基于信号序列的调制方式识别  

Modulation Recognition Based on Signal Sequences

作　　者：吴光磊 李强[3] WU Guanglei;Li Qiang(Fourth Laboratory,Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100085,China;School of Cyberspace Security,University of Chinese Academy of Sciences,Beijing 100049,China;Agency Service Bureau of the Ministry of Industry and Information Technology,Beijing 100804,China)

机构地区：[1]中国科学院信息工程研究所第四研究室,北京100085 [2]中国科学院大学网络空间安全学院,北京100049 [3]工业和信息化部机关服务局,北京100804

出　　处：《数字通信世界》2023年第5期25-28,共4页Digital Communication World

摘　　要：信号调制识别是无线电领域的重要技术,在无线通信和频谱资源优化等领域中具有广泛应用,有效的调制识别方法对于未知信号的分析认证具有重要意义。文章提出了一种基于信号序列的调制识别方法,通过BiLSTM网络对信号的频域和时域序列数据进行特征提取,并采用Attention机制对特征进行加权处理,最终利用S of tmax完成调制分类。通过在公开数据集RML2016.10.a上进行对比实验,证明了该方法的有效性。Modulation recognition of signals is an important technology in the field of wireless communication,with broad applications in wireless communication,and spectrum resource optimization.Effective modulation recognition methods have significant importance in the analysis and identification of unknown signals.In this paper,we propose a modulation recognition method based on signal sequences,which extracts features from the frequency and time domain sequences of signals using BiLSTM networks,and weights the features using the attention mechanism.Finally,the modulation classification is accomplished using Softmax.The effectiveness of the proposed method is demonstrated through comparative experiments on the publicly available RML2016.10.a dataset.

关 键 词：调制识别 时频信号 无线通信 

分 类 号：TN911.3[电子电信—通信与信息系统]