Position-enabled complex Toeplitz LISTA for DOA estimation with unknow mutual coupling

被引：2

作者：

Guo, Yuzhang ^{[1
]}

Jin, Jie ^{[1
]}

Wang, Qing ^{[1
]}

Chen, Hua ^{[2
]}

Liu, Wei ^{[3
]}

机构：

[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China

[2] Ningbo Univ, Fac Elect Engn & Comp Sci, Ningbo 315211, Peoples R China

[3] Univ Sheffield, Dept Elect & Elect Engn, Sheffield S1 3JD, S Yorkshire, England

来源：

SIGNAL PROCESSING | 2022年 / 194卷

关键词：

DOA estimation; LISTA; Complex neural network; Sparse recovery; Mutual coupling; ALGORITHM;

D O I：

10.1016/j.sigpro.2021.108422

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Unfolding iterative algorithms into deep networks can increase the rate of convergence which is amenable to Direction-of-arrival (DOA) estimation problems. However, there normally exists unknown mutual coupling between antenna array elements. In this paper, a novel Position-enAbled Complex Toeplitz Learned Iterative Shrinkage Thresholding Algorithm (PACT-LISTA) is proposed which makes use of the data driven method to solve the mutual coupling problem and improve the parameter estimation performance. First, a sparse recovery (SR) model is developed to explore the inherent Topelitz structure. In order to solve the SR problem, a Complex Toeplitz LISTA (CT-LISTA) network is proposed, which integrates the Toeplitz structure into the Complex LISTA (C-LISTA) network. By ignoring the amplitude and phase information of the recovered signal, the idea of position-priority is applied to further improve the estimation accuracy. Through an innovative iteration method, the system gradually converges to the optimized stable state, which is associated with an accuracy parameter. Simulations are provided to demonstrate that the proposed approach significantly outperforms the state of art methods.(c) 2021 Elsevier B.V. All rights reserved.

引用

页数：9

共 23 条

[21] ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing [J].

Yang, Yan ;

Sun, Jian ;

Li, Huibin ;

Xu, Zongben .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 42 (03) :521-538

[22] ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing [J].

Zhang, Jian ;

Ghanem, Bernard .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :1828-1837

[23]

Zhu YY, 2019, IEEE WRK SIG PRO SYS, P1, DOI [10.1109/SiPS47522.2019.9020522, 10.1109/sips47522.2019.9020522, 10.1109/csqrwc.2019.8799111]

← 1 2 3 →