Time series: theory and methods
Time series: theory and methods
A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Nonstationary signal parameter estimation/detection is challenging on account of the underlying stationarity assumption in most of the known classical techniques. We present a framework for a class of nonstationary processes via a multiscale analysis. This framework allows us to gain insight into the problem, and we obtain new results on multiscale ARIMA processes. We show the possibility of inducing stationarity at different resolution levels of nonstationary processes by an appropriate wavelet transform. This permits us to use classical estimation/detection techniques. The approach is also extended to wavelet packet decompositions.