基于softmax回归的通信信号循环谱的多分类识别方法Softmax regression based multi-classification recognition method of communication signal cyclic spectrum
刘亚冲,唐智灵
摘要(Abstract):
通信信号调制方式的自动识别在通信对抗领域中具有重要作用,同时也是未来认知无线电系统的重要组成部分,如何在日趋密集的信号环境中快速准确地识别多个混合通信信号是实现通信信号调制方式自动识别的重点。针对这种情况,以数字通信信号的循环谱为特征,通过构建softmax回归多分类识别器,提出一种基于softmax回归的通信信号循环谱的多分类识别方法。通过计算机验证不同条件下的算法性能,证明了该方法无需知道典型的数字调制信号(如ASK,BPSK,QPSK,16QAM,64QAM)的符号率、载频以及同步定时等先验信息,对它们组成的混合信号可以正确识别其中包含的每个调制信号的调制方式,并且识别速度较快。
关键词(KeyWords): softmax;多分类识别;循环谱;调制方式识别;神经网络;电子对抗
基金项目(Foundation): 国家自然科学基金(61461013);; 广西自动检测技术与仪器重点实验室主任基金(YQ15115);; 桂林电子科技大学创新团队“广西无线宽带通信与信号处理重点实验室”2016年主任基金项目(GXKL06160103)~~
作者(Author): 刘亚冲,唐智灵
DOI: 10.16652/j.issn.1004-373x.2018.03.001
参考文献(References):
- [1]XU J L,SU W,ZHOU M.Likelihood-ratio approaches to automatic modulation classification[J].IEEE transactions on systems,man,and cybernetics:part C:applications and reviews,2011,41(4):455-469.
- [2]DOBRE O A,INKOL R.Blind signal identification:achievements,trends,and challenges[C]//Proceedings of 2012 International Conference on Communications.Bucharest:IEEE,2012:349-352.
- [3]梁晓芳.基于邻域粗糙集快速属性约简神经网络的调制信号识别研究[D].太原:太原理工大学,2012.LIANG Xiaofang.The research of modulation recognition based on efficient attribute reduction with neighborhood rough set and neural network[D].Taiyuan:Taiyuan University of Technology,2012.
- [4]赵文华.基于小波变换的数字调制信号识别研究[D].西安:西安电子科技大学,2011.ZHAO Wenhua.Research on digital modulation recognition based on wavelet transform[D].Xi’an:Xidian University,2011.
- [5]FENG Hongmei,HOU Yanfang.Study of modulation recognition algorithm based on wavelet transform and neural network[J].Journal of computers,2011,6(7):1511-1518.
- [6]刘聪杰,彭华,吴迪,等.突发自适应调制信号的调制识别算法研究[J].信号处理,2012,28(3):417-424.LIU Congjie,PENG Hua,WU Di,et al.Modulation recognition algorithm of burst adaptive modulation signal[J].Signal processing,2012,28(3):417-424.
- [7]URRIZA P,REBEIZ E,CABRIC D.Optimal descriminant functions based on sampled distribution distance for modulation classification[J].IEEE communications letters,2013,17(10):1885-1888.
- [8]BAHLOUL M R,YUSOFF M Z,SAAD M N M.Efficient and low complexity modulation classification algorithm for MIMO systems[J].Research journal of applied sciences,engineering and technology,2015,9(1):58-64.
- [9]AZAMI H,AZARBAD M,SANEI S.Classification of digital communication signals based on adaptive neuro-fuzzy inference system[C]//Proceedings of 2013 the 21st Iranian Conference on Electrical Engineering.Mashhad:IEEE,2013:1-6.
- [10]余志斌,于宁宇.基于循环谱包络的多信号调制识别[J].计算机应用,2012,32(8):2119-2122.YU Zhibin,YU Ningyu.Modulation recognition for multi-component PSK signals based on cyclic spectrum amplitude[J].Journal of computer applications,2012,32(8):2119-2122.
- [11]程汉文,朱雷,吴乐南.基于累计量的干扰信号调制识别算法[J].电子与信息学报,2009,31(7):1741-1745.CHENG Hanwen,ZHU Lei,WU Lenan.Modulation classification algorithm for jamming signal based on cumulant[J].Journal of electronics&information technology,2009,31(7):1741-1745.
- [12]赵宇峰,曹玉健,纪勇,等.基于循环频率特征的单信道混合通信信号的调制识别[J].电子与信息学报,2014,36(5):1202-1208.ZHAO Yufeng,CAO Yujian,JI Yong,et al.Modulation identification for single-channel mixed communication signals based on cyclic frequency features[J].Journal of electronics&information technology,2014,36(5):1202-1208.
- [13]李世平,陈方超,王隆,等.多径信道下基于循环谱特征的调制识别算法[J].计算机应用,2012,32(8):2123-2127.LI Shiping,CHEN Fangchao,WANG Long,et al.Modulation identification algorithm based on cyclic spectrum characteristics in multipath channel[J].Journal of computer applications,2012,32(8):2123-2127.
- [14]兰铂.FSK和PSK信号特征研究[D].北京:北京邮电大学,2011.LAN Bo.Study on features of FSK signal and PSK signal[D].Beijing:Beijing University of Posts and Telecommunications,2011.