摘要
针对频率随时间的变化规律是不同调制信号之间最重要的区别,提出一种结合崔-威廉斯分布和改进卷积神经网络模型的无线电调制分类识别方法。在信号预处理阶段,为了更好保留信号的时频特征,引入崔-威廉斯变换将原始时间序列转换成时频图像,进而将调制信号分类问题转化成图像识别问题。在信号识别阶段,通过在卷积神经网络模型中引入残差密集块和全局平均池化层,以克服卷积神经网络模型泛化能力差和训练时间久等缺点。实验结果表明,所提方法可以有效解决梯度消失问题,具有识别率高、泛化能力强等优点。尤其是在低信噪比情况下,表现更为优异,在信噪比为-4 dB时,8种信号的分类精度便可达到100%。
As the variation law of frequency with time is the most important difference between different modulated signals,a radio modulation classification and recognition method combining Choi-Williams distribution and improved convolutional neural network model is proposed.In the signal preprocessing stage,in order to better retain the timefrequency characteristics of the signal,the Choi-Williams transform is introduced to transform the original time series signal into time-frequency image,and then the modulation signal classification problem is transformed into an image recognition problem.In the signal recognition stage,the convolutional neural network model is introduced with residual dense blocks and global average pooling layer to overcome the shortcomings of poor generalization ability and long training time of convolutional neural network model.Experimental results show that the proposed method can effectively solve the problem of gradient disappearance,and has the advantages of high recognition rate and strong generalization ability.Especially in the case of low SNR,the performance is even better.When the SNR is-4dB,the classification accuracy of 8kinds of signals can reach 100%.
作者
李宝平
魏坡
Li Baoping;Wei Po(School of Physics and Electronic Information,Henan Polytechnic University,Jiaozuo 454003,China)
出处
《电子测量技术》
北大核心
2023年第5期50-56,共7页
Electronic Measurement Technology
基金
河南省科技攻关项目(212102210557)
河南理工大学博士基金(B2017-55)项目资助
关键词
无线电调制分类
崔-威廉斯分布
卷积神经网络
残差密集块
radio modulation classification
Choi-Williams distribution
convolutional neural network
residual dense block
