高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

船舶辐射噪声分类卷积神经网络的可视化分析和卷积核剪枝

徐源超 蔡志明 孔晓鹏 黄炎

徐源超, 蔡志明, 孔晓鹏, 黄炎. 船舶辐射噪声分类卷积神经网络的可视化分析和卷积核剪枝[J]. 电子与信息学报, 2024, 46(1): 74-82. doi: 10.11999/JEIT230149
引用本文: 徐源超, 蔡志明, 孔晓鹏, 黄炎. 船舶辐射噪声分类卷积神经网络的可视化分析和卷积核剪枝[J]. 电子与信息学报, 2024, 46(1): 74-82. doi: 10.11999/JEIT230149
XU Yuanchao, CAI Zhiming, KONG Xiaopeng, HUANG Yan. Visualization Analysis and Kernel Pruning of Convolutional Neural Network for Ship-Radiated Noise Classification[J]. Journal of Electronics & Information Technology, 2024, 46(1): 74-82. doi: 10.11999/JEIT230149
Citation: XU Yuanchao, CAI Zhiming, KONG Xiaopeng, HUANG Yan. Visualization Analysis and Kernel Pruning of Convolutional Neural Network for Ship-Radiated Noise Classification[J]. Journal of Electronics & Information Technology, 2024, 46(1): 74-82. doi: 10.11999/JEIT230149

船舶辐射噪声分类卷积神经网络的可视化分析和卷积核剪枝

doi: 10.11999/JEIT230149
详细信息
    作者简介:

    徐源超:男,博士生,研究方向为水声目标识别

    蔡志明:男,教授,研究方向为水声信号与信息处理

    孔晓鹏:男,讲师,研究方向为水声目标识别与非线性声学

    黄炎:男,助教,研究方向为水声目标识别

    通讯作者:

    徐源超 xycwshr@126.com

  • 中图分类号: TN911.7; TP181; TB56

Visualization Analysis and Kernel Pruning of Convolutional Neural Network for Ship-Radiated Noise Classification

  • 摘要: 当前基于深度神经网络的船舶辐射噪声分类研究主要关注分类性能,对模型的解释性关注较少。本文首先采用导向反向传播和输入空间优化,基于DeepShip数据集,构建以对数谱为输入的船舶辐射噪声分类卷积神经网络(CNN),提出了一种船舶辐射噪声分类CNN的可视化分析方法。结果显示,多帧特征对齐算法改进了可视化效果,深层卷积核检测线谱和背景两类特征。其次,基于线谱是船舶分类的稳健特征这一知识,提出了一种卷积核剪枝方法,不仅提升了CNN分类性能,且训练过程更加稳定。导向反向传播可视化结果表明,卷积核剪枝后的CNN更加关注线谱信息。
  • 图  1  基于导向反向传播(GBP)和输入空间优化(OIS)的船舶辐射噪声CNN卷积核可视化流程

    图  2  CNN卷积核可视化分析各步骤输出

    图  3  Conv7中一个卷积核的可视化结果

    图  4  卷积核的4种典型模式

    图  5  线谱强度与分类正确率的关系

    图  6  卷积核剪枝前后CNN性能对比

    图  7  针对类别的GBP重建样本

    表  1  CNN模型参数

    层号参数
    0输入1×8×512维
    1Conv2d(16, 3×3)
    2Conv2d+MaxPool2d(32, 3×3), 2×2
    3Conv2d+MaxPool2d(64, 1×3), 2×2
    4Conv2d+MaxPool2d(64, 1×3), 2×2
    5Conv2d+MaxPool2d(64, 1×3), 1×2
    6Conv2d+MaxPool2d(64, 1×3), 1×2
    7Conv2d+MaxPool2d(128, 1×3), 1×2
    8FC256
    9FC64
    10FC4
    下载: 导出CSV

