A PREDICTION METHOD OF NONSTATIONARY TIME-SERIES DATA BY USING A MODULAR STRUCTURED NEURAL-NETWORK

This paper proposes a prediction method for non-stationary time series data with time varying parameters. A modular structured type neural n etwork is newly introduced for the purpose of grasping the changing pr operty of time varying parameters. This modular structured neural netw ork is constructed by the hierarchical combination of each neural netw ork (NNT: Neural Network for Prediction of Time Series Data) and a neu ral network (NNW: Neural Network for Prediction of Weights). Next, we propose a reasonable method for determination of the length of the loc al stationary section by using the additive learning ability of neural networks. Finally, the validity and effectiveness of the proposed met hod are confirmed through simulation and actual experiments.