Local spectral analysis using wavelet packets
2001 (English)In: Circuits, systems, and signal processing, ISSN 0278-081X, E-ISSN 1531-5878, Vol. 20, no 5, 497-528 p.Article in journal (Refereed) Published
Wavelet packets are a useful extension of wavelets, which are of wide potential use in a statistical context. In this paper, an approach to the local spectral analysis of a stationary time series based on wavelet packet decomposition is developed. This involves extensions to the wavelet context of standard time series ideas such as the periodogram and spectrum. Some asymptotic properties of the new estimate are provided. The technique is illustrated by simulated signals and its application to physiological data, and its potential use in studies of time-dependent spectral analysis is discussed.
Place, publisher, year, edition, pages
Birkhäuser Verlag, 2001. Vol. 20, no 5, 497-528 p.
Wavelet transform, wavelet packets, multiresolution analysis, second-order stationary process, spectral estimation, wavelet packet spectrum
Probability Theory and Statistics
Research subject Mathematical Statistics
IdentifiersURN: urn:nbn:se:umu:diva-63696DOI: 10.1007/BF01201975ISI: 000171785300002OAI: oai:DiVA.org:umu-63696DiVA: diva2:582374