A Computer System for Signals Modelling and Prediction

The paper is concerned with a computer system for signal analysis, identification, and prediction. The system offers a possibility of signal modeling with the use of Box-Jenkins methodology, neural networks, bilinear and hybrid linear-bilinear models. The system makes possible signal forecasting on the basis of linear, neural, bilinear and hybrid linear-bilinear predictors. The aim of the paper is to present the system as well as the results obtained for signals coming from biological, economic, and technical processes.