Deep Learning-Based DOA Estimation

doi:10.1109/TCCN.2024.3360527

Deep Learning-Based DOA Estimation

2024-06-01

10

OA

AI

DOI：10.1109/TCCN.2024.3360527

Original

Original request for help

Save

Abstract

En 中文

Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications in many fields. In recent years, deep learning has been applied to DOA estimation to improve the performance. However, most existing deep learning-based DOA estimation methods extract DOA information from the covariance matrix (CM) input. In this paper, we introduce a novel deep learning-based DOA estimation scheme that utilizes the raw in-phase (I) and quadrature (Q) components of the signal as the input. We formulate the problem as single-label classification and multi-label classification based on the number of signal sources. We design a convolutional neural network to solve the problems and to adapt to different number of snapshots. We also propose a deep learning regression-based method to overcome the limitations of classify-based methods in dealing with off-grid angles. We conduct extensive experiments with simulations and over-the-air collected signals to analyze the performance of the proposed method in various scenarios including different SNRs, additive generalized Gaussian noise (AGGN) and extreme multi-source DOA estimation. Results demonstrate that our proposed method outperforms the existing deep learning-based DOA estimation methods.

Keywords:

Direction-of-arrival estimation

Estimation

Covariance matrices

Adaptation models

Training

Convolutional neural networks

Antenna arrays

Direction-of-arrival (DOA) estimation

deep learning

residual neural network

classification

regression

Deep Learning-Based DOA Estimation

Abstract

Journal

Organization