基于CCGA优化的ANN信号调制模式识别
|
摘要
信号调制模式识别是非合作通信中重要的研究内容,是民用无线电管理部门进行频谱管理和军用电子对抗的必备技术。软件无线电和认知无线电概念的提出和微电子技术的发展,使多体制通信系统能够在同一接收机中实现成为可能,对信号的调制模式识别提出了新要求。本文是在前人研究的基础上,将CCGA优化的神经网络应用到基于统计模式信号调制识别。
第一,阐述信号调制模式识别的两种途径,即决策理论和统计模式。瞬时参数的提取是统计模式识别的基础,针对解析信号法提取瞬时参数的不足与限制条件,给出希尔伯特—黄变换(Hilbert-Haung Transform,HHT)提取瞬时参数的方法。试验仿真结果表明,HHT方法能克服部分噪声的影响。
第二,依据提取出的特征参数作为特征向量,研究人工神经元网络(Artificial Neural Network,ANN)单信号调制模式识别问题。在简要介绍ANN基本原理和用于模式识别的方法与特点的基础上,把BP神经网络引入到信号调制模式识别。针对BP算法收敛慢,易陷入局部极小点等缺陷,引入遗传算法(genetic algorithm,GA)优化神经网络,提高全局搜索能力。试验仿真结果表明,本文运用GA优化神经网络的结构和权值,网络分类时间比BP网络缩短约60%,比L-M网络缩短近40%,识别率也有提升。由于GA过分强调“生存竞争”,忽略了个体之间的合作关系,文中接着研究CCGA优化神经网络的实现方案。针对CCGA的特点,文中详细论述子种群分割、代表个体选择、子个体编码方案、子个体交叉和变异的方法。试验仿真结果表明,相同条件下,CCGA比GA优化的神经网络在识别率提高的同时,运行时间缩短40%。
第三,针对多信号调制模式识别问题,依据处理多信号的接收数据模型,对多信号进行分离识别。因受噪声和滤波器性能的影响,对分离后的单信号计算时域特征参数,用CCGA优化后的神经网络判定其调制模式,识别率较低。采用AR模型提取信号的短时平均中心频率和短时平均带宽,并用直方图压缩其维数后作为待识别信号的特征向量,判定其调制类型,识别率可提高约12%。
Signal modulation pattern recognition is very important of non-cooperative communication and it is the essential technology of the administrative department of civil radio spectrum management and military electronic countermeasures. The concept of software radio and cognitive radio was put forward, and with the development of microelectronics technology, which makes the multi-institutional communication system in the same receiver as possible, that put new requirements on the modulation of the signal pattern recognition. This thesis is on the basis of previous research to use the neural network optimized by CCGA(cooperative co-evolutionary genetic algor-ithms)to comply the signal modulation pattern recognition based on statistical model.
Firstly, the two ways of the signal modulation pattern recognition based on decision theory and statistical modeling are described in the thesis. The parameters extracted of instantaneous are the basis of statistical pattern recognition, but the instantaneous parameters extracted is lack and with restrictions by analytic signal method, so the HHT(Hilbert-Haung Transform) method is used to extract the instantaneous parameters. The results of simulation show that the HHT method can overcome some of noises.
Secondly, the parameters extracted as the feature vector to recognize the single signal modulation pattern using ANN(Artificial Neural Network) is described in the thesis. The basic principles and pattern recognition methods of ANN is analyzed briefly, then the BP neural network is applied to the signal modulation pattern recognition. Against slower convergence and easy to fall into local minimum point of BP neural network, the genetic algorithm (GA) is used to optimize the neural network structure and connection weights. The results of experimental show that the neural network optimized by GA can effectively improve the network performance, the classification time shortened by about60%than BP network and nearly40%shorter than the LM network with the recognition rate raised. GA emphasis on competition of survival too much, and ignore the cooperative relationship between the individual. The neural network optimized by CCGA is focused. The sub-population division, sub-individual choice, sub-individual encoding, sub-individual crossover and mutation are discussed detail in the thesis. The results simulated show that, with the same conditions, the neural network optimized by CCGA is significantly better than neural network optimized by GA, and its running time shortened by40%with recognition rate raised.
