Research on Underwater Targets Recognition Based on Decision-Makings Fusion

Abstract:

A current problem in the development of passive sonar is the classification of different noise sources. The existing Automatic Underwater Target Recognition Technique (AURT) is mainly based on spectrum analysis of radiated noise in passive sonar. However, with the development of noise control techniques, the radiated noise of underwater targets have been reduced enormously in the past few years, even the working states of the same target also weaken the stationarity of spectrum features of its radiated noise. The objective of this paper concentrates on the AURT with multi-method analysis on radiated noise and decision-makings fusion. A kind of multi-classifier decision-makings fusion model to overcome the non-stationarity is presented. Its application of the model on the data derived from sea trial confirms its validation even in the case of low SNR, and the classification rate is above 83%, better than that of spectrum analysis only.

• Periodical: Advanced Materials Research (Volumes 546-547)
• Pages: 458-463
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.546-547.458
• Online since: July 2012
• Authors: Yue Hui Teng, Ping Xiang Liu
• Keywords: Decision-Makings Fusion, Feature Extraction, Target Recognition, Underwater Target

References

[1] Y.W. Ding: Review on passive sonar target recognition. Technical Acoustics, vol. 24(2004) No. 4, p.253.

[2] J.L. Terry, A. Crampton and C.J. Talbot: Passive Sonar Harmonic Detection Using Feature Extraction and Clustering Analysis. Oceans, 2005, Proceeding of MTS/IEEE, vol. 3(2005), p.2760.

DOI: 10.1109/oceans.2005.1640192

[3] G.Q. Wu: Ship radiate-noise recognition(I) the overall framework, analysis and extraction of line-spectrum, Acta Acustic, Beijing, vol. 23(1998) No. 5, p.394.

[4] J.W. Yin : Extraction of shaft frequency based on the DEMON line spectrum. Acta Acustic, vol. 25(2005) No. 6, p.369.

[5] F. Tong ,J.R. Lu,S.L. Fang: method to estimate the propeller shaft rate in underwater acoustic vessel classification. Acta Acustic, vol. 29(2004)No. 5, p.398.

[6] C.Y. Kang and X.H. Zhang: A Fusion Algorithm of Multiple Classifers for Recognition of Ships Radiated-Noise Based on Many-Person Decision-Making Thoery. Fourth International Conference on Fuzzy Systems and Knowledge Discovery , vol. 2(2007), p.71.

DOI: 10.1109/fskd.2007.29

[7] D.E. Nelson, J.A. Starzyk and D. D. Ensley: Wavelet transformation and signal discrimination for HRR radar target recognition. Multidimensional Systems and Signal Processing, vol. 14(2003), Numbers1-3, p.9.

DOI: 10.1007/978-1-4757-6342-3_1

[8] L.R. Wang: Research of Target Detection Base on Wavelet Transform(Ph.D., JiLin University, China, 2006 ).

[9] N. E. Huang,Z. Shen and R.L. steven et al: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non- stationary time series analysis, Proc. Royal Soc. London A, vol. 454(1998), No. 1971, p.903.

DOI: 10.1098/rspa.1998.0193

[10] N. E. Huang M.C. Wu and R.L. Steven et al: A confidence limit for the empirical mode decomposition and Hilbert spectral analysis. the Royal Society. Vol. 459(2003), No. 2037, p.2317.

[11] Y.H. Teng, P.X. Liu and Y.Z. Dong : The application of empirical mode decomposition to underwater targets classification. Ship Science and technology, Beijing, vol. 32(2010), p.66.

[12] H.D. Li: Modes classification(First edition). China Machine Press, China, 2009, p.230.

[13] Y.H. Kang: The theory of data fusion and its application (Second edition ). Xi'an: XDU Press, China, 2006, p.38.