基于稀疏自动编码网络的水声通信信号调制识别
|
摘要
研究了基于稀疏自动编码网络的水声通信信号识别方法。首先利用稀疏自动编码网络对接收信号的功率谱识别分类,得到除PSK外信号的调制类型,然后对识别结果为PSK的信号做四次方谱,最后利用稀疏自动编码网络完成对QPSK和8PSK的识别分类。仿真实验表明,稀疏自动编码网络能从接收信号的谱信息中自动提取有效谱特征。与传统基于功率谱特征提取的识别方法相比,本文算法减少了依赖领域知识的特征提取环节,识别性能优于传统算法。
This paper studies the method of underwater communication signals' recognition based on sparse autoencoding network. Firstly,the power spectrums of the received signals are classified using a sparse autoencoding network,getting modulation types of signals except of PSK. Then make the quartic spectrums of the signals whose recognition results are PSK in the first step. Finally,the classification of QPSK and 8PSK's quartic spectrums is completed by using another sparse autoencoding network. Simulation experiments show that the sparse autoencoding network can automatically extract effective spectrum features from the received signals' spectrum information. Compared with the traditional recognition method based on power spectrum feature extraction,the proposed algorithm reduces the feature extraction process based on domain knowledge,and the recognition performance is better than the traditional algorithm.
This paper studies the method of underwater communication signals' recognition based on sparse autoencoding network. Firstly,the power spectrums of the received signals are classified using a sparse autoencoding network,getting modulation types of signals except of PSK. Then make the quartic spectrums of the signals whose recognition results are PSK in the first step. Finally,the classification of QPSK and 8PSK's quartic spectrums is completed by using another sparse autoencoding network. Simulation experiments show that the sparse autoencoding network can automatically extract effective spectrum features from the received signals' spectrum information. Compared with the traditional recognition method based on power spectrum feature extraction,the proposed algorithm reduces the feature extraction process based on domain knowledge,and the recognition performance is better than the traditional algorithm.
引文
[1]Zhang Conghui,Wang Yiyin,Guan Xinping.Chaotic Modulation Detection for Underwater Acoustic Communications Via Instantaneous Features[C]∥Oceans.IEEE,2016:1-5.
[2]赵春晖,杨伟超,杜宇.采用分数低阶循环谱相干系数的调制识别[J].应用科学学报,2011,29(6):565-570.Zhao Chunhui,Yang Weichao,Du Yu.Modulation Recognition Using Fractional Low-Order Cyclic Spectrum Coherence Coefficient[J].Journal of Applied Sciences,2011,29(6):565-570.(in Chinese)
[3]赵春晖,杨伟超,马爽.基于广义二阶循环统计量的通信信号调制识别研究[J].通信学报,2011,32(1):144-150.Zhao Chunhui,Yang Weichao,Ma Shuang.Research on Communication Signal Modulation Recognition Based on Generalized Second-Order Cyclic Statistics[J].Journal of Communications,2011,32(1):144-150.(in Chinese)
[4]周青,孙海信,周明章.一种水声通信信号调制模式识别方法[J].通信对抗,2017,1(2):12-17.Zhou Qing,Sun Haixin,Zhou Mingzhang.One Method of Standard Recognition of Underwater Acoustic Signal[J].Communications Countermeasures,2017,1(2):12-17.(in Chinese)
[5]Goodfellow I,Bengio Y,Courville A.深度学习[M].赵申剑,黎彧君,符天凡,等,译.北京:人民邮电出版社,2017:306-310.Goodfellow I,Bengio Y,Courville A.Deep Learning[M].Zhao Shenjian,Li Yujun,Fu Tianfan,et al,Trans.Beijing:People Posts and Telecom Press,2017:306-310.(in Chinese)
[6]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.Sun Wenjun,Shao Siyu,Yan Ruqiang.Introduction Motor Fault Diagnosis Based on Deep Neural Network of Sparse Auto-encoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.(in Chinese)
[7]Sch9lkopf B,Platt J,Hofmann T.Greedy Layer-Wise Training of Deep Networks[J].Advances in Neural Information Processing Systems,2007,19(1):153-160.
