
Hong, X.: Modified Radial Basis Function Neural Network Using Output Transformation. IET Control Theory & Applications 1, 1–8 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, PY., Fu, YY., Jeng, JT., Su, KL. (2011). A Fast Identification Algorithm with Skewness Noises under Box-Cox Transformation-Based Annealing Robust Fuzzy Neural Networks. In: Li, TH.S., et al. Next Wave in Robotics. FIRA 2011. Communications in Computer and Information Science, vol 212. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23147-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-23147-6_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23146-9
Online ISBN: 978-3-642-23147-6
eBook Packages: Computer ScienceComputer Science (R0)