基于SCHKS-SSVM的通信信号调制方式识别研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
随着通信体制及信号调制样式的多样化和复杂化,无线通信环境越来越复杂,通信信号在时域、频域、空域上交织重叠,使信号调制样式的识别难度越来越大,这也使通信信号的调制方式识别研究成为军、民领域极为关注的课题。本文在借鉴已有知识基础上,提出了基于变形光滑支持向量机通信信号调制方式识别的新方法,对混合通信信号中各类别信号的调制方式进行了识别研究和仿真分析。
     首先分析了7种常用数字信号的调制原理,对目前常用的特征提取和载波频率估计方法进行了研究,提取6类特征作为分类器识别的特征向量。然后针对接收信号多为混叠信号、先验知识少、分离困难等特点,引入独立分量分析的方法,从若干独立信源混合后的观察信号中分解出各个独立的信号。最后,对支持向量机的相关理论进行了研究。针对传统支持向量机二次规划问题的目标函数具有二阶不光滑、不可微的特点,提出了一类变形光滑支持向量机模型(SCHKS-SSVM),采用CHKS函数作为光滑函数,并用Newton-Armijo算法来训练该模型,通过批处理训练提高训练速度,节省了大量存储空间。实验仿真表明,该方法可以有效求解高维、大规模的分类问题。
With the diversification and the complication of communication system and signal modulation pattern, the wireless communication environment is more and more complicated, the communication signals overlap in the time domain、the frequency domain and the airspace, it makes signal recognition more difficult and makes the research of the communication signals modulation identification become attention topic in civil and military field. Referencing to the existing knowledge, this paper puts forward a new identification method based on the deformation smooth support vector machine. Simulation proves that this method can recognize the modulation mode of hybrid communication signals.
     First, this paper analyses the modulation principle of seven common digital signals. Given the study of the usual feature extraction and the carrier frequency estimation, choose six characteristics to be recognition characteristic vector. And then, according to the receive signal for aliasing signal、prior knowledge less、separation difficult and so on, introducing to independent component analysis method. It separates the independent composition from the observed signals which are mixed by several independent sources. Finally, researchs the theory about the support vector machine (SVM). The second order objective function of traditional support vector machine quadratic programming problem is not smooth、not micro. So it introduces a smooth deformation support vector machine (SCHKS-SSVM) mode, which uses CHKS function as smooth function. The model is trained by Newton-Armijo algorithm. Beacause it can improves the training speed through the batch train, meanwhile saving a lot of storage space. Experiments show that the proposed method can effectively solve high-dimension、large-scale classification problem.
引文
[1]Polydorosand K.Kim.On the detection and celassifieation of quadrature digital modulations in broad-band noise.IEEE Trans. Conmun,1990,38(8):1199-1211
    [2]C.Y.Huang and A.Polydoros.Likelihood method for MPSK modulation classification. IEEE Trans.Commun,1995,43(3):1493-1504
    [3]C.Schreyogg and J.Reiehert.Modulation Classification of QAM sehemes using the DFT of phase histogram conlblned with modulus information.Proeeedings of IEEE MILCOM,Monterey,CA,1997.1372-1376
    [4]Sills J A.Maximum-likelihood modulation classification for PSK/QAM.Proeeedings of IEEE MILCOM,Atlalltle City,NJ,1999
    [5]Alltti-Veikko Rosti and Visa Koivunen.Classifieation Of MASK Modulated Signals Using The Mean Of Complex Envelope.Proeeedings of EUSIPCO-2000,2000.581-584
    [6]G.Han,J.D.Li,and D.H.Lu.Study of modulation recognition based on HOCs and SVM.IEEE Vehicular Technology Conference,2004,2:898-902
    [7]张炜.数字通信信号调制方式自动识别研究[D].国防科学技术大学博士学位论文.2006:28-46页
    [8]边肇棋,张学工.模式识别[M].北京:清华大学出版社.2000.1
    [9]A.K.Jain,Robert P.W.Dubin,J.C.Mao, " Statistical Pattern Reeognition:A Review",IEEE Trans.PAMI,Vol.22,No.1,PP.4-37,Jan,2000
    [10]F.F.Liedtke.Computer Simulation of an Automatic Classification Procedure for Digital Modulated Communication Signals with Unknown Parameters.Signal Processing.August 1984,6(4):311-323
    [11]Swami A,Sadler B M.Hierarehieal digital modulation classifieation using cumulants,IEEE Trans on communication,Vol.48,No3,Mar 2000 pp.416-429
    [12]陈卫东,杨绍全.利用累量不变量对MPSK信号分类[J].西安电子科技大学学报.2002.29(2):229-232页
    [13]吕新政,魏平.利用高阶累积量实现数字调制信号的自动识别[J].电子对抗技术.2004.19(6):154-159页
    [14]吕铁军,魏平,肖先赐.基于分形和测度理论的信号调制识别[J].电波科学学报.2001.1.16(1):123-127页
    [15]吕铁军,郭双冰,肖先赐.调制信号的分形特征研究[J].中国科学E辑2001.631(6):508-513页
    [16]M.L.D.WOng,A.K Nandi.Automatic digital modulation recognition using speetral and statistieal featLlres with multi-layer Perceptrons. Signal Proeessing and its Applieations,Sixth Intemational,Sympositun,2001,2:390-393
    [17]Wei Dai,Wbuzheng Wang, "Joint Power Estimation and Modulation Classification Using Seeond-and Higher Statistics",Wireless Communications and networking Conference,2002,IEEE,Vol.1 pp.155-158.