[8]张歆,张小蓟.水声通信理论与应用[M].西安:西北工业大学出版社,2012.Zhang Xin,Zhang Xiaoji.Theory and Application of Underwater Acoustic Communication[M].Xi’an:Northwestern Polytechnical University Press,2012.(in Chinese)
[9]殷敬伟.水声通信原理及信号处理技术[M].北京:国防工业出版社,2011.Yin Jingwei.Underwater Acoustic Communication Principle and Signal Processing Technology[M].Beijing:National Defense Industry Pess,2011.(in Chinese)
[10]Zhou Y,Qaraqe K,Serpedin E,et al.FSK-signal Detection in Cognitive Radios Using First-order Cyclostationarity[C]∥Telecommunications(ICT),2010IEEE 17th International Conference on.IEEE,2010:110-115.
[11]Theodore S R.无线通信原理与应用[M].周文安,付秀花,王志辉,等,译.第2版.北京:电子工业出版社,2007.Theodore S R.Wireless Communications:Principles and Practice[M].Zhou Wen’an,Fu Xiuhua,Wang Zhihui,et al.Trans.Sencond Edition.Beijing:Pubilishing House of E-lectronics Industry,2007.(in Chinese)
[12]Punchiewa A,Dobre O A,Rajan S,et al.Cyclostationarity-based Algorithm for Blind Recognition of OFDM and Single Carrier Liner Digital Modulations[C]∥IEEE PIM-RC,2007:1-5.
[13]刘勇,张国毅,张旭洲.线性调频连续波雷达信号的参数估计[J].信号处理,2014,30(7):848-855.Liu Yong,Zhang Guoyi,Zhang Xuzhou.Parameter Estimation of LFMCW Radar Signal[J].Journal of Signal Processing,2014,30(7):848-855.(in Chinese)
[14]史甜姝.数字通信信号调制方式自动识别方法的研究与应用[D].天津:天津大学,2016.Shi Tianshu.Research and Application of Automatic Modulation Recognition of Digital Communication Signals[D].Tianjin:Tianjin University,2016.(in Chinese)
[15]邢晓晴,朱根民.Welch功率谱估计中窗函数的选择与算法分析[J].计算机时代,2018,1(2):1-4.Xing Xiaoqing,Zhu Genmin.Window Function Selection and Algorithm analysis in Welch Power Spectrum Estimation[J].Computer Age,2018,1(2):1-4.(in Chinese)
[16]刘亚冲,唐智灵.基于Softmax回归的通信辐射源特征分类识别方法[J].计算机工程,2018,44(2):98-102.Liu Yachong,Tang Zhiling.Classification and Identification Method of Communication Radiation Source Feature Based on Softmax Regression[J].Computer Engineering,2018,44(2):98-102.(in Chinese)
[17]汪海波,陈雁翔,李艳秋.基于主成分分析和Softmax回归模型的人脸识别方法[J].合肥工业大学学报:自然科学版,2015,38(6):759-763.Wang Haibo,Chen Yanxiang,Li Yanqiu.Face Recognition Method Based on Principal Component Analysis and Softmax Regression Model[J].Journal of Hefei University of Technology:Natural Science,2015,38(6):759-763.(in Chinese)
[2]赵春晖,杨伟超,杜宇.采用分数低阶循环谱相干系数的调制识别[J].应用科学学报,2011,29(6):565-570.Zhao Chunhui,Yang Weichao,Du Yu.Modulation Recognition Using Fractional Low-Order Cyclic Spectrum Coherence Coefficient[J].Journal of Applied Sciences,2011,29(6):565-570.(in Chinese)
[3]赵春晖,杨伟超,马爽.基于广义二阶循环统计量的通信信号调制识别研究[J].通信学报,2011,32(1):144-150.Zhao Chunhui,Yang Weichao,Ma Shuang.Research on Communication Signal Modulation Recognition Based on Generalized Second-Order Cyclic Statistics[J].Journal of Communications,2011,32(1):144-150.(in Chinese)
[4]周青,孙海信,周明章.一种水声通信信号调制模式识别方法[J].通信对抗,2017,1(2):12-17.Zhou Qing,Sun Haixin,Zhou Mingzhang.One Method of Standard Recognition of Underwater Acoustic Signal[J].Communications Countermeasures,2017,1(2):12-17.(in Chinese)
[5]Goodfellow I,Bengio Y,Courville A.深度学习[M].赵申剑,黎彧君,符天凡,等,译.北京:人民邮电出版社,2017:306-310.Goodfellow I,Bengio Y,Courville A.Deep Learning[M].Zhao Shenjian,Li Yujun,Fu Tianfan,et al,Trans.Beijing:People Posts and Telecom Press,2017:306-310.(in Chinese)
[6]孙文珺,邵思羽,严如强.基于稀疏自动编码深度神经网络的感应电动机故障诊断[J].机械工程学报,2016,52(9):65-71.Sun Wenjun,Shao Siyu,Yan Ruqiang.Introduction Motor Fault Diagnosis Based on Deep Neural Network of Sparse Auto-encoder[J].Journal of Mechanical Engineering,2016,52(9):65-71.(in Chinese)
[7]Sch9lkopf B,Platt J,Hofmann T.Greedy Layer-Wise Training of Deep Networks[J].Advances in Neural Information Processing Systems,2007,19(1):153-160.
