Current Proceedings on Technology
Yazarlar: Yulia Maslennikova, Bochkarev Bochkarev
Konular:-
Anahtar Kelimeler:Forecasting,Singular spectrum analysis,Neural network,Long-term prediction
Özet: In this article, we propose a combination of a noise-reduction algorithm based on Singular Spestrum Analysis (SSA) and a standard feedforward neural prediction model. Basically, the proposed algorithm consists of two different steps: data preprocessing based on the SSA filtering method and step-by-step training procedure in which we use a simple feedforward multilayer neural network with backpropagation learning. The proposed noise-reduction procedure successfully removes most of the noise. That increases long-term predictability of the processed dataset comparison with the raw dataset. The method has been applied to predict the International sunspot number RZ time series. The results show that our combined technique has better performances than those offered by the same network directly applied to the raw dataset.