Modulation recognition of non-cooperation underwater acoustic communication signals using principal component analysis

Abstract The modulation classification of the non-cooperation underwater acoustic (UWA) communication signals is extremely challenging due to the adverse UWA channel transmission characteristics and low signal to noise ratio (SNR), which lead to considerable impairments of the signal features. In this paper, the principal component analysis (PCA) is proposed for efficient extraction of the power spectra and square spectrum features of UWA signals at the presence of multipath, Doppler, and noise induced in UWA channels. The employment of PCA enables extraction of the principal components associated with different modulation mode as the input vector of classier, thus reducing the feature dimension and suppressing the influence of UWA channels and environmental noise. With the features obtained by PCA, an artificial neural network (ANN) classifier is adopted for modulation recognition of UWA communication signals. The experimental modulation classification results obtained with field signals in 4 different underwater acoustic channels show that the proposed PCA based modulation recognition method outperforms the classifier using classic features in terms of classification performance and noise tolerance.

[1]  Milica Stojanovic,et al.  Efficient processing of acoustic signals for high-rate information transmission over sparse underwater channels , 2008, Phys. Commun..

[2]  S. K. Tso,et al.  Impact-acoustics-based health monitoring of tile-wall bonding integrity using principal component analysis , 2006 .

[3]  Nandi K. Nandi,et al.  Automatic analogue modulation recognition , 1995, Signal Process..

[4]  Cao Zhigang,et al.  Automatic recognition for common used modulations in satellite communication , 2004 .

[5]  Gui Yun Tian,et al.  A FEATURE EXTRACTION TECHNIQUE BASED ON PRINCIPAL COMPONENT ANALYSIS FOR PULSED EDDY CURRENT NDT , 2003 .

[6]  Milica Stojanovic,et al.  Underwater Acoustic Communications and Networking: Recent Advances and Future Challenges , 2008 .

[7]  G. R. Wilson,et al.  Nonlinear and non-Gaussian ocean noise , 1986 .

[8]  Elsayed Elsayed Azzouz,et al.  Algorithms for automatic modulation recognition of communication signals , 1998, IEEE Trans. Commun..

[9]  Rafael A. Calvo,et al.  Fast Dimensionality Reduction and Simple PCA , 1998, Intell. Data Anal..

[10]  Feng Tong,et al.  Exploiting joint sparsity for underwater acoustic MIMO communications , 2017 .

[11]  William A. Gardner,et al.  Spectral Correlation of Modulated Signals: Part II - Digital Modulation , 1987, IEEE Transactions on Communications.

[12]  Chisheng Li,et al.  An Efficient and Simple Method of MPSK Modulation Classification , 2008, 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing.

[13]  Brian M. Sadler,et al.  Hierarchical digital modulation classification using cumulants , 2000, IEEE Trans. Commun..

[14]  Y. Chan,et al.  Identification of the modulation type of a signal , 1989 .

[15]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[16]  José Manoel de Seixas,et al.  Principal component analysis for classifying passive sonar signals , 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

[17]  Yang Xiang,et al.  Detection and classification of flaws in concrete structure using bispectra and neural networks , 2002 .

[18]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[19]  Mikael Johnson.  Waveform based clustering and classification of AE transients in composite laminates using principal component analysis , 2002 .

[20]  Ali Azadeh,et al.  Forecasting electrical consumption by integration of Neural Network, time series and ANOVA , 2007, Appl. Math. Comput..

[21]  R. Webster.  Ambient noise statistics , 1993, IEEE Trans. Signal Process..