Finally, the ANN optimized by CCGA is used for multi-signal modulation pattern recognition. Separation of multi-signal on the receiving model is to determine the signal separated modulation pattern. With the noise and filter performance, the time-domain characteristic parameters of the signal separated are used to determine the modulation model, the recognition rate is lower. In order to improve recognition performance, the short-term average center frequency and short-term average bandwidth are extracted by AR(AutoRegressive) model and the dimension is compressed by histogram as the feature vector to fix the modulation pattern, the recognition rate raised about12%.
第一,阐述信号调制模式识别的两种途径,即决策理论和统计模式。瞬时参数的提取是统计模式识别的基础,针对解析信号法提取瞬时参数的不足与限制条件,给出希尔伯特—黄变换(Hilbert-Haung Transform,HHT)提取瞬时参数的方法。试验仿真结果表明,HHT方法能克服部分噪声的影响。
第二,依据提取出的特征参数作为特征向量,研究人工神经元网络(Artificial Neural Network,ANN)单信号调制模式识别问题。在简要介绍ANN基本原理和用于模式识别的方法与特点的基础上,把BP神经网络引入到信号调制模式识别。针对BP算法收敛慢,易陷入局部极小点等缺陷,引入遗传算法(genetic algorithm,GA)优化神经网络,提高全局搜索能力。试验仿真结果表明,本文运用GA优化神经网络的结构和权值,网络分类时间比BP网络缩短约60%,比L-M网络缩短近40%,识别率也有提升。由于GA过分强调“生存竞争”,忽略了个体之间的合作关系,文中接着研究CCGA优化神经网络的实现方案。针对CCGA的特点,文中详细论述子种群分割、代表个体选择、子个体编码方案、子个体交叉和变异的方法。试验仿真结果表明,相同条件下,CCGA比GA优化的神经网络在识别率提高的同时,运行时间缩短40%。
第三,针对多信号调制模式识别问题,依据处理多信号的接收数据模型,对多信号进行分离识别。因受噪声和滤波器性能的影响,对分离后的单信号计算时域特征参数,用CCGA优化后的神经网络判定其调制模式,识别率较低。采用AR模型提取信号的短时平均中心频率和短时平均带宽,并用直方图压缩其维数后作为待识别信号的特征向量,判定其调制类型,识别率可提高约12%。
Signal modulation pattern recognition is very important of non-cooperative communication and it is the essential technology of the administrative department of civil radio spectrum management and military electronic countermeasures. The concept of software radio and cognitive radio was put forward, and with the development of microelectronics technology, which makes the multi-institutional communication system in the same receiver as possible, that put new requirements on the modulation of the signal pattern recognition. This thesis is on the basis of previous research to use the neural network optimized by CCGA(cooperative co-evolutionary genetic algor-ithms)to comply the signal modulation pattern recognition based on statistical model.
Firstly, the two ways of the signal modulation pattern recognition based on decision theory and statistical modeling are described in the thesis. The parameters extracted of instantaneous are the basis of statistical pattern recognition, but the instantaneous parameters extracted is lack and with restrictions by analytic signal method, so the HHT(Hilbert-Haung Transform) method is used to extract the instantaneous parameters. The results of simulation show that the HHT method can overcome some of noises.
Secondly, the parameters extracted as the feature vector to recognize the single signal modulation pattern using ANN(Artificial Neural Network) is described in the thesis. The basic principles and pattern recognition methods of ANN is analyzed briefly, then the BP neural network is applied to the signal modulation pattern recognition. Against slower convergence and easy to fall into local minimum point of BP neural network, the genetic algorithm (GA) is used to optimize the neural network structure and connection weights. The results of experimental show that the neural network optimized by GA can effectively improve the network performance, the classification time shortened by about60%than BP network and nearly40%shorter than the LM network with the recognition rate raised. GA emphasis on competition of survival too much, and ignore the cooperative relationship between the individual. The neural network optimized by CCGA is focused. The sub-population division, sub-individual choice, sub-individual encoding, sub-individual crossover and mutation are discussed detail in the thesis. The results simulated show that, with the same conditions, the neural network optimized by CCGA is significantly better than neural network optimized by GA, and its running time shortened by40%with recognition rate raised.