    表  2  DeepShip数据集样本划分

    船舶
    类别
    训练
    记录数
    测试
    记录数
    训练
    样本数
    测试
    样本数
    货轮(A)882176581922
    客轮(B)1533887202824
    油轮(C)1924890422006
    拖船(D)561381421970
    合计489120335628722
    下载: 导出CSV
    算法1 多帧特征对齐算法
     输入:$ {N} $列160个频点的特征${\boldsymbol{M} }_{160 \times N}$;
       最大迭代次数$i_{\max }$;
       每列的最大平移量$ s_{\max } $。
     初始化:$s_{j}=0, \quad j=1, 2,\cdots, N$
     for $i=1,2, \cdots, i_{\max}$
       for $ j=1,2, \cdots, N $
         计算${\boldsymbol{M}}_j$与${\boldsymbol{M}}_{-j}$的相关${\rm{corr} }\left({\boldsymbol{M}}_{-j}, {\boldsymbol{M}}_{j}\right)$
         确定${\boldsymbol{M}}_j$的平移量$ s \in \{-1,0,1\} $
         if ${\rm{abs}}(s_j+s )\le s_{\max}$
           ${\boldsymbol{M}}_j$平移s个单位(该列末端补零):${ {\rm{shift} } }\left({\boldsymbol{M}}_{j}, s\right)$
           $s_j \leftarrow s_j +s$
     输出:${\boldsymbol{M}}_{160 \times N} $
    注:${\boldsymbol{M}}_{j}$指${\boldsymbol{M}}_{160 \times N}$的第j列;${\boldsymbol{M}}_{-j}$指${\boldsymbol{M}}_{160 \times N}$的除第j列外其余列的平均值;它们都是160维的向量。
    下载: 导出CSV

    表  3  各CNN模型分类正确率(%)

    模型训练集测试集
    CNN-12898.9469.28
    CNN-L6498.6770.58
    CNN-B6498.7868.28
    CNN-6498.4869.05
    P-CNN-6498.3768.53
    下载: 导出CSV

    表  4  不同最大线谱强度(dB)下CNN模型分类正确率(%)

    模型<12.912.9~14.014.0~15.715.7~18.218.2~21.021.0~23.023.0~24.6>24.6
    CNN-12855.7165.7670.8473.5071.2870.9767.0857.14
    CNN-L6456.8164.8470.8174.3472.7373.3672.0059.19
    CNN-B6454.1465.2870.0671.8870.7269.4766.9056.85
    CNN-6454.0364.9969.1973.3371.1870.2468.9559.96
    P-CNN-6453.2662.6467.4172.3570.8071.3870.0260.37
    下载: 导出CSV
  • [1] SHEN Sheng, YANG Honghui, LI Junhao, et al. Auditory inspired convolutional neural networks for ship type classification with raw hydrophone data[J]. Entropy, 2018, 20(12): 990. doi: 10.3390/e20120990
    [2] HU Gang, WANG Kejun, PENG Yuan, et al. Deep learning methods for underwater target feature extraction and recognition[J]. Computational Intelligence and Neuroscience, 2018, 2018: 1214301. doi: 10.1155/2018/1214301
    [3] LI Junhao and YANG Honghui. The underwater acoustic target timbre perception and recognition based on the auditory inspired deep convolutional neural network[J]. Applied Acoustics, 2021, 182: 108210. doi: 10.1016/j.apacoust.2021.108210
    [4] CHEN Yuechao and SHANG Jintao. Underwater target recognition method based on convolution autoencoder[C]. Proceedings of 2019 IEEE International Conference on Signal, Information and Data Processing, Chongqing, China, 2019: 1–5.
    [5] CHEN Jie, HAN Bing, MA Xufeng, et al. Underwater target recognition based on multi-decision LOFAR spectrum enhancement: A deep-learning approach[J]. Future Internet, 2021, 13(10): 265. doi: 10.3390/FI13100265
    [6] ZHANG Qi, DA Lianglong, ZHANG Yanhou, et al. Integrated neural networks based on feature fusion for underwater target recognition[J]. Applied Acoustics, 2021, 182: 108261. doi: 10.1016/J.APACOUST.2021.108261
    [7] 伊恩·古德费洛, 约书亚·本吉奥, 亚伦·库维尔, 赵申剑, 黎彧君, 符天凡, 等译. 深度学习[M]. 北京: 人民邮电出版社, 2017: 224–225.

