AIPUB归智期刊联盟

微信公众号

网站二维码

2025年4月1日 9:49 星期二
首页 > 过刊浏览>2025年第34卷第3期 >72-84. DOI:10.15888/j.cnki.csa.009800
PDF HTML阅读 XML下载 导出引用 引用提醒
基于3D融合特征联合神经网络的水声目标识别
作者:
基金项目:

国家自然科学基金青年科学基金(62203405); 山西省应用基础研究计划(20210302124545, 202303021212206, 202202110401015)


Hydroacoustic Target Recognition Based on 3D Fusion Feature Joint Neural Network
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [36]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    面对复杂的海洋环境, 利用舰船辐射噪声进行水声目标特征提取与识别具有极大的挑战性. 本文首先将船舶音频信号的三维梅尔频率倒谱系数(3D dynamic Mel-frequency cepstrum coefficient, 3D-MFCC)特征与三维梅尔谱(3D dynamic Mel-spectrogram, 3D-Mel)特征进行融合作为模型输入, 并基于此提出了一种新的水声目标识别深度神经网络模型, 该模型在卷积神经网络(convolutional neural network, CNN)和长短期记忆网络(long short-term memory, LSTM)的串行架构基础上, 用多尺度深度可分离卷积网络(multi-scale depthwise convolutional network, MSDC), 替代了传统的CNN, 并增加了多尺度通道注意力机制(multi-scale channel attention, MSCA). 实验结果表明, 该方法在DeepShip数据集和ShipsEar数据集上的平均识别率分别达到了85.92%和97.32%, 展现了良好的分类效果.

    Abstract:

    Facing the complex marine environment, it is extremely challenging to utilize ship radiated noise for hydroacoustic target feature extraction and recognition. In this study, 3D dynamic Mel-frequency cepstrum coefficient (3D-MFCC) features of ship audio signals are fused with 3D dynamic Mel-spectrogram (3D-Mel) features as model inputs. Based on this, a new deep neural network model for hydroacoustic target recognition is proposed. The model is based on the serial architectures of convolutional neural network (CNN) and long short-term memory (LSTM). Here, the traditional CNN is replaced by multi-scale depthwise convolutional network (MSDC), and multi-scale channel attention (MSCA) is added. The experimental results show that the average recognition rate of this method on DeepShip and ShipsEar datasets reaches 85.92% and 97.32% respectively, which demonstrates a good classification effect.

