Deep learning-based DOA estimation using CRNN for underwater acoustic arrays

被引:2
|
作者
Li, Xiaoqiang [1 ]
Chen, Jianfeng [1 ]
Bai, Jisheng [1 ]
Ayub, Muhammad Saad [1 ]
Zhang, Dongzhe [1 ]
Wang, Mou [1 ]
Yan, Qingli [2 ]
机构
[1] Northwestern Polytech Univ, Sch Marine Sci & Technol, Joint Lab Environm Sound Sensing, Xian, Peoples R China
[2] Xian Univ Posts & Telecommun, Sch Comp Sci & Technol, Xian, Peoples R China
基金
中国国家自然科学基金;
关键词
DOA estimation; array signal processing; underwater acoustic; convolutional recurrent neural network; deep learning; OF-ARRIVAL ESTIMATION; NEURAL-NETWORK; MUSIC; COMMUNICATION; ALGORITHM; LOCATION; ESPRIT;
D O I
10.3389/fmars.2022.1027830
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In the marine environment, estimating the direction of arrival (DOA) is challenging because of the multipath signals and low signal-to-noise ratio (SNR). In this paper, we propose a convolutional recurrent neural network (CRNN)-based method for underwater DOA estimation using an acoustic array. The proposed CRNN takes the phase component of the short-time Fourier transform of the array signals as the input feature. The convolutional part of the CRNN extracts high-level features, while the recurrent component captures the temporal dependencies of the features. Moreover, we introduce a residual connection to further improve the performance of DOA estimation. We train the CRNN with multipath signals generated by the BELLHOP model and a uniform line array. Experimental results show that the proposed CRNN yields high-accuracy DOA estimation at different SNR levels, significantly outperforming existing methods. The proposed CRNN also exhibits a relatively short processing time for DOA estimation, extending its applicability.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Deep Learning-Based DOA Estimation
    Zheng, Shilian
    Yang, Zhuang
    Shen, Weiguo
    Zhang, Luxin
    Zhu, Jiawei
    Zhao, Zhijin
    Yang, Xiaoniu
    [J]. IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2024, 10 (03) : 819 - 835
  • [2] An end-to-end DOA estimation method based on deep learning for underwater acoustic array
    Peng, Junyu
    Nie, Weihang
    Li, Ta
    Xu, Ji
    [J]. 2022 OCEANS HAMPTON ROADS, 2022,
  • [3] On the DOA Estimation Performance of Optimum Arrays Based on Deep Learning
    Wandale, Steven
    Ichige, Koichi
    [J]. 2020 IEEE 11TH SENSOR ARRAY AND MULTICHANNEL SIGNAL PROCESSING WORKSHOP (SAM), 2020,
  • [4] Deep Learning-Based Timing Offset Estimation for Deep-Sea Vertical Underwater Acoustic Communications
    Wu, Yanbo
    Yao, Yan
    Wang, Ning
    Zhu, Min
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (23): : 1 - 12
  • [5] CRNN-Based Multiple DoA Estimation Using Acoustic Intensity Features for Ambisonics Recordings
    Perotin, Laureline
    Serizel, Romain
    Vincent, Emmanuel
    Guerin, Alexandre
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2019, 13 (01) : 22 - 33
  • [6] Design of a Deep Learning-Based Underwater Acoustic Sensor Transceiver
    Yen, Chih-Ta
    Wu, Tzu-Yen
    [J]. IEEE SENSORS JOURNAL, 2024, 24 (06) : 8694 - 8711
  • [7] Model-Driven Deep Learning-Based Estimation for Underwater Acoustic Channels With Uncertain Sparsity
    Feng, Xiao
    Zhou, Mingzhang
    Wang, Junfeng
    Sun, Haixin
    Pan, Gaofeng
    Wen, Miaowen
    [J]. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2024, 23 (06) : 5710 - 5725
  • [8] Data-Driven DOA Estimation Methods Based on Deep Learning for Underwater Acoustic Vector Sensor Array
    Xie, Yangyang
    Wang, Biao
    [J]. MARINE TECHNOLOGY SOCIETY JOURNAL, 2023, 57 (03) : 16 - 29
  • [9] Adversarial Attacks on Deep Learning-Based DOA Estimation With Covariance Input
    Yang, Zhuang
    Zheng, Shilian
    Zhang, Luxin
    Zhao, Zhijin
    Yang, Xiaoniu
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2023, 30 : 1377 - 1381
  • [10] DOA estimation based on CNN for underwater acoustic array
    Liu, Yuji
    Chen, Huixiu
    Wang, Biao
    [J]. Applied Acoustics, 2022, 172