Xinzhou XU, Xinwei LUO, Chen WU, Li ZHAO

Ship-radiated noise feature extraction using multiple kernel graph embedding and auditory model

The analysis of underwater acoustic signals, especially ship-radiated noise received by passive sonar, is of great importance in the fields of defense, military, and scientific research. In this paper, we investigate multiple kernel learning graph embedding using auditory model features in the application of ship-radiated noise feature extraction. We use an auditory model to get auditory model features for each signal sample. In order to have more effective features, iterative multiple kernel learning methods are adopted to conduct dimensionality reduction. Validated by experiments, the proposed method outperforms ordinary kernel-based graph embedding methods. The experiments show that the multiple kernel learning method can automatically choose relatively appropriate kernel combinations in dimensionality reduction for ship-radiated noise using auditory model features. In addition, some worthwhile conclusions can be drawn from our experiments and analysis

PDF

___

[1] Lourens J, Coetzer M. Detection of mechanical ship features from underwater acoustic sound. In: IEEE Conference on Acoustics, Speech and Signal Processing; 69 April 1987; Dallas, TX, USA. New York, NY, USA: IEEE. pp. 1700-1703.
[2] Lourens J. Classification of ships using underwater radiated noise. In: IEEE Conference on Communication and Signal Processing; 24 June 1988; Pretoria, South Africa. New York, NY, USA: IEEE. pp. 130-134.
[3] Seol H, Suh J, Lee S. Development of hybrid method for the prediction of underwater propeller noise. J Sound Vib 2005; 288: 345-360.
[4] Arveson P, Vendittis D. Radiated noise characteristics of a modern cargo ship. J Acoust Soc Am 2000; 107: 118-129.
[5] Roweis S, Saul L. Nonlinear dimensionality reduction by locally linear embedding. Science 2000; 290: 2323-2326.
[6] Belkin M, Niyogi P. Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neutral Information Processing Systems; 38 December 2001; Vancouver, Canada. pp. 585-591.
[7] Tenenbaum J, de Silva V, Langford J. A global geometric framework for nonlinear dimensionality reduction. Science 2000; 290: 2319-2323.
[8] Donoho D, Grimes C. Hessian eigenmaps: locally linear embedding techniques for high-dimensional data. P Natl Acad Sci USA 2003; 100: 5591-5596.
[9] He X, Cai D, Yan S, Zhang H. Neighborhood preserving embedding. In: IEEE Conference on Computer Vision; 1521 October 2005; Beijing, China. New York, NY, USA: IEEE. pp. 1208-1213.
[10] He X, Niyogi P. Locality preserving projections. In: Advances in Neural Information Processing Systems; 1318 December 2004; Whistler, Canada. pp. 153-160.
[11] Yan S, Xu D, Zhang B, Zhang H, Yang Q, Lin S. Graph embedding and extensions: a general framework for dimensionality reduction. IEEE T Pattern Anal 2007; 29: 40-51.
[12] Chen H, Chang H, Liu T. Local discriminant embedding and its variants. In: IEEE Conference on Computer Vision and Pattern Recognition; 2026 June 2005; San Diego, CA, USA. New York, NY, USA: IEEE. pp. 846-853.
[13] Cai D, He X, Han J. Semi-supervised discriminant analysis. In: IEEE Conference on Computer Vision; 1420 October 2007; Rio de Janeiro, Brazil. New York, NY, USA: IEEE. pp. 1-7.
[14] Cortes C, Vapnik V. Support vector networks. Mach Learn 1995; 20: 273-297.
[15] Smola A. Learning with kernels. PhD, GMD, Birlinghoven, Germany, 1998.
[16] Fisher R. The use of multiple measurements in taxonomic problems. Ann Hum Genet 1936; 7: 179-188.
[17] Fisher R. The statistical utilization of multiple measurements. Ann Hum Genet 1938; 8: 376-386.
[18] Theodoridis S, Koutroumbas K. Pattern Recognition. New York, NY, USA: Elsevier, 2006.
[19] Bishop C. Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2007.
[20] Mika S, R¨atsch G, Weston J, Sch¨olkopf B, M¨uller K. Fisher discriminant analysis with kernels. In: IEEE Neural Networks for Signal Processing Workshop; 25 August 1999; Madison, WI, USA. New York, NY, USA: IEEE. pp.41-48.
[21] Yang J, Frangi A, Yang J, Zhang D, Jin Z. KPCA plus LDA: a complete kernel Fisher discriminant framework for feature extraction and recognition. IEEE T Pattern Anal 2005; 27: 230-244.
[22] Yang M, Ahuja N, Kriegman D. Face recognition using kernel eigenfaces. In: IEEE Conference on Image Processing; 1013 September 2000; Vancouver, Canada. New York, NY, USA: IEEE. pp. 37-40.
[23] Kim S, Magnani A, Boyd S. Optimal kernel selection in kernel fisher discriminant analysis. In: IEEE Conference on Machine Learning; 2529 June 2006; Pittsburgh, PA, USA. New York, NY, USA: IEEE. pp. 465-472.
[24] Lin Y, Liu T, Fuh C. Dimensionality reduction for data in multiple feature representations. In: Advances in Neural Information Processing Systems; 68 December 2009; Vancouver, Canada. pp. 961-968.
[25] Lin Y, Liu T, Fuh C. Multiple kernel learning for dimensionality reduction. IEEE T Pattern Anal 2011; 33: 1147- 1160.
[26] Wang Z, Chen S, Sun T. MultiK-MHKS: a novel multiple kernel learning algorithm. IEEE T Pattern Anal 2008; 30: 348-353.
[27] Quatieri T. Discrete-Time Speech Signal Processing: Principles and Practice. New York, NY, USA: Pearson Education, 2008.
[28] Lyon R, Mead C. An analog electronic cochlea. IEEE T Acoust Speech 1988; 36: 1119-1134.
[29] Patterson R, Nimmo-Smith I, Holdsworth J, Rice P. An efficient auditory filterbank based on the gammatone function. In: A Meeting of the IOC Speech Group on Auditory Modelling at RSRE; 1987.
[30] Yang X, Wang K, Shamma S. Auditory representations of acoustic signals. IEEE T Inform Theory 1992; 38: 824-839.
[31] Teolis A, Shamma S. Classification of the Transient Signals via Auditory Representations. Tech Rep TR91-99. College Park, MD, USA: Institute for Systems Research, 1991.
[32] Tucker S, Brown G. Classification of transient sonar sounds using perceptually motivated features. IEEE J Oceanic Eng 2005; 30: 588-600.
[33] Tucker S. Auditory analysis of sonar signals. PhD transfer report. Sheffield, UK: University of Sheffield, 2001.
[34] Parks T, Weisburn B. Classification of whale and ice sounds with a cochlear model. In: IEEE Conference on Acoustics, Speech and Signal Processing; 2326 March 1992; San Francisco, CA, USA. New York, NY, USA: IEEE.pp. 481-484.
[35] dAspremont A, Boyd S. Relaxations and Randomized Methods for Nonconvex QCQPs. Tech. Rep. Stanford, CA, USA: Stanford University, 2003.
[36] Slaney M. Auditory Toolbox: A MATLAB Toolbox for Auditory Modeling Work (Version 2). Tech Rep 1998: #1998-010. West Lafayette, IN, USA: Purdue University, 1998.