A Fiber Vibration Signal Recognition Method Based on CNN-CBAM-LSTM

被引:13
|
作者
Huang, Jincheng [1 ]
Mo, Jiaqing [1 ]
Zhang, Jiangwei [1 ]
Ma, Xinrong [1 ]
机构
[1] Xinjiang Univ, Coll Informat Sci & Engn, Key Lab Signal Detect & Proc, Urumqi 830017, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 17期
关键词
optical fiber vibration signal; convolutional neural network; long short-term memory; convolutional block attention module; INTRUSION DETECTION; ALGORITHM; LONG;
D O I
10.3390/app12178478
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
By trying to solve the issue of identifying multiple types of intrusion vibration signals collected by distributed vibrating fiber optic sensors, this study investigates the signal identification and feature extraction of intrusion signals, and proposes an optical fiber vibration signal (OFVS) identification method based on deep learning. The external vibration signal is collected by the Sagnac fiber optic interferometer, and then denoised by spectral subtraction. Endpoint detection is carried out by combining the short-time logarithmic energy method and the spectral entropy method. Finally, the equal-length signal containing valid information is intercepted and the corresponding preprocessing is carried out. The method for feature processing incorporates the strong feature learning capability of the long-short-term memory (LSTM) and the great short-term feature extraction capability of the convolutional neural network (CNN). At the same time, to further enhance the signal feature identification, a convolutional block attention module (CBAM) is introduced to perform adaptive feature refinement on the signal. In summary, a network model combining CNN, LSTM, and CBAM is proposed to process the signal features, and finally, the multi-layer perceptron (MLP) is used to complete the task of classification and recognition of multi-type intrusion signals. The experimental findings indicate that the OFVS method of CNN-CBAM-LSTM can effectively identify four kinds of OFVS, and the overall average recognition accuracy reaches 97.9%. Walking and knocking signals among them are recognized with over 99% accuracy.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Signal Recognition Method of X-ray Pulsar Based on CNN and Attention Module CBAM
    Xiang, Liming
    Zhou, Zhiqiang
    Miao, Lingjuan
    Chen, Qiang
    PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 5436 - 5441
  • [2] CNN-CBAM-LSTM: Enhancing Stock Return Prediction Through Long and Short Information Mining in Stock Prediction
    Ye, Peijie
    Zhang, Hao
    Zhou, Xi
    MATHEMATICS, 2024, 12 (23)
  • [3] Automatic recognition of radar signal types based on CNN-LSTM
    Ruan G.
    Wang Ya.
    Wang Sh.L.
    Zheng Yu.
    Guo Q.
    Shulga S.
    Zheng, Yu. (zhengyu@qdu.edu.cn), 1600, Begell House Inc. (79): : 305 - 321
  • [4] An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model
    Lu, Xiang
    Wen, Anhao
    Sun, Lei
    Wang, Hao
    Guo, Yinjing
    Ren, Yande
    IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE, 2023, 11 : 417 - 423
  • [5] 基于CNN-CBAM-LSTM的稳态视觉诱发电位脑电信号识别方法
    巩炫麟
    陶庆
    苏娜
    马金旭
    科学技术与工程, 2025, 25 (10) : 4175 - 4182
  • [6] Motor Imagery EEG Signal Recognition Based on ACVAE and CNN-LSTM
    Hu, Cunlin
    Ye, Ye
    Li, Jian
    Wang, Hongliang
    Zhou, Tao
    Xie, Nenggang
    2024 INTERNATIONAL CONFERENCE ON ELECTRONIC ENGINEERING AND INFORMATION SYSTEMS, EEISS 2024, 2024, : 197 - 202
  • [7] Use AF-CNN for End-to-End Fiber Vibration Signal Recognition
    Ruan, Saisai
    Mo, Jiaqing
    Xu, Liang
    Zhou, Gang
    Liu, Yajun
    Zhang, Xin
    IEEE ACCESS, 2021, 9 : 6713 - 6720
  • [8] A Network Intrusion Detection Method Based on CNN and CBAM
    Liu, Yang
    Kang, Jian
    Li, Yiran
    Ji, Bin
    IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021), 2021,
  • [9] Radar Emitter Recognition Based on CNN and LSTM
    Liu, Han
    Cheng, Donghang
    Sun, Xiaojun
    Wang, Feng
    2021 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, INFORMATION AND COMMUNICATION ENGINEERING, 2021, 11933
  • [10] Human Activity Recognition Based on CNN and LSTM
    Tan, Xu-Nan
    Journal of Computers (Taiwan), 2023, 34 (03) : 221 - 235