Parametric estimation of the third-order spectra of the mixture of a non-Gaussian signal and Gaussian correlated interference

V. A. Tikhonov; K. V. Netrebenko

doi:10.3103/S0735272705020044

Authors

V. A. Tikhonov Kharkiv National University of Radioelectronics, Ukraine
K. V. Netrebenko Kharkiv National University of Radioelectronics, Ukraine

DOI:

https://doi.org/10.3103/S0735272705020044

Abstract

The paper is devoted to application of higher-order spectra for estimating the spectrum of a non-Gaussian process in combination with Gaussian correlated interference. The derived expressions for parametric estimation of higher-order spectra are used for estimating the spectra of non-Gaussian processes described by generalized autoregression models. The obtained parametric spectral estimates of the third order are compared with similar estimates calculated by known methods based on the Fourier transform.

References

BRILLINGER, D.R. Time Series. Data Analysis and Theory. Holt, Rinehart and Winston, Inc., 1975.

SHIRYAYEV, A.N. Teoriya Veroyatnosti i Yeyo Primeneniye, n.3, 5, p.293-313, 1960.

LEONOV, V.P. Some Applications of Higher Semi-Invariants in the Theory of Stationary Random Processes [in Russian]. Moscow: Nauka, 1964.

MALAKHOV, A.N. Cumulant Analysis of Random Non-Gaussian Processes and of Their Transforms [in Russian]. Moscow: Sov. Radio, 1978.

MARPLE Jr., S.L. Digital Spectral Analysis with Applications. Prentice-Hall, 1987.

SHALTANITE, V. Estimation of parameters of an autoregressive sequence measured in the presence of additive interference. Statistical Problems of Control, Vilnius, Institute of Mathematics and Cybernetics of AS LSSR, n.39, p.55-73, 1979.

TIKHONOV, V.A.; RUSANOVSKII, D.Y.; TIKHONOV, D.V. Radioelektronika i Informatika, n.4, p.83-85, 1999.