    [18]陈怀新,南建设,肖先赐.基于统计特征主分量的信号调制识别[J].电子科技大学学报.2004.33(3):231-238页
    [19]高永强.基于高阶累积量的数字调制方式识别[D]西安电子科技大学硕士学位论文.2006:19-31页
    [20]贺涛.数字通信信号调制识别若干新问题研[D].电子科技大学博士学位论文.2007:63-72页
    [21]吕幼新.通信信号自动调制识别研究[D].电子科技大学硕士学位论文.2007:10-17页,81-84页
    [22]邓名桂.数字通信信号调制类型识别研究[D].清华大学硕士学位论文.2007:50-57页
    [23]陆明泉.多信号的调制识别技术研究[D].电子科技大学博士学位论文.2008:107-112页
    [24]杨琳.数字通信信号调制方式自动识别技术研究[D].中国科学技术大学博士学位论文.2008:74-81页
    [25]张帆.基于DSP的通信信号调制方式识别[D].西安电子科技大学硕士学位论文.2009:15-16页,33-35页
    [26]曹家亮.数字调制信号识别研究[D].哈尔滨工程大学硕士学位论文.2009:26-35页
    [27]王永娟.基于高阶累积量的OFDM信号调制识别技术研究[D].西安电子科技大学硕士学位论文.2009:22-30页
    [28]Cortes C,Vapnik V.N.Support vector networks[J].Machine Learning,1995,20:144-152
    [29]E.Osuna,R.Freund and F.Girosi.Training support vector machines:An application to face detection.Proc.IEEE.Conf.Computer Vision and Pattern Recognition,1997:130-136.
    [30]E.Osuna,R.Freund and F.Girosi.An improved training algorithm for support vector machines.Proceedings of the 1997 IEEE Workshop on Neural Networks for Signal Processing.NewYork:IEEE Press,1997:276-285.
    [31]Platt J C. Fast training of SVMs using sequential minimal optimization. In:Scholkopf B,Burges C J C,Smola A J ed. Advances in Kernel Method-Support Vector Learnin.Cambridge,MA:MIT Press,1998:185-208.
    [32]Keerthi S S.et al.Improvements to Platt s SMO Algorithm for SVM Classier Design,Technical report,National University of Singapore,1999
    [33]Y.J.Lee.O.L.Mangasarian.SSVM:A smooth support vector machine. Computational Optimization and Applications.2001.20(1):5-22.
    [34]袁玉波,严杰,徐成贤.多项式光滑的支撑向量机[J].计算机学报2005.28(1):223-342.
    [35]熊金志,胡金莲,袁华强等.一类光滑支持向量机新函数的研究[J].电子学报.2007.35(2):366-370页
    [36]吴丹.通信信号调制方式分类识别算法研究[D].哈尔滨工业大学博士学位论文.2007:84-102页
    [37]孙刚.基于支持向量机的多分类方法研究[D].大连海事大学硕士学位论文.2008:24-27页,36-40页
    [38]张小路.V-支持向量机中参数选取的两种模型[D].大连理工大学硕士学位论文.2008:31-38页
    [39]Q.Wu,S.Y.Liu and L.Y.Zhang.Adjustable entropy function method for support vector machines.Journal of Systems Engineering and Electronics.2008.19(5):1029-1034.
    [40]王海洋.基于SVM的分段贪婪算法研究[D].西安科技大学硕士学位论文.2009:39-41页
    [41]王秉钧,冯玉珉,田宝玉.通信原理[M].北京:清华大学出版社.2006.11:220-299页
    [42]郭黎利,张晓林,周凯.通信原理[M].哈尔滨:哈尔滨工程大学出版社.2005.7
    [43]宋祖顺,宋晓勤,宋平.现代通信原理.第三版.[M].北京:电子工业出版社.2009:199-236页
    [44]陈明.通信与信息工程中的随机过程[M].南京:东南大学出版社.2001.8
    [45]张雯,程家兴.利用Hilbert变换提取信号瞬时特征参数的问题研究[J].电讯技术.2003.4:44-48页
    [46]刘慧婷,程家兴.利用Hilbert变换提取信号瞬时特征的算法实现[J].微机发展.2003.13(6):82-85页
    [47]程家兴,樊甫华等.利用Hilbert变换提取信号瞬时特征参数的问题研究[J].电讯技术.2003.4:44-48页
    [48]刘娟.数字通信信号自动调制识别算法研究[D].重庆大学硕士学位论文.2009:29-31页
    [49]卢娜.调制模式识别和信号特征提取的研究[D].西安电子科技大学硕士学位论文.2008:39-43页
    [50]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社.2006:11-24页,99-100页
    [51]A.Hyvarinen,E.Oja.Independent component analysis:algorithms and app 1ICA tions.Neural Networks,2000,13:411-430
    [52]张发启,张斌,张喜斌.盲信号处理及应用[M].西安:西安电子科技大学出版社.2006:36-39页
    [53]谢亮.基于独立分量分析特征提取方法的研究及其应用[D].浙江师范大学硕士学位论文.2009:19-21页
    [54]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社.2004:193-196页,274-341页
    [55]Vapnik V N著.张学工译.统计学习理论的本质[M].北京:清华大学出版社.2000.9
    [56]温熙森.模式识别与状态监控[M].北京:科学出版社.2007:315-340页
    [57]迟晓妮.二次锥规划的算法研究[D].西安电子科技大学博士学位论文.2008:52-54页
    [58]吴青.基于优化理论的支持向量机学习算法研究[D].西安电子科技大学博士学位论文.2009:45-46页
    [59]张贤达.矩阵分析与应用[M].北京:清华大学出版社.2004:320-331页
    [60]王琳琳.基于支持矢量机的调制方式识别研究[D].国防科学技术大学硕士学位论文.2009:45-47页

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700