2-D Unconditional Maximum Likelihood DOA Estimation Based on Majorization-Minimization

doi:10.1109/TVT.2024.3467394

2-D Unconditional Maximum Likelihood DOA Estimation Based on Majorization-Minimization

2025-02-01

0

PRE

AI

DOI：10.1109/TVT.2024.3467394

Original

Original request for help

Save

Abstract

En 中文

In this paper, we propose a majorization-minimization (MM) based refinement strategy tailored for two-dimensional (2-D) unconditional maximum likelihood (UML) direction-of-arrival (DOA) estimation of a single source. We introduce two surrogate functions (linear and quadratic) for 2-D UML DOA estimation with the aim of successively reducing the objective function's value. The proposed MM method guarantees convergence to the objective function's stationary point. Furthermore, we employ the backtracking squared iterative method (SQUAREM) to accelerate the convergence speed of the proposed MM method. Numerical experiments further validate the efficiency of our proposed MM method.

Keywords:

Direction-of-arrival estimation

Unified modeling language

Vectors

Convergence

Maximum likelihood estimation

Linear programming

Minimization

Array signal processing

direction-of-arrival (DOA) estimation

majorization-minimization (MM)

unconditional maximum likelihood (UML)

optimization

2-D Unconditional Maximum Likelihood DOA Estimation Based on Majorization-Minimization

Abstract

Journal

Organization