Finally, the ANN optimized by CCGA is used for multi-signal modulation pattern recognition. Separation of multi-signal on the receiving model is to determine the signal separated modulation pattern. With the noise and filter performance, the time-domain characteristic parameters of the signal separated are used to determine the modulation model, the recognition rate is lower. In order to improve recognition performance, the short-term average center frequency and short-term average bandwidth are extracted by AR(AutoRegressive) model and the dimension is compressed by histogram as the feature vector to fix the modulation pattern, the recognition rate raised about12%.
引文
[1]Weaver, C.S.; Cole, C.A.; Krumland, R.B.; Miller, M.L., "The automatic classification of modulation types by pattern recognition"[R], AD691069, April,1969
[2]P A. J. Nagy. A Modulation Classifier for Muti Channel Systems and Multi Transmitter Sitiations. Proc. IEEE MILCOM,1994,816-820
[3]刘澍.基于改进蚁群算法与神经网络的调制识别研究[D].武汉：华中科技大学,2009
[4]贺涛.数字通信信号调制识别若干新问题研究[D].成都：电子科技大学,2009
[5]Liedtle F F. "Computer simulation of an automatic classification procedure for digitally modulated communication signals with unknown parameters"[J]. Signal Processing 1984,6(4):311-323
[6]J. G. Proakis, M. Salehi. Fundamentals of Communication Systems, Prentice-Hall,2004
[7]E. E. Azzouz, A. K. Nandi. Automatic Modulation Recognition of Communication Signals. Kluwer Academic,1996
[8]Antti-Veikko Rosti "Statistic Methods in Modulation Classification" Master of Science Thesis,Tampere University of Technology Department of Information Technology,1998.
[9]赵知劲等.基于Hilbert-Huang的信号瞬时参数提取[J].信号处理,2005,Vol.21.No.4A
[10]王艳聪,胡中豫,张云飞.基于谱相关特性和组合神经网络的数字调制信号识别[J].计算机应用研究,2009,26(11)
[11]杨琳.数字通信信号调制方式自动识别技术研究[D].合肥：中国科技大学,2008
[12]赵叶芳.基于谱相关和神经网络的调制方式识别究[D].哈尔滨：哈尔滨工业大学,2011
[13].龚晓洁.基于支持向量机的调制方式识别算法的研究[D].南京：南京邮电大学,2011
[14]薛富强.进化RBF神经网络分类器研究[D].郑州：解放军信息工程大学,2009
[15]陆明泉.多信号调制识别研究[D].成都：电子科技大学.2009
[16]A. K. Nandi, E. E. Azzouz. Modulation recognition using artificial neural networks[J]. Signal Processing,1997,165-175
[17]M. L. D. Wong, A. K. Nandy. Automatic digital modulation recognition using spectral and statistical features with multi-layer perceptrons. Proc. Int. Symp. Signal Processing and Its Applications,2001,2:390-393
[18]李旷代,郭黎利,石荣,吴丹.单信道时频重叠MPSK信号的调制识别方法[J].火力与指挥控制.2010,35(2)
[19]程汉文,吴乐南.基于多天线接收机的信号调制方式识别[J].信号处理.2009,25(2)
[20]李园敏,江桦,李霞.数字信号调制识别的RBFNN分类器算法研究与实现[J].计算机应用.2009年,29(3)
[21]Yue-xian Wu, Lin-dong Ge, Fan-fan Liu. Comprehensive features based digital modulation identification using a neural tree network. Proc. ICCCS,2005,2:214-217
[22]Mirmomeni, B. Moshiri, C. Lucas. Modulation identification using combined classifiers and co-evolution of classifiers and tests. Proc.10th International Conference on Information Fusion,2007,1-8
[23]齐峰.人工神经树网络模型的优化研究与应用[D].济南：山东师范大学.2011
[24]A.K. Nandi and E.E. Azzouz, "Automatic analogue modulation recognition"[J],Signal Processing, Vol.46, No.2, November 1995, pp.211-222.
