基于深度学习的多进制相移键控信号调制识别研究  

作　　者：杜云玲 唐明涛 

机构地区：[1]运城职业技术大学,山西运城044000 [2]河南理工大学鹤壁工程技术学院,河南鹤壁058000

出　　处：《现代传输》2024年第4期72-75,共4页Modern Transmission

摘　　要：众多学者深入研究了信号调制识别方法,但对于多进制相移键控信号(MPSK)的识别效果不佳。本文提出基于深度学习的识别模型,利用时频图和星座图特征识别MPSK信号类型,并融合两种识别结果进行决策。对比三种方法,有效提升了MPSK信号的识别效果。Numerous scholars have studied signal modulation recognition methods in depth,but they are not effective in recognising Multi-Progressive Phase Shift Keying(MPSK)signals.This paper proposes a recognition model based on deep learning,which uses time-frequency diagram and constellation diagram features to identify MPSK signal types,and fuses the two recognition results for decision making.Comparing the three methods,the recognition effect of MPSK signals is effectively improved.

关 键 词：深度学习 调制识别 多进制相移键控 决策融合 

分 类 号：TN911.3[电子电信—通信与信息系统] TP18[电子电信—信息与通信工程]