A Specific Combination Scheme for Communication Modulation Recognition Based on the Bees Algorithm and Neural Network

For the modulation recognition of the wireless communication signal, when extracting Eigenvalues, it is necessary to improve modulation recognition rate in order to achieve the optimized effect. In this article, combination eigenvalue module of the signal is extracted by applying bee colony algorithm and automatic recognition of the communication signal is achieved through the classifier which has multi-layer sensor neural network. The simulation results show that the proposed algorithm in this paper can result the communication signal modulation recognition rate is higher than the corresponding rate in using the conventional method under the conditions that the number of neurons is only 20 in the hidden layers, and the system is easy to realize, it has wide application prospect in signal recognition. Keywords-wireless communication signal; bee colony algorithm; combination eigenvalue module; multi-layer perceptron neural network; modulation recognition

[1]  Zhang Zhongzhao.  MLP neural network based adaptive UWB modulation scheme recognition algorithm , 2008 .

[2]  Li Yan-bin.  Modulation Recognition Based on Joint Characteristics in Spectrum Domain , 2010 .

[3]  Wang Xiang.  Overview of research on bee colony algorithms , 2011 .

[4]  Yang Faquan,et al.  Method of Modulation Recognition of Mixed Modulation Signal , 2014 .

[5]  Cosmin Cernazanu-Glavan,et al.  A Model for Determining the Number of Negative Examples used in Training a MLP , 2009, SCSS.

[6]  Zan Li,et al.  A New Method of Modulation Recognition of Block Orthogonal Amplitude Modulation , 2014, J. Commun..

[7]  Chen Yin.  Digital modulation recognition method based on BP neural network , 2012 .

[8]  Guo Hui.  Digital modulation recognition algorithm based on support vector machine , 2011 .

[9]  Yailé Caballero Mota,et al.  Improving the MLP Learning by Using a Method to Calculate the Initial Weights of the Network Based on the Quality of Similarity Measure , 2011, MICAI.

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

[11]  Zan Li,et al.  Method of neural network modulation recognition based on clustering and Polak-Ribiere algorithm , 2014 .

[12]  Ataollah Ebrahimzadeh,et al.  Blind signal-type classification using a novel robust feature subset selection method and neural network classifier , 2010, Ann. des Télécommunications.

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

[14]  Wang Yu.  Recognition of OFDM Signals Based on Cyclic Autocorrelation , 2012 .

[15]  Engelbert Mephu Nguifo,et al.  M-CLANN: Multiclass Concept Lattice-Based Artificial Neural Network , 2009, Constructive Neural Networks.

[16]  Ai Lingme.  Tire tread pattern recognition based on composite feature extraction and hierarchical support vector machine , 2013 .