[25]E.E. Azzouz and A.K. Nandi, "Automatic Modulation Recognition of Communication Signals", Kluwer Academic Publishers,1996.
[26]E.E. Azzouz and A.K. Nandi, "Procedure for Automatic Recognition of Analogue and Digital Modulations"[J], IEEE Proceedings Communication, vol.143, no.5, pp.259_ 266, October 1996.
[27]A.K. Nandi and E.E. Azzouz, "Algorithms for Automatic Modulation Recognition of Communication Signals"[J], IEEE Transactions on Communication, vol.46, no.4, pp.431_436, April 1998.
[28]苗建苏,傅丰林.RBF网络在通信信号自动识别中的应用[J].西安电子科技大学学报,1996,23：112-120
[29]Ta, Nhi P., "Wavlet packet approach to radio signal modulation classification". ICCS'94, Singapore, Vol.80, No.2, pp.251-277,2000
[30]H. Mustafa, M. Doroslovacki. Digital modulation recognition using support vector machine classifier. Proc.38th Asilomar Conference on Signals, Systems and Computers, 2004,2:2238-2242
[31]Cheol-Sun Park, Jun-Ho Choi, Sun-Phil Nah, Won Jang, Dae Young Kim. Automatic Modulation Recognition of Digital Signals using Wavelet Features and SVM[C]. Proc. 1CACT,2008,1:387-390
[32]Mingquan Lu, Xianci Xiao and Lemin Li. AR Modeling Based Feature Extraction of Mutiple Signals for Modulation Recognition[C].Proc. of 1CSP,1998,2:1385-1388
[33]Kuang-dai Li.Modulation Recognition Method Based on High Order Cyclic Cumulants for Time-Frequency Overlapped Two-Signal in the Single-Channel[C]. Proc. CISP,2008,5:474-478
[34]葛春,何兵,高江.基于小波神经网络的信号调制识别[J].通信技术,2009,42(10)
[35]敖仙丹,何世彪,黄付庆.基于谱相关和神经网络的信号调制识别[J].重庆邮电大学学报(自然科学版),2008,20(5)
[36]Thomas A, Drumright, Zhi D. A New Algorithmfor QAM SignalClassfication in AWGN Channels. ISCAS,2002,1:849-852.
[37]Zhijin Zhao, Tao Lang.A classification method for MPSK signals based onthe maximum likelihood criterion. IEEE6th CAS Symp. On Emerging Technologies:Mobile and Wireless Comm. Shanghai, China, May 31-June 2,2004.
[38]刘明赛,李兵兵,刘涵.数字调制信号识别性能的评估方法[J].计算机科学,2011,38(5)
[39]胡敏,易波,土世练.基于滑动平均和高阶统计量的数字调制识别[J].电子信息对抗技术,2006,7(4)：15-18
[40]高玉龙.基于循环谱的调制方式识别与高动态同步技术研究[D].哈尔滨：哈尔滨工业大学,2007
[41]吕铁军,肖先赐.基于神经网络最佳分类器通信信号的调制识别[J].系统工程与电子技术,2001.23：44-46
[42]葛娟,李一兵,林云.一种新的混合信号调制识别方法[J].弹箭与制导学报,2011,31(6)
[43]L. C. Godara. Applications of Antenna Arrays to Mobile ommunications, Part I: Performance Improvement, Feasibility, and System Considerations. Proc. of The IEEE,1997, 85(7):1031-1060
[44]高宪军,张杰,洪俞,程国晓.基于遗传算法优化神经网络的技术研究[J].装备制造技术,2010,2
[45]杨梅,卿晓霞,王波.基于改进遗传算法的神经网络优化方法[J].计算机仿真,2009,26(5)
[46]张伟栋,叶贞成,钱锋.基于混合编码的遗传算法在神经网络优化中的应用[J].华东理工人学学报(自然利学版),2008,Vol.34 No.1
[47]李慧芳,姚跃华,陈一栋.改进的遗传算法对神经网络优化的分类[J].微计算机信息,2008,24(5-3)
