Unsupervised Classification of Hydrophone Signals With an Improved Mel-Frequency Cepstral Coefficient Based on Measured Data Analysis

Recently, passive detection technology has developed the ability to detect surface ships based on the noise emissions recorded by hydrophones, making it possible in some cases to classify surface ships. One of the most concerning issues with ships and underwater targets is the current lack of reliable features for unsupervised classification. To solve this problem, this paper proposes an improved Mel-frequency cepstral coefficients (IMFCC) feature for unsupervised clustering of marine targets. As the feature extraction of hydrophone signals rely on preprocessing, the IMFCC adds cyclic modulation spectrum (CMS) and cross-correlation bispectrum (CCB) in the preprocessing module before traditional the Mel-frequency cepstral coefficient process, and the principal component analysis (PCA) is added as the backend processing module. There are four contributions as follows: First, for IMFCC extraction, it combines the advantages of the CMS, CCB, MFCC, and PCA. Second, the two common unsupervised clusters, Gaussian mixture model (GMM) and fuzzy C-means are used to evaluate the CMS, CCB, and several MFCCs—MFCC-vector quantization (MFCC-VQ), MFCC-Gaussian mixture model (MFCC-GMM), TEO-MFCC (Teager Energy Operator based MFCC), and IMFCC. Third, the performances of traditional MFCC, Teager-energy operator (TEO)-MFCC, IMFCC, MFCC-VQ, and MFCC-GMM are discussed under different dimensions, signal-to-noise ratios, distances, and depths. Finally, the experimental results prove that the IMFCC method has a strong anti-interference ability and is robust and has a high-success rate for clustering multitarget or different depth targets, which enables the IMFCC to be a reliable feature for unsupervised classification.

[1]  Seyed Mostafa Mirhassani,et al.  Fuzzy-based discriminative feature representation for children's speech recognition , 2014, Digit. Signal Process..

[2]  Keun-Sung Bae,et al.  Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network , 2008, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[3]  Paul R. White,et al.  Practical Issues Concerning the Use of Bicoherence for the detection of quadratic phase coupling , 1995 .

[4]  Alexander Sutin,et al.  Improvement of the Detection of Envelope Modulation on Noise (DEMON) and its application to small boats , 2016, OCEANS 2016 MTS/IEEE Monterey.

[5]  J. Antoni,et al.  Detection of Surface Ships From Interception of Cyclostationary Signature With the Cyclic Modulation Coherence , 2012, IEEE Journal of Oceanic Engineering.

[6]  R.J. Rak,et al.  Denoising based on wavelet and PCA signal compression , 2005, IEEE International Workshop on Intelligent Signal Processing, 2005..

[7]  Dattatraya S. Bormane,et al.  Automatic musical instrument classification using fractional fourier transform based- MFCC features and counter propagation neural network , 2015, Journal of Intelligent Information Systems.

[8]  A. Enis Çetin,et al.  Recognition of vessel acoustic signatures using non-linear teager energy based features , 2016, 2016 International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM).

[9]  Zhang Guo-jun,et al.  A method for extracting the characteristic spectral line from the ship-radiated noises , 2010, 2010 2nd International Conference on Signal Processing Systems.

[10]  Deshmukh Sachin,et al.  Dimensionality Reduction and Classification through PCA and LDA , 2015 .

[11]  S. Elgar,et al.  Statistics of bicoherence and biphase , 1989 .

[12]  Wei-bin Zhang,et al.  IFCM:Fuzzy clustering for rule extraction of interval Type-2 fuzzy logic system , 2007, 2007 46th IEEE Conference on Decision and Control.

[13]  Manas Ranjan Jena,et al.  Mel-Frequency Cepstral Coefficient (MFCC) - a Novel Method for Speaker Recognition , 2014 .

[15]  Milica Stojanovic,et al.  Underwater acoustic communication channels: Propagation models and statistical characterization , 2009, IEEE Communications Magazine.

[16]  Shogo Muramatsu,et al.  Interval calculation of EM algorithm for GMM parameter estimation , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[17]  Monika Agrawal,et al.  Underwater acoustic noise with generalized Gaussian statistics: Effects on error performance , 2013, 2013 MTS/IEEE OCEANS - Bergen.

[18]  Divya Kumar,et al.  Speaker Recognition for Hindi Speech Signal using MFCC-GMM Approach , 2018 .

[19]  Phillip Joseph,et al.  Investigation of Rotor Wake Turbulence Through Cyclostationary Spectral Analysis , 2009 .

[20]  Sazali Yaacob,et al.  Classification of speech dysfluencies with MFCC and LPCC features , 2012, Expert Syst. Appl..

[21]  Gao Xinbo,et al.  A novel FCM clustering algorithm for interval-valued data and fuzzy-valued data , 2000, WCC 2000 - ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000.

[22]  Karen O. Egiazarian,et al.  Practical Poissonian-Gaussian Noise Modeling and Fitting for Single-Image Raw-Data , 2008, IEEE Transactions on Image Processing.