Efficient use of correlation entropy for analysing time series data

摘要

The correlation dimension D_2 and correlation entropy K_2 are both important quantifiers in nonlinear time series analysis. However, use of D_2 has been more common compared to K_2 as a discriminating measure. One reason for this is that D_2 is a static measure and can be easily evaluated from a time series. However, in many cases, especially those involving coloured noise, K_2 is regarded as a more useful measure. Here we present an efficient algorithmic scheme to compute K_2 directly from a time series data and show that K_2 can be used as a more effective measure compared to D_2 for analysing practical time series involving coloured noise.