Journal Article10.1109/tccn.2024.3360527
Deep Learning-Based DOA Estimation
Shilian Zheng,Zhuang Yang,Weiguo Shen,Luxin Zhang,Jiawei Zhu,Zhijin Zhao,Xiaoniu Yang +6 more
15
TL;DR: Deep learning-based DOA estimation using I/Q components outperforms existing methods.
read more
Abstract: 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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Edge-Enhanced Dual-Stream Perception Network for Monocular Depth Estimation
Zihang Liu,Quande Wang +1 more
TL;DR: A new edge-enhanced dual-stream monocular depth estimation method that achieves better performance for monocular depth estimation and has good generalization capabilities for various scenarios and real-world images is introduced.
2
Unsupervised Spectrum Anomaly Detection With Distillation and Memory Enhanced Autoencoders
NULL AUTHOR_ID,NULL AUTHOR_ID,NULL AUTHOR_ID,Jinyang He,NULL AUTHOR_ID,NULL AUTHOR_ID +5 more
TL;DR: This study proposes a novel unsupervised spectrum anomaly detection method using knowledge distillation and memory-enhanced autoencoders, achieving improved accuracy and localization capabilities on synthetic and real-world spectral data, including IQ signals.
2
Direction of Arrival Joint Prediction of Underwater Acoustic Communication Signals Using Faster R-CNN and Frequency–Azimuth Spectrum
Le Cheng,Yue Liu,Bingbing Zhang,Zhengliang Hu,Hongna Zhu,Bin Luo +5 more
TL;DR: This study redefines the task of UWAC signal detection as an object detection problem within the frequency–azimuth (FRAZ) spectrum and proposes a method that consistently outperforms existing techniques across all signal-to-noise ratios (SNRs), particularly excelling in low SNRs.
1
Multi-RIS-Assisted 3D Localization and Synchronization via Deep Learning
Alireza Fadakar,Maryam Sabbaghian,Henk Wymeersch +2 more
TL;DR: Multi-RIS-assisted 3D localization and synchronization via deep learning achieves high accuracy and robustness against multipath effects.
1
Deep Learning-Based Blind Estimation of Symbol Rate
Shiqi Zhang,Tao Chen,Shilian Zheng +2 more
- 19 Apr 2024
TL;DR: This paper proposes a deep learning-based method for blind symbol rate estimation from complex baseband signals, leveraging a ResNet to extract latent features from IQ components, outperforming existing methods in AWGN and Rayleigh channels.
References
Compressive Sensing in Electromagnetics - A Review
TL;DR: A review of the state-of-the-art and most recent advances of compressive sensing and related methods as applied to electromagnetics can be found in this article, where a wide set of applicative scenarios comprising the diagnosis and synthesis of antenna arrays, the estimation of directions of arrival, and the solution of inverse scattering and radar imaging problems are reviewed.
376
Detectors for discrete-time signals in non-Gaussian noise
James H. Miller,John B. Thomas +1 more
TL;DR: The structure and performance of a class of nonlinear detectors for discrete-time signals in additive white noise are investigated and three general classes of symmetric, unimodal, univariate probability density functions are introduced that are generalizations of the Gaussian, Cauchy, and beta distributions.
319
Maximum-likelihood narrow-band direction finding and the EM algorithm
TL;DR: Generalized EM (expectation-maximization) algorithms have been derived for the maximum-likelihood estimation of the direction-of-arrival of multiple narrowband signals in noise and it is shown via simulation that themaximum- likelihood method allows for the resolution of the directions- of-ar arrival of signals at angular separation and noise levels for which other high-resolution methods will not work.
235
Deep Networks for Direction-of-Arrival Estimation in Low SNR
TL;DR: This work introduces a Convolutional Neural Network that predicts angular directions using the sample covariance matrix estimate and presents a training method, where the CNN learns to infer their number and predict the DoAs with high confidence.
210
A Discretization-Free Sparse and Parametric Approach for Linear Array Signal Processing
Zai Yang,Lihua Xie,Cishen Zhang +2 more
TL;DR: An exact discretization-free method, named as sparse and parametric approach (SPA), is proposed for uniform and sparse linear arrays that carries out parameter estimation in the continuous range based on well-established covariance fitting criteria and convex optimization and is statistically consistent under uncorrelated sources.