Adaptive regularization method with application to sinusoidal frequency estimation

Author

Liu, Sheng ; Xiang, Jingcheng

Author_Institution

Inst. of Electron. Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

fYear

1998

fDate

1998

Firstpage

137

Abstract

A novel nonparametric method for super-resolution frequency estimation from a noisy sinusoidal sequence is presented. The main idea of the method is to make use of data-adaptive weighted regularization based on iteration techniques. With a fast algorithm the computational cost of the proposed method is moderate. Furthermore, the method does not need the a priori knowledge of the superimposed sinusoid´s number and any additional information such as frequency domain bandwidth and energy distribution

Keywords

adaptive signal processing; frequency estimation; iterative methods; nonparametric statistics; sequences; signal resolution; signal sampling; computational cost; data-adaptive weighted regularization; iteration techniques; noisy sinusoidal sequence; nonparametric method; super-resolution frequency estimation; Bandwidth; Computational efficiency; Convergence; Energy resolution; Frequency domain analysis; Frequency estimation; Gaussian noise; Multiple signal classification; Numerical stability; Signal resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-4325-5

Type

conf

DOI

10.1109/ICOSP.1998.770169

Filename

770169