[48]王宏禹等.非平稳随机信号处理[M].北京：国防工业出版社,2008,p(31-39)
[49]Huang, N.E, et al. The empirical mode composition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Soc.Lond.A.1998; Vol-454:903-995
[50]邵峰晶.数据挖掘原理与算法[M].北京：科学出版社,2009,p(132-258)
[51]兰盛芳.试论达尔文进化论与协同进化论[J].生态科学,1995,2：167-170
[52]巩敦卫,孙晓燕.协同进化遗传算法理论及应用[M].北京：科学出版社,2009,p(1-125)
[53]李敏强,寇纪松,多模态函数优化的协同多群体遗传算法[J].自动化学报,2002,28(4)：497-504
[54]Jason M. Co-evolution and genetic algorithm.Carleton University,1997
[55]Pottre. M. A.The design and analysis of a computational model of cooperaLive coevolution [D].George Mmon University. Fairfax.1997
[56]Wiegand R P.An analysis of cooperative co-evolutionary aigrithm. Fairfax:George Mason University,2003
[57]Tsutsui S,Goldberg D E.Simplex crossover andlinkage identification, single-stage evolution vs. multi-stage evolution. IlliGA1 Report No.2002001,Urbana:University of Illinois at Urbana-Champaign,2002
[58]PEDRAIAS N C,MARTINEZ C H,PEREZ.J.M. Multi-objective cooperative co-evolution of artificial neural networks [J].Neural Networks.2008.15(10):1259-1278
[59]POTTER M A, DE JONG K A. Cooperative co-evolutionary architecture for evolving co-adapted subcomponents [J].Evolutionary Compution.2006.8(1)1-29
[60]A. A. Tadaion, M. Derakhtian, S. Gazor, M. R. Aref, Hong Li, O. A. Dobre,Y Bar-Ness, W.Su. Quasi-hybrid likelihood modulation classification with nonlinear carrier frequency offsets estimation using antenna arrays[J].Proc. IEEE MILCOM,2005,1:570-575
[61]M. L. D. Wong, A. K. Nandi. Blind Phase-Amplitude Modulation Classification with Unknown Phase Offset. Proc. ICPR,2006,4:177-180
[62]Hsiao-Chun Wu, M. Saquib, Zhifeng Yun, Novel Automatic Modulation Classification Using Cumulate Features for Communications via Multipath Channels. IEEE Transactions on Wireless Communications,2008,7:3098-3105
[2]P A. J. Nagy. A Modulation Classifier for Muti Channel Systems and Multi Transmitter Sitiations. Proc. IEEE MILCOM,1994,816-820
[3]刘澍.基于改进蚁群算法与神经网络的调制识别研究[D].武汉：华中科技大学,2009
[4]贺涛.数字通信信号调制识别若干新问题研究[D].成都：电子科技大学,2009
[5]Liedtle F F. "Computer simulation of an automatic classification procedure for digitally modulated communication signals with unknown parameters"[J]. Signal Processing 1984,6(4):311-323
[6]J. G. Proakis, M. Salehi. Fundamentals of Communication Systems, Prentice-Hall,2004
[7]E. E. Azzouz, A. K. Nandi. Automatic Modulation Recognition of Communication Signals. Kluwer Academic,1996
[8]Antti-Veikko Rosti "Statistic Methods in Modulation Classification" Master of Science Thesis,Tampere University of Technology Department of Information Technology,1998.
