Title :
Nonlinear time series forecasting with dynamic RBF neural networks
Author :
Zhang, Dongqing ; Ning, Xuanxi ; Liu, Xueni ; Han, Yubing
Author_Institution :
Coll. of Econ.&Manage., Nanjing Univ. of Aeronaut. & Astronaut., Nanjing
Abstract :
In order to cope with nonlinear time series, a variable structure radial basis function (RBF) networks model, in which the numbers of basis functions and input order vary over time, is proposed in this paper. Then sequential Monte Carlo (SMC) method is used for time series on-line prediction and corresponding algorithm is developed. At last, the data of weekly price of the shipbuilding steel product are analyzed, and experimental results indicate that the variable structure RBF networks model proposed is effective.
Keywords :
Monte Carlo methods; forecasting theory; radial basis function networks; time series; RBF neural networks; SMC; nonlinear time series forecasting; radial basis function; sequential Monte Carlo method; time series online prediction; Autoregressive processes; Economic forecasting; Intelligent control; Monte Carlo methods; Neural networks; Prediction algorithms; Predictive models; Radial basis function networks; Sliding mode control; Steel; Prediction; Radial Basis Function Neural Networks; Sequential Monte Carlo Methods;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4593999
