基于高效双流输入结构的自动调制识别方法  

Automatic Modulation Recognition Method Based on Efficient Dual Stream Input Structure

作　　者：郭业才[1,2] 毛湘南 胡晓伟 周雪 赵涵优 GUO Ye-cai;MAO Xiang-nan;HU Xiao-wei;ZHOU Xue;ZHAO Han-you(School of Electronics and Information Engineer,Nanjing University of Information Science and Technology,Nanjing 210044,China;School of Electronics and Information Engineer,Wuxi University,Wuxi 214000,China)

机构地区：[1]南京信息工程大学电子与信息工程学院,江苏南京210044 [2]无锡学院电子与信息工程学院,江苏无锡214000

出　　处：《中国电子科学研究院学报》2024年第3期248-256,295,共10页Journal of China Academy of Electronics and Information Technology

基　　金：国家自然科学基金资助项目(61673222)。

摘　　要：自动调制识别是现代通信系统中一项重要技术。为提高通信系统对不同调制信号间的识别性能,文中首先探索了包含11类调制信号的公开数据集RML2016.10A上原始同相正交(In-phase and Quadrature,IQ)格式数据和经过数据预处理后的幅度和相位(Amplitude and Phase,AP)格式数据的差异;随后,依据原始IQ格式数据和AP格式数据在特征提取过程中对局部相关性及时序特征敏感性的差异,设计了针对空间特征提取的SFE-Block模块、针对长期依赖关系提取的TFE-Block模块,以及联合时空特征提取模块STFE-Block,并将前两者的输出特征作为STFE-Block模块输出特征的重要补充进行特征融合,以全连接(Fully Connected)层负责最终分类。实验结果表明,本模型在数据集RML2016.10A上表现良好。当信噪比(Signal to Noise Ratio,SNR)低于-8 dB时,平均识别精度比其他模型提升7%,而SNR在0~18 dB时,平均识别精度比其他模型提高1%~8%,且在SNR为16 dB时,最高识别精度达92.95%。此外,在RML2016.10B数据集上重复了实验以检验模型泛化性,所得结果同样最优,且当SNR为12 dB时,最高识别精度达到93.6%。Automatic Modulation Recognition(AMR) is a critical technology in modern communication systems.To improve the recognition performance of communication systems for different modulation signals,this study initially explores the differences between the original In-phase and Quadrature(IQ) format data and Amplitude and Phase(AP) format data after preprocessing.Subsequently,based on the sensitivity of local correlation and temporal features during feature extraction from both IQ and AP formatted data,we designed the SFE-Block module for spatial feature extraction,the TFE-Block module for extracting long-term dependencies and the STFE-Block module for extracting joint spatiotemporal features.The outputs of these modules supplement the joint spatio-temporal feature extraction provided by the STFE-Block module,which are then fused for feature integration,with a fully connected(FC) layer responsible for the final classification.Experimental results demonstrate that our model performs well on the public dataset RML2016.10A.When the Signal to Noise Ratio(SNR) is below-8 dB,the average recognition accuracy of this model improves by 7% compared to other models.In the SNR range of 0~18 dB,the average recognition accuracy exceeds that of other models by 1%~8%,and achieving a maximum recognition accuracy of 92.95% at a SNR of 16 dB.In addition,the experiment was replicated on the RML2016.10 B dataset to test the model's generalizability,where it also showed favorable results,reaching a peak recognition accuracy of 93.6% at an SNR of 12 dB.

关 键 词：自动调制识别 深度学习 双流输入 

分 类 号：TN911[电子电信—通信与信息系统]