Semi-supervised underwater acoustic source localization based on residual convolutional autoencoder

Passive localization of underwater targets was a thorny problem in underwater acoustics. For traditional model-driven passive localization methods, the main challenges are the inevitable environmental mismatch and the presence of interference and noise everywhere. In recent years, data-driven machin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:EURASIP journal on advances in signal processing Ročník 2022; číslo 1; s. 1 - 20
Hlavní autoři: Jin, Pian, Wang, Biao, Li, Lebo, Chao, Peng, Xie, Fangtong
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 01.12.2022
Springer
Springer Nature B.V
SpringerOpen
Témata:
Acoustics
Advances in Underwater Signal Processing for SONAR
AUV and Communications Applications
Coders
Computational linguistics
Convolutional autoencoder
Data mismatch
Datasets
Engineering
Feature extraction
Language processing
Localization
Machine learning
Multilayer perceptrons
Natural language interfaces
Quantum Information Technology
Self-attentive mechanism
Semi-supervised learning
Signal,Image and Speech Processing
Sound sources
Spintronics
Underwater acoustic source localization
Underwater acoustics
China
Underwater acoustic source localization
Self-attentive mechanism
Semi-supervised learning
Convolutional autoencoder
Data mismatch
ISSN:1687-6180, 1687-6172, 1687-6180
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Passive localization of underwater targets was a thorny problem in underwater acoustics. For traditional model-driven passive localization methods, the main challenges are the inevitable environmental mismatch and the presence of interference and noise everywhere. In recent years, data-driven machine learning approaches have opened up new possibilities for passive localization of underwater acoustics. However, the acquisition and processing of underwater acoustics data are more restricted than other scenarios, and the lack of data is one of the most enormous difficulties in the application of machine learning to underwater acoustics. To take full advantage of the relatively easy accessed unlabeled data, this paper proposes a framework for underwater acoustic source localization based on a two-step semi-supervised learning classification model. The first step is trained in unsupervised mode with the whole available dataset (labeled and unlabeled dataset), and it consists of a convolutional autoencoder (CAE) for feature extraction and self-attention (RA) mechanism for picking more useful features by applying constraints on the CAE. The second step is trained in supervised mode with the labeled dataset, and it consists of a multilayer perceptron connected to an encoder from the first step and is used to perform the source location task. The proposed framework is validated on uniform vertical line array data of SWellEx-96 event S5. Compared with the supervised model and the model without the RA, the proposed framework maintains good localization performance with the reduced labeled dataset, and the proposed framework is more robust when the training dataset and the test dataset of the second step are distributed differently, which is called “data mismatch.”
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-6180
1687-6172
1687-6180
DOI:10.1186/s13634-022-00941-9