An Underwater Acoustic Target Recognition Method Based on Combined Feature With Automatic Coding and Reconstruction
Open accessAbstract
Underwater acoustic target recognition is one of the main functions of the SONAR systems. In this paper, a target recognition method based on combined features with automatic coding and reconstruction is proposed to classify ship radiated noise signals. In the existing underwater acoustic target recognition systems, the target category features are mostly constructed based on the power spectrum according to a certain presupposed model, and some useful information in the data is discarded artificially. In the proposed recognition method, a feature extractor based on auto-encoding is designed. The feature extractor uses the restricted Boltzmann machine (RBM) to automatically encode the combined data of the power spectrum and demodulation spectrum of ship radiated noise without supervision and extracts the deep data structure layer by layer to obtain the signal feature vector. The extracted feature vector is sent to a Back Propagation (BP) neural network to realize target recognition. Due to the high cost of ship radiated noise acquisition, the sample size of ship radiated noise signals is often hard to meet the needs of neural network training. A method of data augmentation is designed by RBM auto-encoder to construct the expanded sample set, which improves the performance of the recognition system. The experimental results based on the actual ship’s radiated noise show that the proposed method has better performance than the traditional methods.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A data-augmentation technique using an RBM autoencoder to reconstruct original signals produced mean squared error between reconstruction and original samples in the range 0.0115 to 0.5649, meaning the difference was minor and the properties were maintained.
“The mean squared error (MSE) between the reconstruction and the original samples was in the range of 0.0115 to 0.5649, meaning that the difference between the two signals was minor and the properties were maintained.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [123]
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measuredRBM autoencoders have been proposed to reconstruct original data for classification of vessels in passive sonar data.
“Boltzmann Machine (RBM) autoencoders have been proposed in [123], aiming at reconstructing the original data to be used in the classification of vessels in passive sonar data.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [123]
Neural-network models that include RBM as a denoising element greatly outperform the traditional Gaussian Mixture Model with a Gammatone Frequency Cepstral Coefficient feature-extraction layer.
“NN models that include RBM as a denoising element have been shown to greatly outperform the traditional Gaussian Mixture Model (GMM) with a Gammatone Frequency Cepstral Coefficient feature-extraction layer.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [123]
Unsupervised feature extraction with an RBM autoencoder plus combining the power spectrum and demodulation spectrum into the input data is a highly effective method for identifying ships from passive sonar signals.
“In this way, the use of an unsupervised feature-extraction approach with RBM autoencoder (to provide noise extraction and signal reconstruction) and the combination of the power spectrum and demodulation spectrum into the input data (recognising important rhythm features of the original sound) have been shown to be a highly effective method for identifying ships from passive sonar signals.”
From A Survey of Underwater Acoustic Data Classification Methods Using Deep Learning for Shoreline Surveillance (2022) · cites this paper as [123]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Flagged first, then by citations
Research works printed but not linked: 30
- P. T. Arveson and D. J. Vendittis, ''Radiated noise characteristics of a modern cargo ship,'' J. Acoust. Soc. Amer., vol. 107, no. 1, pp. 118-129, Jan. 2000, doi: 10.1121/1.428344. · DOI
- F. Bao, C. Li, X. Wang, Q. Wang, and S. Du, ''Ship classification using nonlinear features of radiated sound: An approach based on empirical mode decomposition,'' J. Acoust. Soc. Amer., vol. 128, no. 1, pp. 206-214, Jul. 2010, doi: 10.1121/1.3436543. · DOI
- Y. S. Cheng, J. X. Qiu, Z. Liu, and H. T. Li, ''Challenges and prospects of underwater acoustic passive target recognition technology,'' J. Appl. Acoust., vol. 38, no. 4, pp. 653-659, 2019.
