A hybrid algorithm to optimize RBF network architecture and parameters for nonlinear time series prediction

Abstract This paper proposes a novel hybrid algorithm for automatic selection of the proper input variables, the number of hidden nodes of the radial basis function (RBF) network, and optimizing network parameters (weights, centers and widths) simultaneously. In the proposed algorithm, the inputs and the number of hidden nodes of the RBF network are represented by binary-coded strings and evolved by a genetic algorithm (GA). Simultaneously, for each chromosome with fixed inputs and number of hidden nodes, the corresponding parameters of the network are real-coded and optimized by a gradient-based fast-converging parameter estimation method. Performance of the presented hybrid approach is evaluated by several benchmark time series modeling and prediction problems. Experimental results show that the proposed approach produces parsimonious RBF networks, and obtains better modeling accuracy than some other algorithms.

[1]  Babak Nadjar Araabi,et al.  Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study , 2006, Neural Processing Letters.

[2]  Christian W. Dawson,et al.  The effect of different basis functions on a radial basis function network for time series prediction: A comparative study , 2006, Neurocomputing.

[3]  Min Gan,et al.  A hybrid approach for parameter optimization of RBF-AR model , 2010, 49th IEEE Conference on Decision and Control (CDC).

[4]  Christian W. Dawson,et al.  A review of genetic algorithms applied to training radial basis function networks , 2004, Neural Computing & Applications.

[5]  Carlos Gomes da Silva,et al.  Time series forecasting with a non-linear model and the scatter search meta-heuristic , 2008, Inf. Sci..

[6]  Junhong Nie,et al.  Constructing fuzzy model by self-organizing counterpropagation network , 1995, IEEE Trans. Syst. Man Cybern..

[7]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[8]  Thomas F. Coleman,et al.  Optimization Toolbox User's Guide , 1998 .

[9]  Min Gan,et al.  A locally linear RBF network-based state-dependent AR model for nonlinear time series modeling , 2010, Inf. Sci..

[10]  Jiwen Dong,et al.  Time-series forecasting using flexible neural tree model , 2005, Inf. Sci..

[11]  Yukihiro Toyoda,et al.  A parameter optimization method for radial basis function type models , 2003, IEEE Trans. Neural Networks.

[12]  Sung-Kwun Oh,et al.  Hybrid optimization of information granulation-based fuzzy radial basis function neural networks , 2010, Int. J. Intell. Comput. Cybern..

[13]  Guoqiang Peter Zhang,et al.  A neural network ensemble method with jittered training data for time series forecasting , 2007, Inf. Sci..

[14]  Juan Julián Merelo Guervós,et al.  Evolving RBF neural networks for time-series forecasting with EvRBF , 2004, Inf. Sci..

[15]  P. W. Strike,et al.  Forecasting and control , 1991 .

[16]  Alaa F. Sheta,et al.  Time-series forecasting using GA-tuned radial basis functions , 2001, Inf. Sci..

[17]  Sung-Kwun Oh,et al.  Identification of fuzzy relation models using hierarchical fair competition-based parallel genetic algorithms and information granulation , 2009 .

[18]  Min Gan,et al.  Stability analysis of RBF network-based state-dependent autoregressive model for nonlinear time series , 2012, Appl. Soft Comput..

[19]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[20]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[21]  Héctor Pomares,et al.  Time series analysis using normalized PG-RBF network with regression weights , 2002, Neurocomputing.

[22]  Chang-Hyun Kim,et al.  Evolving Compact and Interpretable Takagi–Sugeno Fuzzy Models With a New Encoding Scheme , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[23]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[24]  Yinghua Lin,et al.  A new approach to fuzzy-neural system modeling , 1995, IEEE Trans. Fuzzy Syst..

[25]  Sung-Kwun Oh,et al.  Identification of fuzzy models using a successive tuning method with a variant identification ratio , 2008, Fuzzy Sets Syst..

[26]  Benjamin W. Wah,et al.  Global Optimization for Neural Network Training , 1996, Computer.

[27]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[28]  Sung-Kwun Oh,et al.  Structural and parametric design of fuzzy inference systems using hierarchical fair competition-based parallel genetic algorithms and information granulation , 2008, Int. J. Approx. Reason..

[29]  Haiping Du,et al.  Time series prediction using evolving radial basis function networks with new encoding scheme , 2008, Neurocomputing.

[30]  H. Akaike.  A new look at the statistical model identification , 1974 .

[31]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[32]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .