Asymptotic analysis of an algorithm for identification of quantized AR time-series

Author

Krishnamurthy, Vikram ; Poor, H. Vincent

Author_Institution

Dept. of Electr. & Electron. Eng., Melbourne Univ., Parkville, Vic., Australia

Volume

3

fYear

1995

fDate

9-12 May 1995

Firstpage

2028

Abstract

Krishnamurthy and Mareels presented a parameter estimation algorithm called the binary series estimation algorithm (BSEA) for Gaussian auto-regressive (AR) time series given 1-bit quantized noisy measurements. The present authors carry out an asymptotic analysis of the BSEA for Gaussian AR models. In particular, from a central limit theorem they obtain expressions for the asymptotic covariances of the parameter estimates. From this they: (1) Present an algorithm for estimating the order of an AR series from one-bit quantized measurements. (2) Theoretically they justify why BSEA can yield better estimates than the Yule-Walker methods in some cases

Keywords

Gaussian processes; autoregressive processes; covariance analysis; interference (signal); parameter estimation; quantisation (signal); signal processing; time series; Gaussian AR models; Gaussian auto-regressive time series; asymptotic analysis; asymptotic covariances; binary series estimation algorithm; central limit theorem; identification; one-bit quantized measurements; parameter estimate; parameter estimation algorithm; quantized AR time-series; Algorithm design and analysis; Computer simulation; Electric variables measurement; Gaussian noise; Noise measurement; Parameter estimation; Particle measurements; Time measurement; Time series analysis; Yield estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.480673

Filename

480673