In the last years, growing attention has been paid to the reconstruction of chaotic attractors from one or more observables. In this paper a Multi Layer Perceptron with a tapped line as input, is used to forecast the hypercaotic Rössler system state variables starting from measurements of one observable. Results show satisfactory prediction performance if a sufficient number of taps is used. Moreover, a sensitivity analysis has been performed to evaluate the predictiveness of the different delayed input in the neural network model.
FORECASTING OF HYPERCHAOTIC SYSTEM STATE VARIABLES USING ONE OBSERVABLE
CANNAS, BARBARA;
2008-01-01
Abstract
In the last years, growing attention has been paid to the reconstruction of chaotic attractors from one or more observables. In this paper a Multi Layer Perceptron with a tapped line as input, is used to forecast the hypercaotic Rössler system state variables starting from measurements of one observable. Results show satisfactory prediction performance if a sufficient number of taps is used. Moreover, a sensitivity analysis has been performed to evaluate the predictiveness of the different delayed input in the neural network model.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I metadati presenti in IRIS UNICA sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono protetti da diritto d'autore, salvo diversa indicazione.
