Optimal determination of number of sinusoids in SVD-based spectral emission

Author

Sano, A. ; Tsuji, H.

Author_Institution

Dept. of Electr. Eng., Keio Univ., Yokohama, Japan

fYear

1990

fDate

3-6 Apr 1990

Firstpage

2563

Abstract

Multiple regularization parameters to modify the Moore-Penrose type of pseudo-inverse matrix are introduced. Two methods for determining these optimal parameters are shown: the first is based on minimization of an estimated mean squares error (EMSE) criterion calculated by using only accessible signal data, and the second is based on minimization of the Akaike Bayesian information criterion (ABIC). The proposed schemes can be extensively applied to separation of the signal subspace and noise subspace

Keywords

parameter estimation; spectral analysis; Akaike Bayesian information criterion; SVD-based spectral emission; accessible signal data; estimated mean squares error; noise subspace; optimal parameters; pseudo-inverse matrix; signal subspace; singular value decomposition; sinusoids; Additive white noise; Bayesian methods; Covariance matrix; Least squares approximation; Matrix decomposition; Mean square error methods; Minimization methods; Parameter estimation; Power system reliability; Singular value decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.116131

Filename

116131

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2951995