Direction finding for coherent sources with deep hybrid neural networks

被引:5
作者
Fan, Rong [1 ]
Si, Chengke [1 ]
Guo, Hesong [1 ]
Wan, Yihe [2 ]
Xu, Yajun [1 ]
机构
[1] Civil Aviat Flight Univ China, Aviat Engn Inst, Guanghan, Peoples R China
[2] Jiangxi Prov Engn Res Ctr Special Wireless Commun, Jiujiang, Peoples R China
关键词
Deep learning; intelligent direction finding; coherent source; residual neural network (ResNet); auto-encoder (AE);
D O I
10.1080/00207217.2021.1941293
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 this paper, an intelligent direction finding (DF) architecture based on hybrid neural network is proposed. Firstly, the array outputs of DF system are multiplied by the corresponding ideal array manifold and a high-dimensional preprocessed feature vector is derived. In the next, the preprocessed feature is straightly fed into the auto-encoder. The auto-encoder outputs are then used as the input of the cascaded deep residual neural network in order to extract spatial spectral of sources. Finally, the direction-of-arrival (DOA) results are derived according to the locations of the normalised spectral peaks. There are two advantages with our proposed network architecture. One is the DF estimation accuracy is independent on the array aperture size when the number of elements is fixed. And the other is that the proposed network structure and processing procedures can be directly generalised into unknown scenarios but having higher angle resolution capacity at the same time. Finally, extensive numerical experiments illustrate the correctness and potential advantages of the proposed deep hybrid neural network.
引用
收藏
页码:811 / 833
页数:23
相关论文
共 23 条
[1]  
Abeywickrama S, 2018, PROCEEDINGS OF 2018 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS (ICCS 2018), P157, DOI 10.1109/ICCS.2018.8689177
[2]   2D off-grid DOA estimation using joint sparsity [J].
Afkhaminia, Fatemeh ;
Azghani, Masoumeh .
IET RADAR SONAR AND NAVIGATION, 2019, 13 (09) :1580-1587
[3]   Deep Autoencoders for DOA Estimation of Coherent Sources using Imperfect Antenna Array [J].
Ahmed, Aya Mostafa ;
Eissa, Omar ;
Sezgin, Aydin .
2020 THIRD INTERNATIONAL WORKSHOP ON MOBILE TERAHERTZ SYSTEMS (IWMTS), 2020,
[4]  
Chakrabarty S, 2017, IEEE WORK APPL SIG, P136, DOI 10.1109/WASPAA.2017.8170010
[5]   In-lab validation of jammer detection and direction finding algorithms for GNSS [J].
Ferre, Ruben Morales ;
Richter, Philipp ;
De La Fuente, Alberto ;
Lohan, Elene Simona .
2019 INTERNATIONAL CONFERENCE ON LOCALIZATION AND GNSS (ICL-GNSS), 2019,
[6]   A Small-Aperture, Ultrawideband HF/VHF Direction-Finding System For Unmanned Aerial Vehicles [J].
Ghaemi, Kasra ;
Ma, Ruyu ;
Behdad, Nader .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2018, 66 (10) :5109-5120
[7]   Application of antenna arrays to mobile communications .2. Beam-forming and direction-of-arrival considerations [J].
Godara, LC .
PROCEEDINGS OF THE IEEE, 1997, 85 (08) :1195-1245
[8]  
Guo FC, 2014, SPACE ELECTRONIC RECONNAISSANCE: LOCALIZATION THEORIES AND METHODS, P47
[9]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[10]   Robust MIMO radar target localization via nonconvex optimization [J].
Liang, Junli ;
Wang, Dong ;
Su, Li ;
Chen, Badong ;
Chen, H. ;
So, H. C. .
SIGNAL PROCESSING, 2016, 122 :33-38