Chaotic Time Series Prediction Based on Radial Basis Function Network

A prediction method for chaotic time series, based on radial basis function (RBF) network, is proposed. First, two important parameters for reconstructing phase space, the time delay and the embedding dimension, are estimated by correlation integral method, and the embedding dimension is the number of input units. Second, RBF centers are optimized by means of the cross iterative fuzzy clustering algorithm (CIFCA) and the regularized orthogonal least squares algorithm (ROISA), and the selected RBF centers construct hidden units. The proposed method centralizes advantages of CIFCA and ROISA, and it can decrease network scale, improve generalization performance, accelerate network training speed and avoid ill-conditioning of learning problems. A case of known chaotic system, Rollser system, verifies validity of the proposed method.