Ma Jiankun, Zhang Zhenxi, Zhang Linrun, Li Yu, Tan Haoyue, Shi Xiaoran, Zhou Feng
The Key Laboratory of Electronic Information Countermeasure and Simulation Technology of Ministry of Education, Xidian University, Xi'an 710126, China.
School of Aerospace Science and Technology, Xidian University, Xi'an 710126, China.
Sensors (Basel). 2025 Jul 23;25(15):4553. doi: 10.3390/s25154553.
Modulation recognition, as one of the key technologies in the field of wireless communications, holds significant importance in applications such as spectrum resource management, interference suppression, and cognitive radio. While deep learning has substantially improved the performance of Automatic Modulation Recognition (AMR), it heavily relies on large amounts of labeled data. Given the high annotation costs and privacy concerns, researching semi-supervised AMR methods that leverage readily available unlabeled data for training is of great significance. This study constructs a semi-supervised AMR method based on dual-student. Specifically, we first adopt a dual-branch co-training architecture to fully exploit unlabeled data and effectively learn deep feature representations. Then, we develop a dynamic stability evaluation module using strong and weak augmentation strategies to improve the accuracy of generated pseudo-labels. Finally, based on the dual-student semi-supervised framework and pseudo-label stability evaluation, we propose a stability-guided consistency regularization constraint method and conduct semi-supervised AMR model training. The experimental results demonstrate that the proposed DualBranch-AMR method significantly outperforms traditional supervised baseline approaches on benchmark datasets. With only 5% labeled data, it achieves a recognition accuracy of 55.84%, reaching over 90% of the performance of fully supervised training. This validates the superiority of the proposed method under semi-supervised conditions.
调制识别作为无线通信领域的关键技术之一，在频谱资源管理、干扰抑制和认知无线电等应用中具有重要意义。虽然深度学习极大地提高了自动调制识别（AMR）的性能，但它严重依赖大量的标注数据。鉴于高标注成本和隐私问题，研究利用现成的未标注数据进行训练的半监督AMR方法具有重要意义。本研究构建了一种基于双学生的半监督AMR方法。具体来说，我们首先采用双分支协同训练架构来充分利用未标注数据并有效学习深度特征表示。然后，我们使用强增强和弱增强策略开发一个动态稳定性评估模块，以提高生成伪标签的准确性。最后，基于双学生半监督框架和伪标签稳定性评估，我们提出一种稳定性引导的一致性正则化约束方法并进行半监督AMR模型训练。实验结果表明，所提出的DualBranch-AMR方法在基准数据集上显著优于传统的监督基线方法。仅使用5%的标注数据，它就实现了55.84%的识别准确率，达到了全监督训练性能的90%以上。这验证了所提出方法在半监督条件下的优越性。
