Sammanfattning
In this paper, we propose a novel 1-D spectral
estimator for signals with mixed spectra. The proposed method
is partly based on the recently introduced smooth spectral
estimator LIMES, in which the smoothness is accounted for by
assuming linearity within predefined segments of the spectrum.
The proposed method utilizes this formulation but also allows
segments to change size to better estimate the spectrum, thereby
allowing for the estimation of spectra that are neither completely
smooth or sparse in frequency, but rather contains a mixture
of such components. Using simulated data, we illustrate the
performance of the proposed estimator, comparing to other recent
spectral estimation techniques.
estimator for signals with mixed spectra. The proposed method
is partly based on the recently introduced smooth spectral
estimator LIMES, in which the smoothness is accounted for by
assuming linearity within predefined segments of the spectrum.
The proposed method utilizes this formulation but also allows
segments to change size to better estimate the spectrum, thereby
allowing for the estimation of spectra that are neither completely
smooth or sparse in frequency, but rather contains a mixture
of such components. Using simulated data, we illustrate the
performance of the proposed estimator, comparing to other recent
spectral estimation techniques.
| Originalspråk | engelska |
|---|---|
| Titel på värdpublikation | 26th European Signal Processing Conference, EUSIPCO 2018. |
| Förlag | IEEE - Institute of Electrical and Electronics Engineers Inc. |
| Sidor | 2345-2349 |
| ISBN (tryckt) | 978-908279701-5 |
| DOI | |
| Status | Published - 2018 |
Ämnesklassifikation (UKÄ)
- Sannolikhetsteori och statistik