Modulation Classification Using Compressed Sensing and Decision Tree–Support Vector Machine in Cognitive Radio System

In this paper, a blind modulation classification method based on compressed sensing using a high-order cumulant and cyclic spectrum combined with the decision tree–support vector machine classifier is proposed to solve the problem of low identification accuracy under single-feature parameters and reduce the performance requirements of the sampling system. Through calculating the fourth-order, eighth-order cumulant and cyclic spectrum feature parameters by breaking through the traditional Nyquist sampling law in the compressed sensing framework, six different cognitive radio signals are effectively classified. Moreover, the influences of symbol length and compression ratio on the classification accuracy are simulated and the classification performance is improved, which achieves the purpose of identifying more signals when fewer feature parameters are used. The results indicate that accurate and effective modulation classification can be achieved, which provides the theoretical basis and technical accumulation for the field of optical-fiber signal detection.

[1]  Xiaoqian Chen,et al.  Performance Analysis and Optimization of Novel High-Order Statistic Features in Modulation Classification , 2008, 2008 4th International Conference on Wireless Communications, Networking and Mobile Computing.

[2]  Qing Guo,et al.  A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals , 2017, MLICOM.

[3]  K. Ohe,et al.  Establishing a Classification System for High Fall-Risk Among Inpatients Using Support Vector Machines , 2017, Computers, informatics, nursing : CIN.

[4]  Biing-Hwang Juang,et al.  Signal Processing in Cognitive Radio , 2009, Proceedings of the IEEE.

[5]  Sun,et al.  The modulation recognition based on decision-making mechanism and neural network integrated classifier , 2013 .

[6]  Brian M. Sadler,et al.  A Survey of Dynamic Spectrum Access , 2007, IEEE Signal Processing Magazine.

[7]  Emmanuel J. Candès,et al.  Decoding by linear programming , 2005, IEEE Transactions on Information Theory.

[8]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[9]  Weifeng Zhang.  Automatic modulation classification based on statistical features and Support Vector Machine , 2014, 2014 XXXIth URSI General Assembly and Scientific Symposium (URSI GASS).

[10]  Sangarapillai Lambotharan,et al.  Spatio-Temporal Spectrum Sensing in Cognitive Radio Networks Using Beamformer-Aided SVM Algorithms , 2018, IEEE Access.

[11]  R.G. Baraniuk,et al.  Compressive Sensing [Lecture Notes] , 2007, IEEE Signal Processing Magazine.

[12]  Takeo Fujii,et al.  A modulation classification method in cognitive radios system using stacked denoising sparse autoencoder , 2017, 2017 IEEE Radio and Wireless Symposium (RWS).

[13]  Linda Doyle,et al.  Cyclostationary Signatures in Practical Cognitive Radio Applications , 2008, IEEE Journal on Selected Areas in Communications.

[14]  Wenbo Wang,et al.  Modulation Classification of Linear Digital Signals Based on Compressive Sensing Using High-Order Moments , 2014, 2014 European Modelling Symposium.

[15]  Jiadong Xu,et al.  A Novel Modulation Classification Method Based on High Order Cumulants , 2006, 2006 International Conference on Wireless Communications, Networking and Mobile Computing.

[16]  Massimo Fornasier,et al.  Compressive Sensing , 2015, Handbook of Mathematical Methods in Imaging.

[17]  S. Kirolos,et al.  Analog-to-Information Conversion via Random Demodulation , 2006, 2006 IEEE Dallas/CAS Workshop on Design, Applications, Integration and Software.

[18]  Brian M. Sadler,et al.  Cyclic Feature Detection With Sub-Nyquist Sampling for Wideband Spectrum Sensing , 2012, IEEE Journal of Selected Topics in Signal Processing.

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

[20]  Jian Liu,et al.  A novel modulation classification algorithm based on daubechies5 wavelet and fractional fourier transform in cognitive radio , 2012, 2012 IEEE 14th International Conference on Communication Technology.

[21]  Anant Sahai,et al.  SNR Walls for Signal Detection , 2008, IEEE Journal of Selected Topics in Signal Processing.

[22]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[23]  Liye,et al.  Cooperative Spectrum Sensing in Cognitive Radio, Part I , 2007 .

[24]  Jing Xiao,et al.  A novel modulation classification for PSK and QAM signals in wireless communication , 2011 .

[25]  Jun-Geol Baek,et al.  A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network , 2018, Applied Sciences.

[26]  Sang-Jo Yoo,et al.  A Strong Machine Learning Classifier and Decision Stumps Based Hybrid AdaBoost Classification Algorithm for Cognitive Radios † , 2019, Sensors.

[27]  Ning Liu,et al.  Investigation on Signal Modulation Recognition in the Low SNR , 2010, 2010 International Conference on Measuring Technology and Mechatronics Automation.

[28]  Hao Hu.  Cyclostationary Approach to Signal Detection and Classification in Cognitive Radio Systems , 2009 .

[29]  Yaakov Tsaig,et al.  Extensions of compressed sensing , 2006, Signal Process..

[30]  Xianfeng Tang,et al.  High order modulation format identification based on compressed sensing in optical fiber communication system , 2016 .