A new low SNR underwater acoustic signal classification method based on intrinsic modal features maintaining dimensionality reduction

• Autorzy: Ju Yang , Wei Zhengxian , Li Huangfu , Feng Xiao

Identyfikatory

DOI

10.2478/pomr-2020-0040

• Języki publikacji: EN

Abstrakty

EN

The classification of low signal-to-noise ratio (SNR) underwater acoustic signals in complex acoustic environments and increasingly small target radiation noise is a hot research topic. . This paper proposes a new method for signal processing—low SNR underwater acoustic signal classification method (LSUASC)—based on intrinsic modal features maintaining dimensionality reduction. Using the LSUASC method, the underwater acoustic signal was first transformed with the Hilbert-Huang Transform (HHT) and the intrinsic mode was extracted. the intrinsic mode was then transformed into a corresponding Mel-frequency cepstrum coefficient (MFCC) to form a multidimensional feature vector of the low SNR acoustic signal. Next, a semi-supervised fuzzy rough Laplacian Eigenmap (SSFRLE) method was proposed to perform manifold dimension reduction (local sparse and discrete features of underwater acoustic signals can be maintained in the dimension reduction process) and principal component analysis (PCA) was adopted in the proces of dimension reduction to define the reduced dimension adaptively. Finally, Fuzzy C-Means (FCMs), which are able to classify data with weak features was adopted to cluster the signal features after dimensionality reduction. The experimental results presented here show that the LSUASC method is able to classify low SNR underwater acoustic signals with high accuracy.

Słowa kluczowe

EN

acoustic; low SNR; signal classification; feature maintain; dimension reduction

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2020
• Tom: nr 2
• Strony: 187--198
• Opis fizyczny: Bibliogr. 22 poz., rys., tab.

Twórcy

autor

Ju Yang

• Science and Technology on Underwater Acoustic Antagonizing Laboratory, 1 Fengxian East Road, Haidian District, 100094 Beijing, China

autor

Wei Zhengxian

• System Engineering Innovation Center, Systems Engineering Research Institute, 1 Fengxian East Road, Haidian District, 100094 Beijing, China

autor

Li Huangfu

• Science and Technology on Underwater Acoustic Antagonizing Laboratory, 1 Fengxian East Road, Haidian District, 100094 Beijing, China

autor

Feng Xiao

• Science and Technology on Underwater Acoustic Antagonizing Laboratory, 1 Fengxian East Road, Haidian District, 100094 Beijing, China

Bibliografia

• 1. Bacry E, Arneodo A, Frisch U, et al. (1989): Wavelet analysis of fully developed turbulence data and measurement of scaling exponents. Proceedings of Turbulence 89: Organized Structures and Turbulence in Fluid Mechanics.
• 2. Chinchu, M, and M. H. Supriya. (2016): Real time target recognition using Labview. International Symposium on Ocean Electronics, IEEE.
• 3. Christopher B, Alric A, Paul D.C, Ryan K. (2016): A Brain-Computer Interface (BCI) for the Detection of Mine-like Objects in Sidescan Sonar Imagery. Journal of Oceanic Engineering, IEEE, No. 1, Vol. 41, p. 124–139.
• 4. Detection and Classification of Acoustic Scenes and Events(2016): Outcome of the DCASE 2016 Challenge.
• 5. Esfahanian M, Zhuang H, Erdol N. (2013): Using Local Binary Pattern as Features for Classification of Dolphin Calls. Journal of the Acoustical Society of America, No. 1, Vol. 134, p.105–111.
• 6. Feng Y, Tao R, Wang Y. (2012): Modeling and feature analysis of underwater acoustic signal of accelerating propeller. Science China Information Sciences, No. 2, Vol. 55, p. 270–280.
• 7. Flandrin P. (1999): Time-Frequency/Time-Scale Analysis. Academic Press.
• 8. Gao Ch., Liu H. (2018): Passive localization for mixed-field moving sources. Polish Maritime Research, Special Issue 2018 S2(98), Vol. 25, 69–74.
• 9. Hong, Yang, Y. Li, and G. Li. (2016): Feature extraction and classification for underwater target signals based on Hilbert-Huang transform theory. Indian Journal of Geo-Marine Sciences, No. 10, Vol. 45, p. 1272-1278.
• 10. Huang N. E, Sheen Z. Steven R. L, et al. (1998): The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis. Proc. R. Soc. Lond. A, Vol. 454, p. 903–995.
• 11. Li, Haitao, et al. (2015): A method based on wavelet packetsfractal and SVM for underwater acoustic signals recognition. International Conference on Signal Processing, IEEE, p. 2169–2173.
• 12. Li, X. K., L. Xie, and Y. Qin. (2009): Underwater target feature extraction using Hilbert-Huang transform. Journal of Harbin Engineering University, No. 5, Vol. 30, p. 542–546.
• 13. Liu, Hui, et al. (2017): Novel Research on Feature Extraction of Acoustic Targets Based on Manifold Learning. International Conference on Computer Science and Applications, IEEE, p. 227–231.
• 14. Oswald. J. N, Au W. W. L. (2011): Minke whale (Balanoptera acutorostrata) boings detected at the Station ALOHA Cabled Observatory. Journal of the Acoustical Society of America, No. 5, Vol. 129, p. 3353–3360.
• 15. Sherin, B. M. and M. H. Supriya. (2016): SOS-based selection and parameter optimization for underwater target classification. Oceans, IEEE, p. 1–4.
• 16. Song H J, Xu F, Zheng B Y, etc. (2015): An Artificial Intelligence Recognition Algorithm for Yangtze Finless Porpoise. OCEANS’15 MTS/IEEE, Washington. 19–22 Oct.
• 17. Sun, Lu, et al. (2017):READER: Robust Semi-Supervised Multi-Label Dimension Reduction. Transactions on Information & Systems, E100.D.10, p. 2597–2604.
• 18. Wang B, He Ch. (2017): Underwater target direction of arrival estimation by small acoustic sensor array based on sparse Bayesian learning. Polish Maritime Research, Special Issue 2017 S2 (94), Vol. 24, pp. 95–102.
• 19. Wens F J, Murphy M S. (1988): A short-time Fourier transform. Signal Processing, No. 1, Vol. 14, p. 3–10.
• 20. Wang S G, Zeng X Y. (2014): Robust underwater noise target classification using auditory inspired time-frequency analysis. Applied Acoustics, No. 4, Vol. 78, p. 68–76.
• 21. Wang, Wenbo, et al. (2016): Feature ex5traction of underwater target in auditory sensation area based on MFCC. Ocean Acoustics, IEEE, p. 1–6.
• 22. Zhang, Lanyue, et al. (2016): Feature Extraction of Underwater Target Signal Using Mel Frequency Cepstrum Coefficients Based on Acoustic Vector Sensor. Journal of Sensors, Vol. 4, p. 1–11.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).