{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:54:04Z","timestamp":1781880844992,"version":"3.54.5"},"reference-count":33,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T00:00:00Z","timestamp":1618272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Norwegian Research Council and the industry partners of the GAMES consortium at NTNU","award":["294404"],"award-info":[{"award-number":["294404"]}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201903170205"],"award-info":[{"award-number":["201903170205"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Underwater source localization is an important task, especially for real-time operation. Recently, machine learning methods have been combined with supervised learning schemes. This opens new possibilities for underwater source localization. However, in many real scenarios, the number of labeled datasets is insufficient for purely supervised learning, and the training time of a deep neural network can be huge. To mitigate the problem related to the low number of labeled datasets available, we propose a two-step framework for underwater source localization based on the semi-supervised learning scheme. The first step utilizes a convolutional autoencoder to extract the latent features from the whole available dataset. The second step performs source localization via an encoder multi-layer perceptron trained on a limited labeled portion of the dataset. To reduce the training time, an interpretable feature selection (FS) method based on principal component regression is proposed, which can extract important features for underwater source localization by only introducing the source location without other prior information. The proposed approach is validated on the public dataset SWellEx-96 Event S5. The results show that the framework has appealing accuracy and robustness on the unseen data, especially when the number of data used to train gradually decreases. After FS, not only the training stage has a 95% acceleration but the performance of the framework becomes more robust on the receiver-depth selection and more accurate when the number of labeled data used to train is extremely limited.<\/jats:p>","DOI":"10.3390\/rs13081486","type":"journal-article","created":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T05:31:37Z","timestamp":1618291897000},"page":"1486","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Feature Selection Based on Principal Component Regression for Underwater Source Localization by Deep Learning"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-239X","authenticated-orcid":false,"given":"Xiaoyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology, 7491 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-3838","authenticated-orcid":false,"given":"Hefeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology, 7491 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6834-8482","authenticated-orcid":false,"given":"Pierluigi","family":"Salvo Rossi","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology, 7491 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4556-2667","authenticated-orcid":false,"given":"Martin","family":"Landr\u00f8","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology, 7491 Trondheim, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1121\/1.396151","article-title":"Matched field processing: Source localization in correlated noise as an optimum parameter estimation problem","volume":"83","author":"Baggeroer","year":"1988","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1121\/1.405257","article-title":"Comparative performance of matched-mode and matched-field localization in a range-dependent environment","volume":"92","author":"Bogart","year":"1992","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/48.262292","article-title":"An overview of matched field methods in ocean acoustics","volume":"18","author":"Baggeroer","year":"1993","journal-title":"IEEE J. Ocean. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1121\/1.4728224","article-title":"Compressive matched-field processing","volume":"132","author":"Mantzel","year":"2012","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1121\/1.4863270","article-title":"Data-based matched-mode source localization for a moving source","volume":"135","author":"Yang","year":"2014","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_6","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press Cambridge."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, R., Zhang, W., and Wang, X. (2020). Machine Learning in Tropical Cyclone Forecast Modeling: A Review. Atmosphere, 11.","DOI":"10.3390\/atmos11070676"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ghahramani, Z. (2003). Unsupervised learning. Summer School on Machine Learning, Springer.","DOI":"10.1007\/978-3-540-28650-9_5"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.apacoust.2016.10.005","article-title":"Direct regressions for underwater acoustic source localization in fluctuating oceans","volume":"116","author":"Lefort","year":"2017","journal-title":"Appl. Acoust."