期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 61, 期 23, 页码 5807-5818出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2013.2272924
关键词
Covariance matrix estimation; elliptically symmetric distributions; expected likelihood; likelihood ratio; regularization
资金
- DGA/MRIS [2012.60.0012.00.470.75.01]
In Abramovich et al. [Bounds on Maximum Likelihood Ratio-Part I: Application to Antenna Array Detection-Estimation With Perfect Wavefront Coherence, IEEE Trans. Signal Process., vol. 52, pp. 1524-1536, June 2004], it was demonstrated, for multivariate complex Gaussian distribution, that the probability density function (p.d.f.) of the likelihood ratio (LR) for the (unknown) actual covariance matrix R-0 does not depend on this matrix and is fully specified by the matrix dimension and the number of independent training samples. This invariance property hence enables one to compare the LR of any derived covariance matrix estimate against this p.d.f., and eventually get an estimate that is statistically as likely as R-0. This expected likelihood quality assessment allowed significant improvement of MUSIC DOA estimation performance in the so-called threshold area, and for diagonal loading and TVAR model order selection in adaptive detectors. Recently, the so-called complex elliptically symmetric (CES) distributions have been introduced for description of highly in-homogeneous clutter returns. The aim of this series of two papers is to extend the EL approach to this class of CES distributions as well as to a particularly important derivative, namely the complex angular central distribution (ACG). For both cases, we demonstrate a similar invariance property for the LR associated with the true scatter matrix Sigma(0). Furthermore, we derive fixed point regularized covariance matrix estimates using the generalized expected likelihood methodology. This first part is devoted to the conventional scenario (T >= M) while Part II deals with the undersampled scenario (T <= M).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据