| 摘要: |
| 针对现有深度学习调制识别算法在复杂信号环境下的鲁棒性和泛化能力不足的问题，提出了一种基于相位参数估计和空间重建的多通道网络（Phase Estimation and Spatial Reconstruction-based Attention Mechanism Multi-channel Network，PET-SAMCL。首先，将输入的同向正交信号(In-phase Quadrature,IQ通过相位参数估计转换，分成3个模块分别提取IQ的幅度-相位特征、IQ合路以及分路特征。在特征提取模块中加入空间重建单元（Spatial Reconstruction Unit，SRU，减少冗余特征的影响。利用全局平均池化和软注意力操作对空间特征进行提炼与融合，通过门控循环单元（Gated Recurrent Unit，GRU及双向门控循环单元（Bidirectional Gated Recurrent Unit，BiGRU提取时间和空间特征。通过消融实验确定了最优模型结构。该模型在RML2016.10a数据集上表现优异，在14 dB时达到了93.9%的最高识别准确率，平均识别率相较其他模型最大提高了7.7%。 |
| 关键词: 自动调制识别 深度学习 相位参数估计 空间重建单元 注意力机制 |
| DOI：10.20079/j.issn.1001-893x.240625003 |
|
| 基金项目:国家自然科学基金资助项目（62371245 |
|
| Automatic Modulation Recognition Based on Phase Parameter Estimation and Spatial Reconstruction |
| ZHANG Ziyin,LI Dapeng,SHAN Guoqiang |
| (a.College of Telecommunications & Information Engineering;b.Portland Institute,Nanjing University of Posts and Telecommunications,Nanjing 210003,China) |
| Abstract: |
| For the problem that the existing deep learning modulation recognition algorithms are not robust enough and have insufficient generalization ability in complex signal environments,a multi-channel network based on phase parameter estimation and spatial reconstruction（PET-SAMCL is proposed.First,the input in-phase quadature(IQ signal is converted by phase parameter estimation and divided into three modules to extract the amplitude-phase feature,IQ combination and branching features of IQ respectively.A spatial reorganization unit（SRUis added to the feature extraction module to reduce the influence of redundant features.The spatial features are refined and fused by global average pooling and soft attention operations,and the temporal and spatial features are extracted by gated recurrent units(GRU and bidirectional gated recurrent units(BiGRU.Ablation study determines the optimal model structure.The model performs well on the RML2016.10a dataset,achieving a maximum recognition accuracy of 93.9% at 14 dB,and the average recognition rate is increased by 7.7% compared with that of other models. |
| Key words: automatic modulation recognition deep learning phase parameter estimation spatial reconstruction unit attention mechanism |