- X. Cao, X. Zhang, R. Togneri, and Y. Yu, ''Underwater target classification at greater depths using deep neural network with joint multiple-domain fea- ture,'' IET Radar, Sonar Navigat., vol. 13, no. 3, pp. 484-491, Mar. 2019, doi: 10.1049/iet-rsn.2018.5279. · DOI
- G. Hu, K. Wang, Y. Peng, M. Qiu, J. Shi, and L. Liu, ''Deep learn- ing methods for underwater target feature extraction and recognition,'' Comput. Intell. Neurosci., vol. 2018, Oct. 2018, Art. no. 1214301, doi: 10.1155/2018/1214301. · DOI · Paper page
- J. Zhang and Y. Ding, ''Underwater target recognition based on spectrum learning with convolutional neural network,'' in Proc. IEEE 5th Inf. Technol. Mechatronics Eng. Conf. (ITOEC), Chongqing, China, Jun. 2020, pp. 1520-1523, doi: 10.1109/ITOEC49072.2020. 9141661. · DOI
- L. M. Gray and D. S. Greeley, ''Source level model for propeller blade rate radiation for the world's merchant fleet,'' J. Acoust. Soc. Amer., vol. 67, no. 2, pp. 516-522, Apr. 1997.
- W. K. McDowell, W. B. Mikhael, and A. P. Berg, ''Efficiency of the KLT on voiced & unvoiced speech as a function of segment size,'' in Proc. IEEE Southeastcon, Orlando, FL, USA, Mar. 2012, pp. 1-5.
- X. Zeng, Q. Wang, C. Zhang, and H. Cai, ''Feature selection based on ReliefF and PCA for underwater sound classification,'' in Proc. 3rd Int. Conf. Comput. Sci. Netw. Technol., Dalian, China, Oct. 2013, pp. 442-445.
- Z. B. Lu, X. H. Zhang, and J. Zhu, ''Feature extraction of ship-radiated noise based on Mel frequency cepstrum coeffcients,'' in Proc. Conf. Ship Sci. Technol., Feb. 2004, pp. 51-54.
- R. Salakhutdinov, J. B. Tenenbaum, and A. Torralba, ''Learning with hierarchical-deep models,'' IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1958-1971, Aug. 2013, doi: 10.1109/tpami. 2012.269. · DOI
- Y. Yang, F. Gao, X. Ma, and S. Zhang, ''Deep learning-based channel estimation for doubly selective fading channels,'' IEEE Access, vol. 7, pp. 36579-36589, 2019, doi: 10.1109/access.2019.2901066. · DOI
- G. Jin, F. Liu, H. Wu, and Q. Song, ''Deep learning-based framework for expansion, recognition and classification of underwater acoustic signal,'' J. Experim. Theor. Artif. Intell., vol. 32, no. 2, pp. 205-218, Mar. 2020, doi: 10.1080/0952813X.2019.1647560. · DOI
- R. Salakhutdinov and G. Hinton, ''An efficient learning procedure for deep Boltzmann machines,'' Neural Comput., vol. 24, no. 8, pp. 1967-2006, Aug. 2012, doi: 10.1162/NECO_a_00311. · DOI
- Q. Wang, L. Wang, X. Zeng, and L. Zhao, ''An improved deep clustering model for underwater acoustical targets,'' Neural Process. Lett., vol. 48, no. 3, pp. 1633-1644, Dec. 2018, doi: 10.1007/s11063-017-9755-7. · DOI
- C.-C. Chang and C.-J. Lin, ''LIBSVM,'' ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, pp. 1-27, Apr. 2011, doi: 10.1145/1961189.1961199. · DOI · Paper page
- C. Biernacki, G. Celeux, and G. Govaert, ''Assessing a mixture model for clustering with the integrated completed likelihood,'' IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 7, pp. 719-725, Jul. 2000, doi: 10.1109/34.865189. · DOI
- J. W. Xie, ''Research on underwater sound source separation technology based on deep learning,'' M.A. dissertation, Univ. Electron. Sci. Technol. China, Chengdu, China, 2019.