[8]张歆,张小蓟.水声通信理论与应用[M].西安:西北工业大学出版社,2012.Zhang Xin,Zhang Xiaoji.Theory and Application of Underwater Acoustic Communication[M].Xi’an:Northwestern Polytechnical University Press,2012.(in Chinese)
[9]殷敬伟.水声通信原理及信号处理技术[M].北京:国防工业出版社,2011.Yin Jingwei.Underwater Acoustic Communication Principle and Signal Processing Technology[M].Beijing:National Defense Industry Pess,2011.(in Chinese)
[10]Zhou Y,Qaraqe K,Serpedin E,et al.FSK-signal Detection in Cognitive Radios Using First-order Cyclostationarity[C]∥Telecommunications(ICT),2010IEEE 17th International Conference on.IEEE,2010:110-115.
[11]Theodore S R.无线通信原理与应用[M].周文安,付秀花,王志辉,等,译.第2版.北京:电子工业出版社,2007.Theodore S R.Wireless Communications:Principles and Practice[M].Zhou Wen’an,Fu Xiuhua,Wang Zhihui,et al.Trans.Sencond Edition.Beijing:Pubilishing House of E-lectronics Industry,2007.(in Chinese)
[12]Punchiewa A,Dobre O A,Rajan S,et al.Cyclostationarity-based Algorithm for Blind Recognition of OFDM and Single Carrier Liner Digital Modulations[C]∥IEEE PIM-RC,2007:1-5.
[13]刘勇,张国毅,张旭洲.线性调频连续波雷达信号的参数估计[J].信号处理,2014,30(7):848-855.Liu Yong,Zhang Guoyi,Zhang Xuzhou.Parameter Estimation of LFMCW Radar Signal[J].Journal of Signal Processing,2014,30(7):848-855.(in Chinese)
[14]史甜姝.数字通信信号调制方式自动识别方法的研究与应用[D].天津:天津大学,2016.Shi Tianshu.Research and Application of Automatic Modulation Recognition of Digital Communication Signals[D].Tianjin:Tianjin University,2016.(in Chinese)
[15]邢晓晴,朱根民.Welch功率谱估计中窗函数的选择与算法分析[J].计算机时代,2018,1(2):1-4.Xing Xiaoqing,Zhu Genmin.Window Function Selection and Algorithm analysis in Welch Power Spectrum Estimation[J].Computer Age,2018,1(2):1-4.(in Chinese)
[16]刘亚冲,唐智灵.基于Softmax回归的通信辐射源特征分类识别方法[J].计算机工程,2018,44(2):98-102.Liu Yachong,Tang Zhiling.Classification and Identification Method of Communication Radiation Source Feature Based on Softmax Regression[J].Computer Engineering,2018,44(2):98-102.(in Chinese)
[17]汪海波,陈雁翔,李艳秋.基于主成分分析和Softmax回归模型的人脸识别方法[J].合肥工业大学学报:自然科学版,2015,38(6):759-763.Wang Haibo,Chen Yanxiang,Li Yanqiu.Face Recognition Method Based on Principal Component Analysis and Softmax Regression Model[J].Journal of Hefei University of Technology:Natural Science,2015,38(6):759-763.(in Chinese)