COMPARATIVE ANALYSIS OF BIFURCATION TIME SERIES(<Special Issue>Contribution to 21 Century Intelligent Technologies and Bioinformatics)

Abstract

The time series analysis (ARIMA models) is a good approach for identification of time series. But, if we have structural break in the time series, we cannot create only one model of time series. Further more, if we don't have enough data between two structural breaks, it's impossible to create valid time series models for identification of the time series. This paper explores the possibility of identification of the inflation process dynamics via of the system-theoretic, by means of both Box-Jenkins ARIMA methodologies and artificial neural networks. The structural break problem can be overcomed by using NN for system identification of unknown order with finite number of breaks.