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1121\/1.5000165","article-title":"Source localization in an ocean waveguide using supervised machine learning","volume":"142","author":"Niu","year":"2017","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"EL455","DOI":"10.1121\/1.5010064","article-title":"Ship localization in Santa Barbara Channel using machine learning classifiers","volume":"142","author":"Niu","year":"2017","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.1121\/1.5032311","article-title":"Underwater acoustic source localization using generalized regression neural network","volume":"143","author":"Wang","year":"2018","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2922","DOI":"10.1121\/1.5036725","article-title":"Source localization using deep neural networks in a shallow water environment","volume":"143","author":"Huang","year":"2018","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"044302","DOI":"10.1088\/0256-307X\/36\/4\/044302","article-title":"Source ranging using ensemble convolutional networks in the direct zone of deep water","volume":"36","author":"Liu","year":"2019","journal-title":"Chin. Phys. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1121\/1.5116016","article-title":"Deep-learning source localization using multi-frequency magnitude-only data","volume":"146","author":"Niu","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"EL317","DOI":"10.1121\/1.5126923","article-title":"Deep transfer learning for source ranging: Deep-sea experiment results","volume":"146","author":"Wang","year":"2019","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhu, M., Wu, Y., and Zhang, W. (2020, January 12\u201315). Passive Source Ranging Using Residual Neural Network With One Hydrophone in Shallow Water. Proceedings of the 2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP), Shanghai, China.","DOI":"10.1109\/ICICSP50920.2020.9232070"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhai, X., Oliver, A., Kolesnikov, A., and Beyer, L. (2019, January 27\u201328). S4l: Self-supervised semi-supervised learning. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Bianco, M.J., Gannot, S., and Gerstoft, P. (2020). Semi-supervised source localization with deep generative modeling. arXiv.","DOI":"10.1109\/MLSP49062.2020.9231825"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Samarasinghe, P.N., Abhayapala, T.D., and Gannot, S. (2020, January 4\u20138). Unsupervised Multiple Source Localization Using Relative Harmonic Coefficients. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053656"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zeng, X., Wang, Q., Zhang, C., and Cai, H. (2013, January 12\u201313). Feature selection based on ReliefF and PCA for underwater sound classification. Proceedings of the 2013 3rd International Conference on Computer Science and Network Technology, Dalian, China.","DOI":"10.1109\/ICCSNT.2013.6967149"},{"key":"ref_22","unstructured":"Ouelha, S., Mesquida, J.R., Chaillan, F., and Courmontagne, P. (2013, January 21\u201325). Extension of maximal marginal diversity based feature selection applied to underwater acoustic data. Proceedings of the 2013 OCEANS-San Diego, San Diego, CA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yang, H., Gan, A., Chen, H., Pan, Y., Tang, J., and Li, J. (2016, January 12\u201316). Underwater acoustic target recognition using SVM ensemble via weighted sample and feature selection. Proceedings of the 2016 13th International Bhurban Conference on Applied Sciences and Technology (IBCAST), Islamabad, Pakistan.","DOI":"10.1109\/IBCAST.2016.7429928"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1016\/j.eswa.2007.07.021","article-title":"Improving classification performance of sonar targets by applying general regression neural network with PCA","volume":"35","author":"Erkmen","year":"2008","journal-title":"Expert Syst. Appl."},{"key":"ref_25","unstructured":"Jackson, J.E. (2005). A User\u2019s Guide to Principal Components, John Wiley & Sons."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1016\/S0950-3293(03)00015-6","article-title":"Variable selection in PCA in sensory descriptive and consumer data","volume":"14","author":"Westad","year":"2003","journal-title":"Food Qual. Prefer."},{"key":"ref_27","unstructured":"CAMO ASA Norway (1998). The Unscrambler User Manual, CAMO ASA Norway."},{"key":"ref_28","unstructured":"Esbensen, K.H., Guyot, D., Westad, F., and Houmoller, L.P. (2002). Multivariate Data Analysis: In Practice: An Introduction to Multivariate Data Analysis and Experimental Design, CAMO Process As."},{"key":"ref_29","unstructured":"Murray, J., and Ensberg, D. (2021, March 01). The Swellex-96 Experiment. Available online: http:\/\/http:\/\/swellex96.ucsd.edu\/index.htm."},{"key":"ref_30","first-page":"313","article-title":"Combining bilinear modelling and ridge regression","volume":"16","author":"Westad","year":"2002","journal-title":"J. Chemom. A J. Chemom. Soc."},{"key":"ref_31","first-page":"3","article-title":"Autoencoders, minimum description length and Helmholtz free energy","volume":"6","author":"Hinton","year":"1994","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","unstructured":"Chen, M., Shi, X., Zhang, Y., Wu, D., and Guizani, M. (2017). Deep features learning for medical image analysis with convolutional autoencoder neural network. IEEE Trans. Big Data."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Du, J.Y., Liu, Z.W., and L\u00fc, L.G. (2020). Range Localization of a Moving Source Based on Synthetic Aperture Beamforming Using a Single Hydrophone in Shallow Water. Appl. Sci., 10.","DOI":"10.3390\/app10031005"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/8\/1486\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:47:19Z","timestamp":1760161639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/8\/1486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,13]]},"references-count":33,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,4]]}},"alternative-id":["rs13081486"],"URL":"https:\/\/doi.org\/10.3390\/rs13081486","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,13]]}}}