基于多模态时-频特征融合的信号调制格式识别方法

Automatic Modulation Recognition Method Based on Multimodal Time-Frequency Feature Fusion

自动调制识别(Automatic Modulation Recognition,AMR)是认知无线电中的关键技术,在无线通信中有着广泛应用。针对现有的自动调制识别方法大多都只利用了信号时域或频域的单模态信息,忽略了多模态信息之间的互补性的问题,提出了一种基于多模态时-频特征融合的信号调制格式识别方法。首先,在融合之前利用对比学习对齐信号的时域特征和频域特征,减小时-频特征间的异质性差异。然后,采用跨模态注意力实现时域特征和频域特征的互补性融合。最后,为了进一步提高模型整体的性能,在频域编码器中引入残差收缩模块来提取信号时频图的频域特征,并在时域编码器中引入复数双向门控循环单元,以提取I和Q两路信号之间的相关性特征及信号时序特征。在RadioML2016a上进行了实验,结果表明,所提方法具有较高的识别准确率和噪声鲁棒性。

Automatic modulation recognition(AMR)is a key technology in cognitive radio and has a wide range of applications in wireless communication.Aiming at the problem that most of the existing automatic modulation classification methods only use the single-modal information in the time domain or frequency domain,ignoring the complementarity between the multi-modal information,a signal modulation classification recognition method based on multimodal time-frequency feature fusion is proposed.First,the time-domain features and frequency-domain features of the signal are aligned by contrastive learning before fusion to reduce the heterogeneity difference.Secondly,cross-modal attention is used to achieve complementary fusion of time-domain features and frequency-domain features.Finally,in order to further improve the overall performance of the model,a residual shrin-kage module is introduced into the frequency domain encoder to extract the frequency domain features of the time-frequency map and the complex bidirectional gated recurrent unit is introduced into the time domain encoder to extract the correlation features between the I and Q signals and the time-domain features.Experimental results on RadioML2016a show that the proposed me-thod has higher recognition accuracy and noise robustness.