Title :
Amplitude and phase estimator study in Prony method for noisy exponential data
Author :
Ducasse, Alain ; Mailhes, Corinne ; Castanie, Francis
Author_Institution :
ENSEEIHT, Toulouse, France
Abstract :
The Prony method is a technique for modeling a data set of N samples using a linear combination of p exponentials (N>p) in a least square estimation procedure. In this paper, a study of the amplitude and phase estimator is presented. In particular, theoretical results are given for bias and variance, which are confirmed by simulations. An optimal number of equations in the corresponding least square estimation procedure is derived, minimizing estimation errors
Keywords :
amplitude estimation; least squares approximations; phase estimation; spectral analysis; Prony method; amplitude estimator; bias; estimation errors; least square estimation procedure; modeling; noisy exponential data; phase estimator; simulations; variance; Amplitude estimation; Damping; Equations; Frequency estimation; Least squares approximation; Noise level; Phase estimation; Phase noise; Polynomials; Yield estimation;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2431-5
DOI :
10.1109/ICASSP.1995.480085
