Yao Xiaohui, Yang Honghui, Sheng Meiping
School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an 710072, China.
Entropy (Basel). 2023 Jul 21;25(7):1096. doi: 10.3390/e25071096.
Automatic modulation classification (AMC) of underwater acoustic communication signals is of great significance in national defense and marine military. Accurate modulation classification methods can make great contributions to accurately grasping the parameters and characteristics of enemy communication systems. While a poor underwater acoustic channel makes it difficult to classify the modulation types correctly. Feature extraction and deep learning methods have proven to be effective methods for the modulation classification of underwater acoustic communication signals, but their performance is still limited by the complex underwater communication environment. Graph convolution networks (GCN) can learn the graph structured information of the data, making it an effective method for processing structured data. To improve the stability and robustness of AMC in underwater channels, we combined the feature extraction and deep learning methods by fusing the multi-domain features and deep features using GCN. The proposed method takes the relationships among the different multi-domain features and deep features into account. Firstly, a feature graph was built using the properties of the features. Secondly, multi-domain features were extracted from the received signals and deep features were extracted from the signals using a deep neural network. Thirdly, we constructed the input of GCN using these features and the graph. Then, the multi-domain features and deep features were fused by the GCN. Finally, we classified the modulation types using the output of GCN by way of a softmax layer. We conducted the experiments on a simulated dataset and a real-world dataset, respectively. The results show that the AMC based on GCN can achieve a significant improvement in performance compared to the current state-of-the-art methods. Our approach is robust in underwater acoustic channels.
水声通信信号的自动调制分类（AMC）在国防和海洋军事领域具有重要意义。准确的调制分类方法有助于准确掌握敌方通信系统的参数和特性。然而，恶劣的水声信道使得正确分类调制类型变得困难。特征提取和深度学习方法已被证明是水声通信信号调制分类的有效方法，但其性能仍受复杂水下通信环境的限制。图卷积网络（GCN）可以学习数据的图结构信息，使其成为处理结构化数据的有效方法。为了提高水下信道中AMC的稳定性和鲁棒性，我们通过使用GCN融合多域特征和深度特征，将特征提取和深度学习方法相结合。所提方法考虑了不同多域特征和深度特征之间的关系。首先，利用特征的属性构建特征图。其次，从接收信号中提取多域特征，并使用深度神经网络从信号中提取深度特征。第三，利用这些特征和图构建GCN的输入。然后，通过GCN融合多域特征和深度特征。最后，通过softmax层利用GCN的输出对调制类型进行分类。我们分别在模拟数据集和真实数据集上进行了实验。结果表明，与当前最先进的方法相比，基于GCN的AMC在性能上有显著提升。我们的方法在水声信道中具有鲁棒性。