[9]赵知劲等.基于Hilbert-Huang的信号瞬时参数提取[J].信号处理,2005,Vol.21.No.4A
[10]王艳聪,胡中豫,张云飞.基于谱相关特性和组合神经网络的数字调制信号识别[J].计算机应用研究,2009,26(11)
[11]杨琳.数字通信信号调制方式自动识别技术研究[D].合肥：中国科技大学,2008
[12]赵叶芳.基于谱相关和神经网络的调制方式识别究[D].哈尔滨：哈尔滨工业大学,2011
[13].龚晓洁.基于支持向量机的调制方式识别算法的研究[D].南京：南京邮电大学,2011
[14]薛富强.进化RBF神经网络分类器研究[D].郑州：解放军信息工程大学,2009
[15]陆明泉.多信号调制识别研究[D].成都：电子科技大学.2009
[16]A. K. Nandi, E. E. Azzouz. Modulation recognition using artificial neural networks[J]. Signal Processing,1997,165-175
[17]M. L. D. Wong, A. K. Nandy. Automatic digital modulation recognition using spectral and statistical features with multi-layer perceptrons. Proc. Int. Symp. Signal Processing and Its Applications,2001,2:390-393
[18]李旷代,郭黎利,石荣,吴丹.单信道时频重叠MPSK信号的调制识别方法[J].火力与指挥控制.2010,35(2)
[19]程汉文,吴乐南.基于多天线接收机的信号调制方式识别[J].信号处理.2009,25(2)
[20]李园敏,江桦,李霞.数字信号调制识别的RBFNN分类器算法研究与实现[J].计算机应用.2009年,29(3)
[21]Yue-xian Wu, Lin-dong Ge, Fan-fan Liu. Comprehensive features based digital modulation identification using a neural tree network. Proc. ICCCS,2005,2:214-217
[22]Mirmomeni, B. Moshiri, C. Lucas. Modulation identification using combined classifiers and co-evolution of classifiers and tests. Proc.10th International Conference on Information Fusion,2007,1-8
[23]齐峰.人工神经树网络模型的优化研究与应用[D].济南：山东师范大学.2011
[24]A.K. Nandi and E.E. Azzouz, "Automatic analogue modulation recognition"[J],Signal Processing, Vol.46, No.2, November 1995, pp.211-222.
[25]E.E. Azzouz and A.K. Nandi, "Automatic Modulation Recognition of Communication Signals", Kluwer Academic Publishers,1996.
[26]E.E. Azzouz and A.K. Nandi, "Procedure for Automatic Recognition of Analogue and Digital Modulations"[J], IEEE Proceedings Communication, vol.143, no.5, pp.259_ 266, October 1996.
[27]A.K. Nandi and E.E. Azzouz, "Algorithms for Automatic Modulation Recognition of Communication Signals"[J], IEEE Transactions on Communication, vol.46, no.4, pp.431_436, April 1998.
[28]苗建苏,傅丰林.RBF网络在通信信号自动识别中的应用[J].西安电子科技大学学报,1996,23：112-120
[29]Ta, Nhi P., "Wavlet packet approach to radio signal modulation classification". ICCS'94, Singapore, Vol.80, No.2, pp.251-277,2000
[30]H. Mustafa, M. Doroslovacki. Digital modulation recognition using support vector machine classifier. Proc.38th Asilomar Conference on Signals, Systems and Computers, 2004,2:2238-2242
[31]Cheol-Sun Park, Jun-Ho Choi, Sun-Phil Nah, Won Jang, Dae Young Kim. Automatic Modulation Recognition of Digital Signals using Wavelet Features and SVM[C]. Proc. 1CACT,2008,1:387-390
[32]Mingquan Lu, Xianci Xiao and Lemin Li. AR Modeling Based Feature Extraction of Mutiple Signals for Modulation Recognition[C].Proc. of 1CSP,1998,2:1385-1388
[33]Kuang-dai Li.Modulation Recognition Method Based on High Order Cyclic Cumulants for Time-Frequency Overlapped Two-Signal in the Single-Channel[C]. Proc. CISP,2008,5:474-478
[34]葛春,何兵,高江.基于小波神经网络的信号调制识别[J].通信技术,2009,42(10)
[35]敖仙丹,何世彪,黄付庆.基于谱相关和神经网络的信号调制识别[J].重庆邮电大学学报(自然科学版),2008,20(5)
[36]Thomas A, Drumright, Zhi D. A New Algorithmfor QAM SignalClassfication in AWGN Channels. ISCAS,2002,1:849-852.
