Bayesian Estimation of Class A Noise Parameters with Hidden Channel States

Author

Jiang, Yu-Zhong ; Hu, Xiu-lin ; Kai, Xu ; Qi, Zhai

Author_Institution

Huazhong Univ. of Sci. & Technol., Wuhan

fYear

2007

fDate

26-28 March 2007

Firstpage

2

Lastpage

4

Abstract

The Middleton Class A interference model is statistical-physical and parametric model for man-made and natural electromagnetic interference. In this letter, the efficient Bayesian estimator of the Class A model parameters is derived and calculated by the Gibbs sampler, a Markov Chain Monte Carlo (MCMC) procedure. The estimator can estimate two-parameter and hidden states for Class A noise model simultaneously. Simulation of this estimator with small sample sizes indicates that this technique is efficient and near-optimal performance.

Keywords

Bayes methods; Markov processes; Monte Carlo methods; channel estimation; electromagnetic interference; parameter estimation; signal detection; Bayesian estimation; Gibbs sampler; Markov Chain Monte Carlo process; Middleton Class A interference model; electromagnetic interference; hidden channel states; noise parameters; signal detection; Background noise; Bayesian methods; Electromagnetic interference; Gaussian distribution; Gaussian noise; Monte Carlo methods; Parameter estimation; Signal processing algorithms; State estimation; Working environment noise; Impulsive Noise; Middleton Class A Model; Non-Gaussian Noise; Parameter Estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Line Communications and Its Applications, 2007. ISPLC '07. IEEE International Symposium on

Conference_Location

Pisa

Print_ISBN

1-4244-1090-8

Electronic_ISBN

1-4244-1090-8

Type

conf

DOI

10.1109/ISPLC.2007.371088

Filename

4231662