- X. Luo and Y. Feng, ''An underwater acoustic target recognition method based on restricted Boltzmann machine,'' Sensors, vol. 20, no. 18, p. 5399, Sep. 2020, doi: 10.3390/s20185399. · DOI
- S. L. Fang, S. P. Du, X. W. Luo, N. Han, and X. N. Xu, ''Feature analysis and recognition technology of underwater acoustic targets,'' Bull. Chin. Acad. Sci., vol. 2019, 34, pp. 297-305, doi: 10.16418/j.issn.1000- 3045.2019.03.007. · DOI
- D. Ross and W. A. Kuperman, ''Mechanics of underwater noise,'' J. Acoust. Soc. Amer., vol. 86, no. 4, p. 1626, Oct. 1989, doi: 10.1121/1.398685. · DOI
- Y. Wen and M. Henry, ''Time frequency characteristics of the vibroacoustic signal of hydrodynamic cavitation,'' J. Vib. Acoust., vol. 124, no. Oct. 2002, pp. 1-19, 2002.
- P. Clark, I. Kirsteins, and L. Atlas, ''Multiband analysis for colored amplitude-modulated ship noise,'' in Proc. IEEE ICASSP, Mar. 2010, pp. 3970-3973, doi: 10.1109/ICASSP.2010.5495776. · DOI
- D. Hanson, J. Antoni, G. Brown, and R. Emslie, ''Cyclostationarity for passive underwater detection of propeller craft: A development of DEMON processing,'' in Proc. Acoust., Nov. 2008, pp. 1-6.
- D. Santos-Domínguez, S. Torres-Guijarro, A. Cardenal-López, and A. Pena-Gimenez, ''ShipsEar: An underwater vessel noise database,'' Appl. Acoust., vol. 113, pp. 64-69, Dec. 2016, doi: 10.1016/j. apacoust.2016.06.008. · DOI
- F. Liu, Q. Song, and G. Jin, ''Expansion of restricted sample for underwater acoustic signal based on generative adversarial networks,'' in Proc. 10th Int. Conf. Graph. Image Process. (ICGIP), May 2019, Art. no. 1106948.
- Y. LeCun, Y. Bengio, and G. Hinton, ''Deep learning,'' Nature, vol. 521, no. 7553, pp. 436-444, May 2015, doi: 10.1038/nature14539. · DOI · Paper page
- G. F. Montufar, R. Pascanu, K. Cho, and Y. Bengio, ''On the number of linear regions of deep neural networks,'' in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 2924-2932.
- XINWEI LUO (Member, IEEE) received the B.S., M.S., and Ph.D. degrees from Southeast Univer- sity, Nanjing, China, in 2001, 2006, and 2013, respectively. He is currently an Associate Pro- fessor with the Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Educa- tion, Southeast University. His research interests include acoustic signal processing, target detec- tion, parameter estimation, and underwater target classification.
- YULIN FENG (Student Member, IEEE) received the B.S. degree from Northeast University, Shenyang, China, in 2019. He is currently pur- suing the master's degree with the Key Labora- tory of Underwater Acoustic Signal Processing of Ministry of Education, Southeast University. His research interests include acoustic signal process- ing, array signal processing, parameter estimation, and signal detection.
Cited by
Sorted by citations
Domingos, L. C. F., Santos, P. E., Skelton, P. S. M., Brinkworth, R. S. A., & Sammut, K. (2022) · Sensors · doi:10.3390/s22062181 · Cited by 93 · see citing works
“A data-augmentation technique was used in [123] to double the size of the dataset used to create the ShipsEar dataset (Section 3.”
BackgroundMethodInfluential
- Authors
- Luo, X., Feng, Y., & Zhang, M.
- Affiliations
- Southeast University (CN)
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 63841-63854
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3158291757
- Cited by
- 47
- References
- 1
- Citations by year
- 2026: 7 · 2025: 10 · 2024: 13 · 2023: 10 · 2022: 5 · 2021: 2
- FWCI
- 3.61
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (11674057, 91938203, 11704069, 11874109)
- Fundamental Research Funds for Central Universities (2242021K30019)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Oceanography › Underwater Acoustics Research
- Physical Sciences › Engineering › Ocean Engineering › Underwater Vehicles and Communication Systems
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- underwater acoustic target recognition, ship radiated noise, sonar, restricted Boltzmann machine, autoencoder, feature extraction, power spectrum, data augmentation, BP neural network
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