    参考文献
    [1] 章业成. 水声目标识别技术的现状与发展. 电子技术与软件工程, 2019(18): 97–98.
    [2] Zhang GJ, Wang PP, Wang P. Feature extraction of underwater target based on the time-frequency analysis. Proceedings of the 2nd International Conference on Signal Processing Systems. Dalian: IEEE, 2010. V3-208–V3-211.
    [3] Hackman RH, Arnold H, Reagan J. Active acoustic classification of underwater targets based on time-frequency analyses. The Journal of the Acoustical Society of America, 1992, 91(S4): 2446.
    [4] Yang S, Jin AQ, Zeng XY, et al. Underwater acoustic target recognition based on sub-band concatenated Mel spectrogram and multidomain attention mechanism. Engineering Applications of Artificial Intelligence, 2024, 133: 107983.
    [5] Li J, Wang BX, Cui XR, et al. Underwater acoustic target recognition based on attention residual network. Entropy, 2022, 24(11): 1657.
    [6] Liu G M, Sun C, Yang YX. Target feature extraction for passive sonar based on two cepstrums. Proceedings of the 2nd International Conference on Bioinformatics and Biomedical Engineering. Shanghai: IEEE, 2008. 539–542.
    [7] Jeevan M, Dhingra A, Hanmandlu M, et al. Robust speaker verification using GFCC based i-vectors. Proceedings of the 2016 International Conference on Signal, Networks, Computing, and Systems. New Delhi: Springer, 2016. 85–91.
    [8] Seok J, Bae K. Target classification using features based on fractional Fourier transform. IEICE Transactions on Information and Systems, 2014, E97.D(9): 2518–2521.
    [9] Azimi-Sadjadi MR, Yao D, Huang Q, et al. Underwater target classification using wavelet packets and neural networks. IEEE Transactions on Neural Networks, 2000, 11(3): 784–794.
    [10] Copiaco A, Ritz C, Abdulaziz N, et al. A study of features and deep neural network architectures and hyper-parameters for domestic audio classification. Applied Sciences, 2021, 11(11): 4880.
    [11] Lim T, Bae K, Hwang C, et al. Classification of underwater transient signals using MFCC feature vector. Proceedings of the 9th International Symposium on Signal Processing and Its Applications. Sharjah: IEEE, 2007. 1–4.
    [12] Zhang LY, Wu D, Han X, et al. Feature extraction of underwater target signal using Mel frequency cepstrum coefficients based on acoustic vector sensor. Journal of Sensors, 2016, 2016(1): 7864213.
    [13] Liu F, Shen TS, Luo ZL, et al. Underwater target recognition using convolutional recurrent neural networks with 3D mel-spectrogram and data augmentation. Applied Acoustics, 2021, 178: 107989.
    [14] 徐小华, 周长兵, 胡忠旭, 等. 轻量级深度神经网络模型适配边缘智能研究综述. 计算机科学, 2024, 51(7): 257–271.
    [15] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504–507.
    [16] 王念滨, 何鸣, 王红滨, 等. 适用于水下目标识别的快速降维卷积模型. 哈尔滨工程大学学报, 2019, 40(7): 1327–1333.
    [17] 张少康, 王超, 田德艳, 等. 长短时记忆网络水下目标噪声智能识别方法. 舰船科学技术, 2019, 41(23): 181–185.
    [18] 张奇, 笪良龙, 王超, 等. 基于深度学习的水声被动目标识别研究综述. 电子与信息学报, 2023, 45(11): 4190–4202.
    [19] 任晨曦, 王黎明, 韩星程, 等. 基于联合神经网络的水声目标识别方法. 舰船科学技术, 2022, 44(1): 136–141.
    [20] Satheesh Chandran C, Suraj K, Mujeeb A, et al. Novel class detection of underwater targets using self-organizing neural networks. Proceedings of the 2015 IEEE Underwater Technology (UT). Chennai: IEEE, 2015. 1–5.
    [21] Hu G, Wang KJ, Liu LL. Underwater acoustic target recognition based on depthwise separable convolution neural networks. Sensors, 2021, 21(4): 1429.
    [22] 张伟. 基于注意力机制的水声目标识别技术研究 [硕士学位论文]. 镇江: 江苏科技大学, 2023.
    [23] Hu J, Shen L, Sun G. Squeeze-and-excitation networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 7132–7141.
    [24] Wang QL, Wu BG, Zhu PF, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle: IEEE, 2020. 11531–11539.
    [25] Xie Y, Ren J, Xu J. Underwater-art: Expanding information perspectives with text templates for underwater acoustic target recognition. The Journal of the Acoustical Society of America, 2022, 152(5): 2641–2651.
    [26] Irfan M, Jiangbin Z, Ali S, et al. DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification. Expert Systems with Applications, 2021, 183: 115270.
    [27] Ren J, Xie Y, Zhang X, et al. UALF: A learnable front-end for intelligent underwater acoustic classification system. Ocean Engineering, 2022, 264: 112394.
    [28] Zhu P, Zhang Y, Huang Y, et al. Underwater acoustic target recognition based on spectrum component analysis of ship radiated noise. Applied Acoustics, 2023, 211: 109552.
    [29] Tian SZ, Chen DB, Fu Y, et al. Joint learning model for underwater acoustic target recognition. Knowledge-based Systems, 2023, 260: 110119.
    [30] Xu K, Xu Q, You K, et al. Self-supervised learning–based underwater acoustical signal classification via mask modeling. The Journal of the Acoustical Society of America, 2023, 154(1): 5–15.
    [31] Zhang Y, Zeng Q. MSLEFC: A low-frequency focused underwater acoustic signal classification and analysis system. Engineering Applications of Artificial Intelligence, 2023, 123: 106333.
    [32] Sadeghi M, Gholamalinejad H, Ali M. A new database for underwater sound recognition using a nonlinear support vector machine. Proceedings of the 2019 International Conference on Computing, Electronics and Communications Engineering (ICCECE). London: IEEE, 2019. 169–172.
    [33] Liu C, Hong F, Feng H, et al. Underwater qcoustic target recognition based on dual attention networks and multiresolution convolutional neural networks. OCEANS 2021: San Diego-Porto. San Diego: IEEE, 2021. 1–5.
    [34] Chen Z, Xie G, Chen M, et al. Model for underwater acoustic target recognition with attention mechanism based on residual concatenate. Journal of Marine Science and Engineering, 2024, 12(1): 24.
    [35] Feng H, Chen X, Wang R, et al. Underwater acoustic target recognition method based on WA-DS decision fusion. Applied Acoustics, 2024, 217: 109851.
    [36] Qi P, Yin G, Zhang L. Underwater acoustic target recognition using RCRNN and wavelet-auditory feature. Multimed Tools Applications, 2024, 83(16): 47295–47317.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

许玮婷,赵英亮,冯思奇,韩星程,贾彩琴.基于3D融合特征联合神经网络的水声目标识别.计算机系统应用,2025,34(3):72-84

复制
分享
文章指标
  • 点击次数:76
  • 下载次数: 917
  • HTML阅读次数: 47
  • 引用次数: 0
历史
  • 收稿日期:2024-09-01
  • 最后修改日期:2024-10-10
  • 在线发布日期: 2025-01-21
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会软件学报
您是第11124139位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码：100190
电话：010-62661041 传真： Email：csa (a) iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号