[37]Zhijin Zhao, Tao Lang.A classification method for MPSK signals based onthe maximum likelihood criterion. IEEE6th CAS Symp. On Emerging Technologies:Mobile and Wireless Comm. Shanghai, China, May 31-June 2,2004.
[38]刘明赛,李兵兵,刘涵.数字调制信号识别性能的评估方法[J].计算机科学,2011,38(5)
[39]胡敏,易波,土世练.基于滑动平均和高阶统计量的数字调制识别[J].电子信息对抗技术,2006,7(4)：15-18
[40]高玉龙.基于循环谱的调制方式识别与高动态同步技术研究[D].哈尔滨：哈尔滨工业大学,2007
[41]吕铁军,肖先赐.基于神经网络最佳分类器通信信号的调制识别[J].系统工程与电子技术,2001.23：44-46
[42]葛娟,李一兵,林云.一种新的混合信号调制识别方法[J].弹箭与制导学报,2011,31(6)
[43]L. C. Godara. Applications of Antenna Arrays to Mobile ommunications, Part I: Performance Improvement, Feasibility, and System Considerations. Proc. of The IEEE,1997, 85(7):1031-1060
[44]高宪军,张杰,洪俞,程国晓.基于遗传算法优化神经网络的技术研究[J].装备制造技术,2010,2
[45]杨梅,卿晓霞,王波.基于改进遗传算法的神经网络优化方法[J].计算机仿真,2009,26(5)
[46]张伟栋,叶贞成,钱锋.基于混合编码的遗传算法在神经网络优化中的应用[J].华东理工人学学报(自然利学版),2008,Vol.34 No.1
[47]李慧芳,姚跃华,陈一栋.改进的遗传算法对神经网络优化的分类[J].微计算机信息,2008,24(5-3)
[48]王宏禹等.非平稳随机信号处理[M].北京：国防工业出版社,2008,p(31-39)
[49]Huang, N.E, et al. The empirical mode composition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Soc.Lond.A.1998; Vol-454:903-995
[50]邵峰晶.数据挖掘原理与算法[M].北京：科学出版社,2009,p(132-258)
[51]兰盛芳.试论达尔文进化论与协同进化论[J].生态科学,1995,2：167-170
[52]巩敦卫,孙晓燕.协同进化遗传算法理论及应用[M].北京：科学出版社,2009,p(1-125)
[53]李敏强,寇纪松,多模态函数优化的协同多群体遗传算法[J].自动化学报,2002,28(4)：497-504
[54]Jason M. Co-evolution and genetic algorithm.Carleton University,1997
[55]Pottre. M. A.The design and analysis of a computational model of cooperaLive coevolution [D].George Mmon University. Fairfax.1997
[56]Wiegand R P.An analysis of cooperative co-evolutionary aigrithm. Fairfax:George Mason University,2003
[57]Tsutsui S,Goldberg D E.Simplex crossover andlinkage identification, single-stage evolution vs. multi-stage evolution. IlliGA1 Report No.2002001,Urbana:University of Illinois at Urbana-Champaign,2002
[58]PEDRAIAS N C,MARTINEZ C H,PEREZ.J.M. Multi-objective cooperative co-evolution of artificial neural networks [J].Neural Networks.2008.15(10):1259-1278
[59]POTTER M A, DE JONG K A. Cooperative co-evolutionary architecture for evolving co-adapted subcomponents [J].Evolutionary Compution.2006.8(1)1-29
[60]A. A. Tadaion, M. Derakhtian, S. Gazor, M. R. Aref, Hong Li, O. A. Dobre,Y Bar-Ness, W.Su. Quasi-hybrid likelihood modulation classification with nonlinear carrier frequency offsets estimation using antenna arrays[J].Proc. IEEE MILCOM,2005,1:570-575
[61]M. L. D. Wong, A. K. Nandi. Blind Phase-Amplitude Modulation Classification with Unknown Phase Offset. Proc. ICPR,2006,4:177-180
[62]Hsiao-Chun Wu, M. Saquib, Zhifeng Yun, Novel Automatic Modulation Classification Using Cumulate Features for Communications via Multipath Channels. IEEE Transactions on Wireless Communications,2008,7:3098-3105