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

• Published in: EURASIP journal on advances in signal processing 2022-12, Vol.2022 (1), p.1-20, Article 107
• Main Authors: Jin, Pian, Wang, Biao, Li, Lebo, Chao, Peng, Xie, Fangtong
• Format: Article
• Language: English
• Subjects: 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
• ISSN: 1687-6180; 1687-6172; 1687-6180
• DOI: 10.1186/s13634-022-00941-9

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.”