Two-Stages Support Vector Regression for Fuzzy Neural Networks with Outliers

Chen-Chia Chuang; Jin-Tsong Jeng; Tao, C. W.
March 2009
International Journal of Fuzzy Systems;Mar2009, Vol. 11 Issue 1, p20
Academic Journal
In this study, two-stages support vector regression (TSSVR) approach is proposed to deal with training data set with outliers for fuzzy neural networks (FNNs). The proposed approach in the stage I, called as data preprocessing, the support vector machines for regression (SVMR) approach is used to filter out the outliers in the training data set and determine the number of fuzzy rule. Due to the outliers in the training data set are removed, the concept of robust statistic theory have no need to reduce the outlier's effect. Then, the training data set except for outliers, called as the reduced training data set, is directly used to training the sparse least squares support vector machines for regression (LS-SVMR) in the stage II. Consequently, the learning mechanism of the proposed approach for fuzzy neural network does not need iterated learning for simplified fuzzy inference systems. Based on the simulation results, the performance of the proposed approach is superior to the robust LS-SVMR approach when the outliers are existed.


Related Articles

  • AN ALTERNATIVE METHOD TO TEST THE RESIDUALS IN A REGRESSION MODEL. Holmes, Donald S.; Mergen, A. Erhan // Proceedings for the Northeast Region Decision Sciences Institute;2008, p679 

    In this paper we propose an alternative method to the Durbin-Watson (DW) test for the fitness of a regression model (see, for example, Makridakis [5, pp. 267-268; 303-304; 630-631] and Wilson & Keating [8, pp. 182-184; 234-236] for DW statistic). The proposed method tests whether the residual...

  • Artificial regression testing in the GARCH-in-mean model. Lucchetti, Riccardo; Rossi, Eduardo // Econometrics Journal;Dec2005, Vol. 8 Issue 3, p306 

    The issue of finite-sample inference in Generalised Autoregressive Conditional Heteroskedasticity (GARCH)-like models has seldom been explored in the theoretical literature, although its potential relevance for practitioners is obvious. In some cases, asymptotic theory may provide a very poor...

  • M-Estimators in Regression Models. Muthukrishnan, R.; Radha, M. // Journal of Mathematics Research;Nov2010, Vol. 2 Issue 4, p23 

    Regression analysis plays a vital role in many areas of science. Almost all regression analyses rely on the method of least squares for estimation of the parameters in the model. But this method is usually constructed under specific assumptions, such as normality of the error distribution. When...

  • Estimator selection with respect to Hellinger-type risks. Baraud, Yannick // Probability Theory & Related Fields;Jul2011, Vol. 151 Issue 1/2, p353 

    We observe a random measure N and aim at estimating its intensity s. This statistical framework allows to deal simultaneously with the problems of estimating a density, the marginals of a multivariate distribution, the mean of a random vector with nonnegative components and the intensity of a...

  • The geometrical interpretation of statistical tests in multivariate linear regression. Langsrud, √ėyvind // Statistical Papers;Jan2004, Vol. 45 Issue 1, p111 

    A geometrical interpretation of the classical tests of the relation between two sets of variables is presented. One of the variable sets may be considered as fixed and then we have a multivariate regression model. When the Wilks' lambda distribution is viewed geometrically it is obvious that the...

  • Determinant Efficiencies in Ill-Conditioned Models. Jensen, D. R. // Journal of Probability & Statistics;2011, p1 

    The canonical correlations between subsets of OLS estimators are identified with design linkage parameters between their regressors. Known collinearity indices are extended to encompass angles between each regressor vector and remaining vectors. One such angle quantifies the collinearity of...

  • Adjusting for covariate errors with nonparametric assessment of the true covariate distribution. Pierce, Donald A.; Kellerer, Albrecht M. // Biometrika;Dec2004, Vol. 91 Issue 4, p863 

    A well-known and useful method for generalised regression analysis when a linear covariate x is available only through some approximation z is to carry out more or less the usual analysis with E(x|z) substituted for x. Sometimes, but not always, the quantity var (x|z) should be used to allow for...

  • The Non-Parametric Identification of Generalized Accelerated Failure-Time Models. Ridder, Geert // Review of Economic Studies;Apr90, Vol. 57 Issue 2, p167 

    We consider a class of models that generalizes the popular Mixed Proportional Hazard (MPH) model for duration data: the Generalized Accelerated Failure-Time (GAFT) model. We show that the GAFT model is non-parametrically identified (up to a normalization). We then reconsider the non-parametric...

  • Estimators for the Convergence Rate of the Distribution Functions of Linear Rank Statistics in the Case of Close Alternatives. II. Vostrikov, A. A. // Journal of Mathematical Sciences;Jan2004, Vol. 119 Issue 3, p347 

    Deals with estimators for the convergence rate of the distribution functions of linear rank statistics in the case of close alternatives. Auxiliary lemmas; Regression constants satisfying regularity condition; Application of the Holder inequality and the first statement of the lemma.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics