An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR

Li, Yingchun; Zhou, Zhengjie; Chen, Cheng; Wu, Peng; Zhou, Zhiquan

doi:10.3390/axioms12090862

Open AccessArticle

An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR

by

Yingchun Li

¹,

Zhengjie Zhou

¹

,

Cheng Chen

^2,*,

Peng Wu

³ and

Zhiquan Zhou

¹

School of Information Science and Engineering, Harbin Institute of Technology, Weihai 264209, China

²

School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an 710072, China

³

Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China

^*

Author to whom correspondence should be addressed.

Axioms 2023, 12(9), 862; https://doi.org/10.3390/axioms12090862

Submission received: 16 July 2023 / Revised: 23 August 2023 / Accepted: 2 September 2023 / Published: 7 September 2023

(This article belongs to the Special Issue Differential Equations and Inverse Problems)

Download

Browse Figures

Versions Notes

Abstract

In this paper, a modified high-efficiency Convolutional Neural Network (CNN) with a novel Supervised Contrastive Learning (SCL) approach is introduced to estimate direction-of-arrival (DOA) of multiple targets in low signal-to-noise ratio (SNR) regimes with uniform linear arrays (ULA). The model is trained using an on-grid setting, and thus the problem is modeled as a multi-label classification task. Simulation results demonstrate the robustness of the proposed approach in scenarios with low SNR and a small number of snapshots. Notably, the method exhibits strong capability in detecting the number of sources while estimating their DOAs. Furthermore, compared to traditional CNN methods, our refined efficient CNN significantly reduces the number of parameters by a factor of sixteen while still achieving comparable results. The effectiveness of the proposed method is analyzed through the visualization of latent space and through the advanced theory of feature learning.

Keywords: array signal processing; convolution neural network; direction-of-arrival estimation; feature learning; supervised contrastive learning

Share and Cite

MDPI and ACS Style

Li, Y.; Zhou, Z.; Chen, C.; Wu, P.; Zhou, Z. An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR. Axioms 2023, 12, 862. https://doi.org/10.3390/axioms12090862

AMA Style

Li Y, Zhou Z, Chen C, Wu P, Zhou Z. An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR. Axioms. 2023; 12(9):862. https://doi.org/10.3390/axioms12090862

Chicago/Turabian Style

Li, Yingchun, Zhengjie Zhou, Cheng Chen, Peng Wu, and Zhiquan Zhou. 2023. "An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR" Axioms 12, no. 9: 862. https://doi.org/10.3390/axioms12090862

APA Style

Li, Y., Zhou, Z., Chen, C., Wu, P., & Zhou, Z. (2023). An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR. Axioms, 12(9), 862. https://doi.org/10.3390/axioms12090862

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

An Efficient Convolutional Neural Network with Supervised Contrastive Learning for Multi-Target DOA Estimation in Low SNR

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI