TY - JOUR
T1 - A classification method of ship radiated noise based on simulation signal of variational auto-encoder
AU - Chen, Chuang
AU - Shen, Xiaohong
AU - Ma, Shilei
AU - Wang, Haiyan
N1 - Publisher Copyright:
© 2021 Institute of Physics Publishing. All rights reserved.
PY - 2021/10/8
Y1 - 2021/10/8
N2 - The performance of the classifier is weak when the number of the ship radiated noise samples is insufficient. Aiming at above problem, this paper proposes a classification method of ship radiated noise based on simulation signal of variational auto-encoder (VAE). First, build a VAE model, input the real ship radiated noise signals into the model to generate a large number of VAE simulation signals. Then, extract the typical features of simulation signals, and use these features to pretrain a convolutional neural network (CNN) classification model. Finally extract the typical features of the real signals to be predicted, and use the pretrained CNN to complete the classification. Experimental results show that the classification accuracy of the pretrained CNN model is 6% to 12% higher than that of the non-pretrained CNN model.
AB - The performance of the classifier is weak when the number of the ship radiated noise samples is insufficient. Aiming at above problem, this paper proposes a classification method of ship radiated noise based on simulation signal of variational auto-encoder (VAE). First, build a VAE model, input the real ship radiated noise signals into the model to generate a large number of VAE simulation signals. Then, extract the typical features of simulation signals, and use these features to pretrain a convolutional neural network (CNN) classification model. Finally extract the typical features of the real signals to be predicted, and use the pretrained CNN to complete the classification. Experimental results show that the classification accuracy of the pretrained CNN model is 6% to 12% higher than that of the non-pretrained CNN model.
KW - Convolutional neural network
KW - Ship target classification
KW - Small sample
KW - Variational auto-encoder
UR - http://www.scopus.com/inward/record.url?scp=85117461175&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/2026/1/012039
DO - 10.1088/1742-6596/2026/1/012039
M3 - 会议文章
AN - SCOPUS:85117461175
SN - 1742-6588
VL - 2026
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012039
T2 - 2021 2nd International Conference on Computer Science and Communication Technology, ICCSCT 2021
Y2 - 29 July 2021 through 31 July 2021
ER -