摘要
为了解决工程应用中传统数字信号处理方法对于低信噪比条件下盲突发通信信号检测存在检测正确率低和虚警率高的问题,提出了一种基于卷积神经网络(Convolutional Neural Network, CNN)的突发通信信号检测方法。该方法将传统数字信号处理提取检测特征与CNN深度学习结合,提高了低信噪比条件下突发通信信号检测的正确率,降低了虚警率。对比实验表明,对于QPSK突发通信信号,该方法比多分辨分析数字信号处理方法性能提高大约4 dB,比自适应门限能量数字信号检测处理方法性能提高大约8 dB。
In engineering application,traditional digital signal processing methods for low signal-to-noise-ratio burst communication signals detection encounter a low detection probability and a high false alarm probability.A new kind of burst communication signals detection method is proposed.It combines traditional digital signal processing methods for low signal-to-noise-ratio burst communication signals with the Convolutional Neural Network(CNN),and turns the signal detection to object detection using deep learning network.It increases the detection probability and decreases the false alarm probability for burst communication signals detection.Simulation experiments verified that the performance increases about 4 dB compared with the traditional multi-resolution signal analysis method,and increases about 8 dB compared with the traditional power method.
作者
吴玲玲
李广峰
韩邦杰
程晓静
CNN WU Lingling;LI Guangfeng;HAN Bangjie;CHENG Xiaojing(The 54th Research Institute of CETC,Shijiazhuang 050081,China;Hebei Key Laboratory of Electromagnetic Spectrum Cognition and Control,Shijiazhuang 050081,China;Unit 91746,PLA,Beijing 102600,China;MRO of AFED,Baoding 071000,China)
出处
《无线电通信技术》
2023年第2期318-324,共7页
Radio Communications Technology
基金
国家自然科学基金(U19B2028)。
关键词
突发通信
信号检测
卷积神经网络
多分辨分析
burst communication
signals detection
CNN
multi-resolution signal analysis