An Auditory Convolutional Neural Network for Underwater Acoustic Target Timbre Feature Extraction and Recognition

被引:0
|
作者
Ni, Junshuai [1 ]
Ji, Fang [1 ,2 ]
Lu, Shaoqing [1 ]
Feng, Weijia [1 ]
机构
[1] China Ship Res & Dev Acad, Beijing 100101, Peoples R China
[2] Harbin Engn Univ, Coll Shipbldg Engn, Harbin 150001, Peoples R China
基金
中国国家自然科学基金;
关键词
gammatone filter bank; attention mechanism; line spectrum; auditory convolutional neural network; global energy pooling; underwater acoustic target recognition;
D O I
10.3390/rs16163074
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In order to extract the line-spectrum features of underwater acoustic targets in complex environments, an auditory convolutional neural network (ACNN) with the ability of frequency component perception, timbre perception and critical information perception is proposed in this paper inspired by the human auditory perception mechanism. This model first uses a gammatone filter bank that mimics the cochlear basilar membrane excitation response to decompose the input time-domain signal into a number of sub-bands, which guides the network to perceive the line-spectrum frequency information of the underwater acoustic target. A sequence of convolution layers is then used to filter out interfering noise and enhance the line-spectrum components of each sub-band by simulating the process of calculating the energy distribution features, after which the improved channel attention module is connected to select line spectra that are more critical for recognition, and in this module, a new global pooling method is proposed and applied in order to better extract the intrinsic properties. Finally, the sub-band information is fused using a combination layer and a single-channel convolution layer to generate a vector with the same dimensions as the input signal at the output layer. A decision module with a Softmax classifier is added behind the auditory neural network and used to recognize the five classes of vessel targets in the ShipsEar dataset, achieving a recognition accuracy of 99.8%, which is improved by 2.7% compared to the last proposed DRACNN method, and there are different degrees of improvement over the other eight compared methods. The visualization results show that the model can significantly suppress the interfering noise intensity and selectively enhance the radiated noise line-spectrum energy of underwater acoustic targets.
引用
收藏
页数:16
相关论文
共 50 条
  • [21] Research on Underwater Acoustic Target Recognition Based on a 3D Fusion Feature Joint Neural Network
    Xu, Weiting
    Han, Xingcheng
    Zhao, Yingliang
    Wang, Liming
    Jia, Caiqin
    Feng, Siqi
    Han, Junxuan
    Zhang, Li
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (11)
  • [22] An Improved Auditory Feature based on Instantaneous Frequency and Gammatone Filters for Underwater Acoustic Target Recognition
    Zhang, Yifan
    Xu, Ke
    Wan, Jianwei
    TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806
  • [23] Imbalanced Underwater Acoustic Target Recognition with Trigonometric Loss and Attention Mechanism Convolutional Network
    Ma, Yanxin
    Liu, Mengqi
    Zhang, Yi
    Zhang, Bingbing
    Xu, Ke
    Zou, Bo
    Huang, Zhijian
    REMOTE SENSING, 2022, 14 (16)
  • [24] Underwater Acoustic Target Classification Using Auditory Fusion Features and Efficient Convolutional Attention Network
    Yang, Junjie
    Zhang, Zhenyu
    Li, Wei
    Wang, Xiang
    Yang, Senquan
    Yang, Chao
    IEEE SENSORS LETTERS, 2025, 9 (03)
  • [25] Underwater acoustic target recognition using line enhancement and deep neural network
    YU Xueyang
    CHI Cheng
    LI Shuqiu
    LI Derui
    Chinese Journal of Acoustics, 2024, 43 (04) : 452 - 467
  • [26] Feature extraction based ondeep-convolutional neural network for face recognition
    Li, Xiaolin
    Niu, Haitao
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2020, 32 (22): : 1
  • [27] Basketball posture recognition based on HOG feature extraction and convolutional neural network
    Gao, Jian
    EAI ENDORSED TRANSACTIONS ON SCALABLE INFORMATION SYSTEMS, 2022, 9 (04):
  • [28] Feature Extraction and Recognition of Human Physiological Signals Based on the Convolutional Neural Network
    Hurr, Chansol
    Li, Caiyan
    Li, Heng
    MOBILE INFORMATION SYSTEMS, 2022, 2022
  • [29] DECENTRALIZING FEATURE EXTRACTION WITH QUANTUM CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC SPEECH RECOGNITION
    Yang, Chao-Han Huck
    Qi, Jun
    Chen, Samuel Yen-Chi
    Chen, Pin-Yu
    Siniscalchi, Sabato Marco
    Ma, Xiaoli
    Lee, Chin-Hui
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 6523 - 6527
  • [30] Underwater Acoustic Target Recognition Based on Dual Attention Networks and Multiresolution Convolutional Neural Networks
    Liu, Chengwei
    Hong, Feng
    Feng, Haihong
    Hu, Menglu
    OCEANS 2021: SAN DIEGO - PORTO, 2021,