LOCAL FILTERING OF NOISY NONLINEAR TIME-SERIES

We investigate the use of different local nonlinear modelling and nonl inear filtering techniques to clean a noisy time series obtained from a deterministic chaotic systems. The methods are tested on data from t he Ikeda map and the Mackey-Glass delay differential equation. We test the results of the filtered times series using the correlation dimens ion statistic and SNR gain. In all cases we see that local filtering h as produced a new time series which is more consistent with the origin al clean time series. (C) 1998 Published by Elsevier Science B.V.