In this paper, the frequencies estimation of two-dimensional (2-D) superimposed exponential model in zero-mean multiplicative and additive noise which is stationary, is considered by a computationally efficient statistics based iterative algorithm. The model we considered is a more general evanescent part of stationary random field as well as an important model in statistical signal processing and texture classifications. It is observed that the estimator is consistent and works quite well in terms of biases and mean squared errors. Moreover, the asymptotic distribution of the estimators for the frequencies is multivariate normal and the estimators attain the same convergence rate as the Least Squares Estimator (LSE) in additive noise. Finally, the effectiveness of the algorithm and the asymptotic results of the estimators for finite sample is verified via some numerical experiments.
Digital Object Identifier (DOI)
Bian, Jiawen; Xing, Jing; Peng, Huiming; and Li, Hongwei
"MTSI Algorithm for Frequencies Estimation of 2-D Superimposed Exponential Model in Multiplicative and Additive Noise which is Stationary,"
Applied Mathematics & Information Sciences: Vol. 08:
4, Article 34.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol08/iss4/34