脉冲噪声下基于平滑循环相关熵谱的调制识别方法  

Pol-CCES based modulation recognition method under impulsive noise

作　　者：戴江安 栾声扬 赵明龙 张兆军 邱天爽 DAI Jiang’an;LUAN Shengyang;ZHAO Minglong;ZHANG Zhaojun;QIU Tianshuang(Faculty of Electronic Information and Electrical Engineering,Dalian University of Technology,Dalian 116024,China;School of Electrical Engineering and Automation,Jiangsu Normal University,Xuzhou 221116,China)

机构地区：[1]大连理工大学电子信息与电气工程学部,辽宁大连116024 [2]江苏师范大学电气工程及自动化学院,江苏徐州221116

出　　处：《通信学报》2021年第12期121-133,共13页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61671105,No.61801197)。

摘　　要：针对脉冲噪声下的信号分类问题,提出了基于平滑循环相关熵谱和浅层残差网络的调制识别方案。所提方案不仅具有较低的计算复杂度,而且在脉冲噪声环境中具有稳健性。仿真实验表明,即使在很低的广义信噪比下,所提方案依然具有良好的性能。To realize signal classification in impulsive noise environment,a modulation recognition scheme based on polished cyclic correntropy spectrum and shallow residual network was proposed.The proposed scheme not only has low computational complexity but also shows robustness to impulsive noise.Simulation results demonstrate the proposed solution’s superior performance under impulsive noise,even when the generalized signal-to-noise ratio is very low.

关 键 词：调制识别 脉冲噪声 平滑循环相关熵谱 浅层残差网络 

分 类 号：TN911.7[电子电信—通信与信息系统]