Title :
Non-linear instantaneous least squares and its high SNR analysis
Author :
Ängeby, J. ; Viberg, M. ; Gustafsson, T.
Author_Institution :
Dept. of Signals & Syst., Chalmers Univ. of Technol., Goteborg, Sweden
Abstract :
A novel approach for signal parameter estimation, named the non-linear instantaneous least squares (NILS) estimator, is proposed and a high SNR statistical analysis of the estimates is presented. The algorithm is generally applicable to deterministic signal in noise models. However, it is of particular interest in applications where the “conventional” non-linear least squares criterion suffers from numerous local minima. The key idea here is to apply a sliding window to estimate the instantaneous amplitude, which is then used in a separable least squares criterion-function. Hereby the radius of attraction of the global minimum is under the control of the user, which makes the NILS approach advantageous to use in practical applications. Numerical results using polynomial-phase signals validate the theoretical results
Keywords :
amplitude estimation; least squares approximations; noise; nonlinear estimation; signal processing; statistical analysis; algorithm; deterministic signal; global minimum; high SNR statistical analysis; instantaneous amplitude estimation; local minima; noise models; nonlinear instantaneous least squares; polynomial-phase signals; radius of attraction; separable least squares criterion-function; signal parameter estimation; sliding window; Amplitude estimation; Least squares approximation; Least squares methods; Maximum likelihood estimation; Parameter estimation; Polynomials; Signal processing; Signal processing algorithms; Signal to noise ratio; Statistical analysis;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on
Conference_Location :
Phoenix, AZ
Print_ISBN :
0-7803-5041-3
DOI :
10.1109/ICASSP.1999.756212