Nonlinear time series modeling and prediction using local variable weights RBF network

Authors:
Garba Inoussa;Usman Babawuro
Affiliations:
College of Information Science and Engineering, Central South University, Changsha, Hunan, P.R. China;Department of Computer Science, Central South University, Changsha, Hunan, P.R. China
Venue:
SEMCCO'11 Proceedings of the Second international conference on Swarm, Evolutionary, and Memetic Computing - Volume Part I
Year:
2011

Citing 13
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Radial basis function based adaptive fuzzy systems and their applications to system identification and prediction

Fuzzy Sets and Systems
Forecasting Time Series Combining Machine Learning and Box-Jenkins Time Series

IBERAMIA 2002 Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence
A tutorial on support vector regression

Statistics and Computing
Forecasting enrollments using high-order fuzzy time series and genetic algorithms: Research Articles

International Journal of Intelligent Systems
Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study

Neural Processing Letters
Time Series Prediction Based on Linear Regression and SVR

ICNC '07 Proceedings of the Third International Conference on Natural Computation - Volume 01
Hybridization of intelligent techniques and ARIMA models for time series prediction

Fuzzy Sets and Systems
Time series prediction using evolving radial basis function networks with new encoding scheme

Neurocomputing
Time-series forecasting using flexible neural tree model

Information Sciences: an International Journal
Time-series prediction using a local linear wavelet neural network

Neurocomputing
Radial basis function networks, regression weights, and the expectation-maximization algorithm

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Forecasting time series with genetic fuzzy predictor ensemble

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a Local Variable-Weights RBF Network (LVW-RBFN) with the aim to address the problem of modeling and prediction of nonlinear time series. The proposed model is a four layered RBFN comprising of input layer, hidden layer, weight layer and output layer. The LVW-RBFN is an enhanced type of RBF network, in which the constant weights that connect the hidden layer with the output layer in the standard RBFN are replaced by functions of the RBFN's inputs computed via the weight layer. This model has the merit of making usage of more linear parameters and learning the dynamic of nonlinear time series through the hidden and weight layers. An offline optimization technique known as Structured Nonlinear Parameter Optimization Method (SNPOM) was used to estimate the model. Simulation results for the modeling and prediction of some nonlinear time-series show the feasibility and effectiveness of the proposed model.