    GOODFELLOW I, BENGIO Y, COURVILLE A, ZHAO Shenjian, LI Yujun, FU Tianfan, et al. translation. Deep Learning[M]. Beijing: Posts & Telecom Press, 2017: 224–225.
    [8] ZEILER M D and FERGUS R. Visualizing and understanding convolutional networks[C]. Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland, 2014: 818–833.
    [9] SPRINGENBERG J T, DOSOVITSKIY A, BROX T, et al. Striving for simplicity: The all convolutional net[EB/OL]. http://arxiv.org/abs/1412.6806, 2015.
    [10] SIMONYAN K, VEDALDI A, and ZISSERMAN A. Deep inside convolutional networks: Visualising image classification models and saliency maps[EB/OL]. http://arxiv.org/abs/1312.6034, 2014.
    [11] YOSINSKI J, CLUNE J, NGUYEN A, et al. Understanding neural networks through deep visualization[EB/OL]. http://arxiv.org/abs/1506.06579, 2015.
    [12] 徐源超, 蔡志明, 孔晓鹏. 基于双对数谱和卷积网络的船舶辐射噪声分类[J]. 电子与信息学报, 2022, 44(6): 1947–1955. doi: 10.11999/JEIT211407

    XU Yuanchao, CAI Zhiming, and KONG Xiaopeng. Classification of ship radiated noise based on Bi-logarithmic scale spectrum and convolutional network[J]. Journal of Electronics &Information Technology, 2022, 44(6): 1947–1955. doi: 10.11999/JEIT211407
    [13] IRFAN M, ZHENG Jiangbin, ALI S, et al. DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification[J]. Expert Systems with Applications, 2021, 183: 115270. doi: 10.1016/J.ESWA.2021.115270
    [14] 赖叶静, 郝珊锋, 黄定江. 深度神经网络模型压缩方法与进展[J]. 华东师范大学学报:自然科学版, 2020(5): 68–82. doi: 10.3969/j.issn.1000-5641.202091001

    LAI Yejing, HAO Shanfeng, and HUANG Dingjiang. Methods and progress in deep neural network model compression[J]. Journal of East China Normal University:Natural Science, 2020(5): 68–82. doi: 10.3969/j.issn.1000-5641.202091001
    [15] 姜晓勇, 李忠义, 黄朗月, 等. 神经网络剪枝技术研究综述[J]. 应用科学学报, 2022, 40(5): 838–849. doi: 10.3969/j.issn.0255-8297.2022.05.013

    JIANG Xiaoyong, LI Zhongyi, HUANG Langyue, et al. Review of neural network pruning techniques[J]. Journal of Applied Sciences, 2022, 40(5): 838–849. doi: 10.3969/j.issn.0255-8297.2022.05.013
    [16] HU Hengyuan, PENG Rui, TAI Y W, et al. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures[EB/OL]. http://arxiv.org/abs/1607.03250, 2016.
    [17] 程玉胜, 李智忠, 邱家兴. 水声目标识别[M]. 北京: 科学出版社, 2018: 8–9.

    CHENG Yusheng, LI Zhizhong, and QIU Jiaxing. Underwater Acoustic Target Recognition[M]. Beijing: Science Press, 2018: 8–9.
    [18] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(56): 1929–1958.
    [19] 鲍雪山. 被动目标DEMON检测方法研究及处理系统方案设计[D]. [硕士论文], 哈尔滨工程大学, 2005.

    BAO Xueshan. The method research of passive target detection using DEMON spectrum and the project design of processing system[D]. [Master dissertation], Harbin Engineering University, 2005.
  • 加载中
图(7) / 表(5)
计量
  • 文章访问数:  400
  • HTML全文浏览量:  185
  • PDF下载量:  68
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-03-13
  • 修回日期:  2023-06-12
  • 网络出版日期:  2023-06-19
  • 刊出日期:  2024-01-17

目录

    /

    返回文章
    返回