基于循环谱和改进的深度神经网络的频谱分析方法  

Cyclic spectrum and improved deep-neural-network based spectrum analysis method

作　　者：吴赛[1] 王智慧[1] 邵炜平 林春生 郑伟军 杨德龙[1] WU Sai;WANG Zhihui;SHAO Weiping;LIN Chunsheng;ZHENG Weijun;YANG Denglong(China Electric Power Research Institute,Beijing 100192,China;State Grid Zhejiang Electric Power Co.,LTD,Hangzhou,Zhejiang 310007,China;School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]中国电力科学研究院,北京100192 [2]国网浙江省电力有限公司,浙江杭州310007 [3]北京邮电大学信息与通信工程学院,北京100876

出　　处：《河北工业大学学报》2020年第3期40-45,共6页Journal of Hebei University of Technology

基　　金：国家电网科技项目(52110418001H)。

摘　　要：频谱分析的关键在于准确识别信号的调制方式,而常用的自动调制识别方法在低信噪比下的识别率低,并且能够识别的信号调制方式种类数少。基于此种情况,提出了一种基于循环谱和改进的深度神经网络的频谱分析方法。该方法使用卷积神经网络、长短时记忆和深度神经网络相结合的神经网络(CLDNN)并将循环谱特征作为该网络的原始输入特征。仿真结果显示所提出的方法在信噪比为-2 dB时能够达到90%的识别准确率,极大的提高了低信噪比情况下的信号识别性能。The essential of the accurate spectrum sensing is the automatic modulation classification.The commonly used automatic modulation classification(AMC)schemes has inferior classification performance at low signal-to-noise ratio(SNR)scenario and only few modulation formats can be identified.On this situation,a novel cyclic spectrum and improved deep-neural-network based modulation classification scheme is proposed,where convolutional neural network and a long short-term memory assisted deep neural network(CLDNN)structure is utilized and the cyclic spectrum features are the inputs of the network.The simulation results verify that the proposed scheme achieves 90%recognition accuracy at-2 dB SNR,which has greatly improved the recognition accuracy at low SNR and outperforms other recent methods.

关 键 词：自动调制分类 循环谱 神经网络 频谱感知 

分 类 号：TN911.7[电子电信—通信与信息系统]