Title :
G-spectral estimation
Author_Institution :
Southern Methodist University, Dallas, Texas
Abstract :
In [1], 1971, a transformation referred to as the G-Transformation was introduced by H. L. Gray, T. A. Atchison and G. V. McWilliams. The transformation was shown to be of value in evaluating improper integrals and was especially effective in those cases where the integrand behaved like a linear combination of exponentials with real or complex arguments. These ideas have more recently ([2,3] 1976-77) been utilized to define a spectral estimator referred to as the G-Spectral Estimator. In this paper the nature of the G-transform and G-Spectral estimator are discussed and it is pointed out that such an estimator is most appropriate for processes whose autocorrelations behave as a linear combination of exponentials with real or complex arguments.
Keywords :
Autocorrelation; Equations; Fourier transforms; Stochastic processes;
Conference_Titel :
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '77.
DOI :
10.1109/ICASSP.1977.1170280