A robust method for the identification of non-Gaussian autoregressive systems in colored Gaussian noise

This paper introduces a novel technique for parameter estimation of an autoregressive (AR) all-pole process under non-Gaussian noise environment using third order cumulants of the observed sequence. The proposed AR parameters estimation technique is based on formulating a particular structured matrix with entries of third order cumulants of the observed output sequence only. This matrix almost possesses a full rank structure. The observed sequence may be contaminated with additive Gaussian noise (white or colored), whose power spectral density is unknown. The system is driven by a zero-mean independent and identically distributed (i.i.d) non-Gaussian sequence. Simulation results confirm the good numerical conditioning of the algorithm and the improvement in performance with respect to well-known methods even when the observed signal is heavily contaminated with Gaussian noise.

Download Full-text

Joint Signal Parameter Estimation in Non–Gaussian Noise by the Method of Polynomial Maximization

Journal of Electrical Engineering ◽

10.1515/jee-2016-0031 ◽

2016 ◽

Vol 67 (3) ◽

pp. 217-221 ◽

Cited By ~ 8

Author(s):

Volodymyr Palahin ◽

Jozef Juhár

Keyword(s):

Parameter Estimation ◽

Gaussian Noise ◽

Parameters Estimation ◽

Polynomial Algorithms ◽

Signal Parameter ◽

The Third ◽

Nonlinear Processing ◽

Joint Parameters ◽

The Moment ◽

Non Gaussian

Abstract This paper considers the adaptation of the method of polynomial maximization for synthesis of the polynomial algorithms of joint signal parameter estimation in non-Gaussian noise. It is shown that the nonlinear processing of samples, the moment and the cumulant description of random variables in the form of cumulant coefficients of the third and higher orders can decrease the variance of joint parameters estimation as compared with the well-known results.

Download Full-text

The Wiener Third-Order-Statistics-Based Compensator of the Non-Gaussian Noise

Telecommunications and Radio Engineering ◽

10.1615/telecomradeng.v65.i6.70 ◽

2006 ◽

Vol 65 (6) ◽

pp. 581-587

Author(s):

V. A. Tikhonov ◽

K. V. Netrebenko ◽

I. V. Savchenko

Keyword(s):

Order Statistics ◽

Gaussian Noise ◽

Third Order ◽

Non Gaussian

Download Full-text

Parameters Estimation Algorithm of Near-Field Cyclostationary Source Based on Propagator

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.962-965.2909 ◽

2014 ◽

Vol 962-965 ◽

pp. 2909-2912 ◽

Cited By ~ 1

Author(s):

Li Guo Wang

Keyword(s):

Near Field ◽

Gaussian White Noise ◽

Estimation Algorithm ◽

Parameters Estimation ◽

Music Algorithm ◽

Third Order ◽

Estimation Problems ◽

Dimensional Parameters ◽

Non Gaussian ◽

Value Decomposition

An improved MUSIC algorithm based on third-order cyclic moment is proposed to estimate the bearing and range parameters of near-field cyclostationary sources. The algorithm adopts the uniform linear array, structures the third-order cyclic moment matrix by the array outputs, and utilizes the propagator method to replace the singular value decomposition, calculate the signal noise subspace directly. Compared with the traditional MUSIC algorithm, the proposed algorithm has high estimation precision and low computational complexity, and effectively solves the two-dimensional parameters estimation problems of near-field cyclostationary sources in the case of interfering signals and non-Gaussian white noise. The performance of the proposed method can be verified by computer simulations.

Download Full-text

Micro-motion parameters estimation in non-Gaussian noise via mutual correntropy

2017 IEEE Radar Conference (RadarConf) ◽

10.1109/radar.2017.7944314 ◽

2017 ◽

Author(s):

Dingding Xiong ◽

Guolong Cui ◽

Shisheng Guo ◽

Lifang Feng ◽

Xiaobo Yang

Keyword(s):

Gaussian Noise ◽

Parameters Estimation ◽

Micro Motion ◽

Motion Parameters ◽

Non Gaussian

Download Full-text

A New Technique for ARMA-System Identification Based on QR-Decomposition of Third Order Cumulants Matrix

International Journal of Circuits, Systems and Signal Processing ◽

10.46300/9106.2021.15.173 ◽

2021 ◽

Vol 15 ◽

pp. 1607-1612

Author(s):

Adnan M Al-Smadi

Keyword(s):

Moving Average ◽

Estimation Method ◽

Qr Decomposition ◽

New Technique ◽

Autoregressive Moving Average ◽

Third Order ◽

Power Spectral ◽

Q Model ◽

A New Technique ◽

Non Gaussian

In this paper a new technique to estimate the coefficients of a general Autoregressive Moving Average (ARMA) (p, q) model is proposed. The ARMA system is excited by an un-observable independently identically distributed (i.i.d) non-Gaussian process. The proposed ARMA coefficients estimation method uses the QR-Decomposition (QRD) of a special matrix built with entries of third order cumulants (TOC) of the available output data only. The observed output may be corrupted with additive colored or white Gaussian noise of unknown power spectral density. The proposed technique was compared with several good methods such as the residual time series (RTS) and the Q-slice algorithm (QSA) methods. Simulations for several examples were tested. The results for these examples confirm the good performance of the proposed technique with respect to existing well-known methods.

Download Full-text