Title :
Constrained least-squares estimation of a random amplitude sinusoid
Author_Institution :
Dept. of Avionics & Syst., ENSICA, Toulouse, France
Abstract :
A new method for estimating the frequency of a random amplitude sinusoid is proposed. It is based upon solving overdetermined Yule-Walker equations using constrained least-squares techniques. A Gauss-Newton algorithm is derived for proceeding to the constrained minimization. Simulation results prove the superiority of the new method over the unconstrained method, specially for a small number of equations
Keywords :
Newton method; estimation theory; frequency estimation; least squares approximations; random processes; signal processing; Gauss-Newton algorithm; constrained least-squares estimation; constrained minimization; frequency estimation; overdetermined Yule-Walker equations; random amplitude sinusoid; simulation results; unconstrained method; Aerospace electronics; Amplitude estimation; Amplitude modulation; Doppler radar; Equations; Frequency estimation; Independent component analysis; Least squares methods; Newton method; Polynomials;
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.1995.480080
