Stochastic Maximum Likelihood Direction Finding in the Presence of Nonuniform Noise Fields

TL;DR

This paper introduces an ECME algorithm for maximum likelihood direction finding of stochastic, potentially correlated sources in unknown nonuniform noise, ensuring positive semi-definite estimates and demonstrating computational efficiency and stability.

Contribution

The paper develops a novel ECME-based method for direction finding that guarantees positive semi-definite covariance estimates and improves computational stability over existing methods.

Findings

Algorithm effectively estimates source directions in nonuniform noise.

Simulation results show high accuracy and stability.

Method outperforms traditional approaches in computational efficiency.

Abstract

In this letter, we employ and design the expectation--conditional maximization either (ECME) algorithm, a generalisation of the EM algorithm, for solving the maximum likelihood direction finding problem of stochastic sources, which may be correlated, in unknown nonuniform noise. Unlike alternating maximization, the ECME algorithm updates both the source and noise covariance matrix estimates by explicit formulas and can guarantee that both estimates are positive semi-definite and definite, respectively. Thus, the ECME algorithm is computationally efficient and operationally stable. Simulation results confirm the effectiveness of the algorithm.