DOA Estimation Method Based on Unsupervised Learning Network With Threshold Capon Spectrum Weighted Penalty

被引:4
作者
Zhang, Zhengyan [1 ,2 ]
Qu, Xiaodong [1 ,2 ]
Li, Wolin [1 ,2 ]
Miao, Hongzhe [1 ,2 ]
Liu, Fengrui [1 ,2 ]
机构
[1] Beijing Inst Technol, Sch Informat & Elect, Beijing, Peoples R China
[2] Minist Educ, Key Lab Elect & Informat Technol Satellite Nav, Beijing 100081, Peoples R China
基金
中国国家自然科学基金;
关键词
Estimation; Direction-of-arrival estimation; Training; Interference; Signal to noise ratio; Covariance matrices; Unsupervised learning; Capon spectrum; direction-of-arrival estimation; unequal power signal; unsupervised learning network; DIRECTION-OF-ARRIVAL; MAXIMUM-LIKELIHOOD; ANTENNA-ARRAYS; NEURAL-NETWORK; RECONSTRUCTION; LOCALIZATION; MODEL;
D O I
10.1109/LSP.2023.3349078
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
In complex electronic countermeasure environment, direction-of-arrival (DOA) is very important for targets detection, localization and tracking. However, the power of interference is usually stronger than that of signal, which degrades the DOA estimation performance severely, and even makes DOA estimation failure. To solve this issue, this paper proposes a DOA estimation method based on unsupervised learning network with threshold Capon spectrum weighted penalty. In this work, an unsupervised network is proposed to obtain the DOA estimation spectrum, in which labels are no longer required. Furthermore, deep unfolded layers are introduced to remove the iterative solution of sparse recovery and increase the depth of network. Additionally, loss function contains reconstruction error and penalty term is developed to generate zero traps in direction of interference and signal, overcoming the influence of strong interference. Both numerical simulations and experiments demonstrate the effectiveness of the proposed method.
引用
收藏
页码:701 / 705
页数:5
相关论文
共 29 条
[1]   A Machine Learning Approach to DoA Estimation and Model Order Selection for Antenna Arrays With Subarray Sampling [J].
Barthelme, Andreas ;
Utschick, Wolfgang .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 :3075-3087
[2]   Robust DoA Estimation Using Denoising Autoencoder and Deep Neural Networks [J].
Chen, Dawei ;
Shi, Shuo ;
Gu, Xuemai ;
Shim, Byonghyo .
IEEE ACCESS, 2022, 10 :52551-52564
[3]   Deep Neural Network for Estimation of Direction of Arrival With Antenna Array [J].
Chen, Min ;
Gong, Yi ;
Mao, Xingpeng .
IEEE ACCESS, 2020, 8 :140688-140698
[4]   DeepAoANet: Learning Angle of Arrival From Software Defined Radios With Deep Neural Networks [J].
Dai, Zhuangzhuang ;
He, Yuhang ;
Tran, Vu ;
Trigoni, Niki ;
Markham, Andrew .
IEEE ACCESS, 2022, 10 :3164-3176
[5]   Performance of radial-basis function networks for direction of arrival estimation with antenna arrays [J].
ElZooghby, AH ;
Christodoulou, CG ;
Georgiopoulos, M .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1997, 45 (11) :1611-1617
[6]  
Fang QY, 2014, IEEE RAD CONF, P591, DOI 10.1109/RADAR.2014.6875660
[7]   Direction-of-Arrival Estimation of Coherent Signals for Uniform Linear Antenna Arrays With Mutual Coupling in Unknown Nonuniform Noise [J].
Fang, Yunfei ;
Zhu, Shengqi ;
Gao, Yongchan ;
Lan, Lan ;
Zeng, Cao ;
Liu, Zhixin .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2022, 71 (02) :1656-1668
[8]   DOA Estimations With Limited Snapshots Based on Improved Rank-One Correlation Model in Unknown Nonuniform Noise [J].
Fang, Yunfei ;
Zhu, Shengqi ;
Zeng, Cao ;
Gao, Yongchan ;
Li, Shidong .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (10) :10308-10319
[9]   Mixed Near-Field and Far-Field Localization and Array Calibration With Partly Calibrated Arrays [J].
He, Jin ;
Shu, Ting ;
Li, Linna ;
Truong, Trieu-Kien .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2022, 70 :2105-2118
[10]   DOA Estimation With Small Snapshots Using Weighted Mixed Norm Based on Spatial Filter [J].
Liu, Beiyi ;
Matsushita, Shin-ya ;
Xu, Li .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2020, 69 (12) :16183-16187