Automatic Recognition of Digital Communication Signal

Automatic recognition of digital communication signals has seen increasing demands nowadays in various applications. This paper investigates the design of high efficient system for classification of the digital communication signals. The system includes two main modules: feature extraction and classification. In the feature extraction module we have used a novel balanced combination of the higher order moments (up to eighth), higher order cumulants (up to eighth) and spectral characteristics. In the classifier we have investigated the performances of the radial basis function (RBF) neural network, probability neural network (PNN) and multilayer perceptron (MLP) neural network. Then we have compared these systems. Experimental results show the proposed systems have high percentage of correct classification to discriminate the different types of digital signals even at very low SNRs.

[1]  Aisheng Liu,et al.  Automatic modulation classification based on the combination of clustering and neural network , 2011 .

[2]  Gu Xuemai,et al.  Automatic digital modulation recognition using artificial neural networks , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[3]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[4]  Ataollah Ebrahimzade Sherme.  A novel method for automatic modulation recognition , 2012, Appl. Soft Comput..

[5]  Donal O'Mahony,et al.  Modulation scheme classification for 4G software radio wireless networks , 2002 .

[6]  Sergio Rapuano,et al.  Validating a method for classifying digitally modulated signals , 2009 .

[7]  Engin Avci,et al.  An expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System for digital modulation recognition , 2007, Expert Syst. Appl..

[8]  Xin Zhou,et al.  Application of kernel methods in signals modulation classification , 2011 .

[9]  MengChu Zhou,et al.  Real-time Modulation Classification Based On Maximum Likelihood , 2008, IEEE Communications Letters.

[10]  Juan Liu,et al.  Digital modulation recognition based on instantaneous information , 2010 .

[11]  Hans G. C. Tråvén,et al.  A neural network approach to statistical pattern classification by 'semiparametric' estimation of probability density functions , 1991, IEEE Trans. Neural Networks.

[12]  Asoke K. Nandi,et al.  Automatic digital modulation recognition using artificial neural network and genetic algorithm , 2004, Signal Process..

[13]  A. Ebrahimzadeh,et al.  Digital communication signals identification using an efficient recognizer , 2011 .

[14]  Milad Azarbad,et al.  Comparison of Clustering Algorithms for Recognition of Radio Communication Signals based on the HOS , 2011 .

[15]  Marion Berbineau,et al.  Automatic modulation recognition using wavelet transform and neural network , 2009 .

[16]  T. Rao,et al.  Tensor Methods in Statistics , 1989 .

[17]  Jerry M. Mendel,et al.  Maximum-likelihood classification for digital amplitude-phase modulations , 2000, IEEE Trans. Commun..

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[19]  Saleem A. Kassam,et al.  Radial basis function networks in nonlinear signal processing applications , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[20]  John G. Proakis,et al.  Digital Communications , 1983 .

[21]  Bijan G. Mobasseri,et al.  Digital modulation classification using constellation shape , 2000, Signal Process..