ICASSP International Conference on Acoustics, Speech and Signal Processing location:Hong Kong, Japan date:6-10 April 2003
A novel method for determining the set of parameters
for a phase space representation of a time series is proposed.
Based upon thedifferential entropy, both theoptimal embedding
dimension m, and time lag r, are simultaneously determined.
The choice of these parameters is closely related to
the length of the optimal tap input delay line of an adaptive
filter or time-delay neural network. The method employs a
singlecriterion-the “entropyratio” between the phase space
representation of a signal and an ensemble of its surrogates
- and is first systematically tested on synthetic time series
for which the optimal embedding parameters are known, after
which it is verified on a number of benchmark real-world
time series. The proposed entropy ratio method is shown to
consistently outperform some well-established methods.