Online Prediction Model Based on New Kernel Method

Ilyes Elaissi(1*), Okba Taouali(2), Messaoud Hassani(3)

(1) Laboratory of Automatic Signal and Image Processing, National School of Engineers of Monastir, University of Monastir, 5019, Tunisia, Tunisia
(2) Laboratory of Automatic Signal and Image Processing, National School of Engineers of Monastir, University of Monastir, 5019, Tunisia, Tunisia
(3) Laboratory of Automatic Signal and Image Processing, National School of Engineers of Monastir, University of Monastir, 5019, Tunisia, Tunisia
(*) Corresponding author


DOI's assignment:
the author of the article can submit here a request for assignment of a DOI number to this resource!
Cost of the service: euros 10,00 (for a DOI)

Abstract


This paper proposes a new online kernel identification method of a nonlinear system. The proposed algorithm entitled online RKPLS-RN kernel method uses the technique Reduced Kernel Partial Least Square (RKPLS) in an offline phase to construct a RKHS model with reduced parameter number. Then the Regularized Network (RN) method is used on online phase to update the reduced parameters of the RKHS model that determined in offline one using the RKPLS technique. The proposed algorithm has been tested to identify an electronic nonlinear system with a Wiener Hammerstein structure
Copyright © 2014 Praise Worthy Prize - All rights reserved.

Keywords


RKHS; SLT; Kernel Method; Online Identification; RKPLS-RN; Wiener Hammerstein Structure

Full Text:

PDF


References


B. Scholkopf and A. Smola. Learning with kernels. The MIT press, 2002.

B. Scholkopf, A. Smola and K-R Muller. Nonlinear component analysis as Kernel eigenvalue problem. Neural computation. 10, 1299-1319,1998

F. Lauer and G. Bloch. Incorporating prior knowledge in support vector regression.Machine Learning, 70, pp. 89-118, 2008.

G. Li, Changyun Wen, Zhengguo Li, Aimin Zhang, Feng Yang, Kezhi Mao. Model-based online Learning with Kernels. IEEE Trans. Neural Netw. Learning Syst. 24(3), 356-369, 2013.

G. Wahba. An introduction to model building with Reproducing Kernel Hilbert Spaces. Technical report No 1020, Department of Statistics, University of Wisconsin-Madison, 2000.

I. Elaissi, Ines jaffal, O. Taouali and H. Messaoud. Online Prediction Model based SVD-KPCA methos ISA transactions, vol 52, 96-104, 2013.

K. Veropoulos. N. Cristianini, and Campbell. C. The Application of Support Vector Machines to Medical Decision Support: A Case Study. ACAI conference, 1999.

M.H. Yang. Kernel Eigenfaces vs kernel First faces: Face recognition using kernel method. In IEEE FGR pp. 215-220, 2002.

O. Taouali, I. Elaissi and H. Messaoud. Online Prediction Model based on Reduced Kernel Principal Component Analysis. Neural Computing and Application journal, Vol 21 (1) , pp. 161-169, 2012.

O. Taouali, I. Elaissi, and H. Messaoud. Design and comparative study of online kernel methods identification of nonlinear system in RKHS space. Artificial Intelligence Review, Issue 4, vol 37, 289-300, 2012.

O. Taouali, I. Elaissi, T. Garna and H. Messaoud. A new approach for identification of MIMO non linear system with RKHS model. Wseas Transactions on Information Science and Applications, Vol 7, 2010.

O. Taouali, I. Aissi , N. Villa and H. Messaoud. Identification of nonlinear Multivariable Processes Modelled on Reproducing Kernel Hilbert Space: Application to Tennessee Process. ICONS, 2nd IFAC International Conference on Intelligent Control Systems and Signal Processing, pp.1-6, Istanbul 2009.

R. Rosipal and L.J. Trecho. Kernel Partial Least Squares in Reproducing Kernel Hilbert Spaces, Journal of machine learning research 2, 97-123, 2001.

R. Rosipal et N. Kramer. Overview and recent advances in Partial least squares. C. Saunders et al. (Eds.): SLSFS 2005, LNCS 3940, pp. 34-51, 2006.

S. Van Vaerenbergh, Javier Vıa and Ignacio Santamarıa. Nonlinear System Identification using a New Sliding-Window Kernel RLS Algorithm. Journal of Communications, vol 2, 2007.

Vandersteen G. Identification of linear and nonlinear systems in an errors-in-variables least squares and total least squares framework, Phd thesis, Vrije Universiteit Brussel, 1997.

W. Wanga, C. Mena, W. Lub, Online prediction model based on support vector machine, Neurocomputing 71,550-558 , 2008.

K. P. Bennett et M. J. Embrechts. Advances in Learning Theory: Methods,Models and Applications, J.A.K. Suykens, G. Horvath, S. Basu, C.Micchelli, J. Vandewalle (Eds.). NATO Science Series III: Computer & Systems Sciences, IOS Press Amsterdam, vol.190, pp. 227–250, 2003.

P.J. Lewi. Pattern recognition, refection from a chemometric point of view. Chemometrics and Intelligent Laboratory Systems, 28:23-33, 1995.

A.Höskuldsson. PLS Regression Methods. Journal of Chemometrics 2:211-228, 1988.

S. Rannär , F. Lindgren P. Geladi and S. Wold. A PLS Kernel algorithm for data sets with many variables and fewer objects. Part1: Theory and algorithm. Chemometrics and Intelligent Laboratory Systems, 8:111-125, 1994

O. Taouali I. Elaissi , and H. Messaoud. New Reduction Kernel method of RKHS model based on Kernel Partial Least Square Technique. Accepted with revision in ISA transactions, 2014

Ines jaffal, O. Taouali, I. Elaissi and H. Messaoud. A new online fault detection method based on PCA technique. IMA Journal of Mathematical Control and Information, 2013.

Elaissi Ilyes, Taouali Okba, Messaoud Hassani, Dimensionality Reduction for Supervised Learning with Reproducing Kernel Hilbert Space, (2010) International Review of Automatic Control (IREACO), 3. (2), pp. 152-160.

Jihane Ben Slimane Dhifallah, Kaouther Laabidi, Moufida Ksouri Lahmari, Support Vector Machines for Failures Diagnosis, (2009) International Review of Automatic Control (IREACO), 2. (5), pp. 505-511.


Refbacks

  • There are currently no refbacks.



Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2020 Praise Worthy Prize