Deep learning has recently been successfully applied in automatic modulation classification by extracting and classifying radio features in an end-to-end way. However, deep learning-based radio modulation classifiers are lacking interpretability, and there is little explanation or visibility into what kinds of radio features are extracted and chosen for classification. In this article, we visualize different deep learning-based radio modulation classifiers by introducing a class activation vector. Specifically, both convolutional neural networks (CNN) based classifier and long short-term memory (LSTM) based classifier are separately studied, and their extracted radio features are visualized. We explore different hyperparameter settings via extensive numerical evaluations and show both the CNN-based classifier and LSTM-based classifiers extract similar radio features relating to modulation reference points. In particular, for the LSTM-based classifier, its obtained radio features are similar to the knowledge of human experts. Our numerical results indicate the radio features extracted by deep learning-based classifiers greatly depend on the contents carried by radio signals, and a short radio sample may lead to misclassification.

中文翻译：

---

可视化基于深度学习的无线电调制分类器


深度学习最近通过以端到端的方式提取和分类无线电特征，成功应用于自动调制分类。然而，基于深度学习的无线电调制分类器缺乏可解释性，并且对于提取和选择何种无线电特征进行分类几乎没有解释或可见性。在本文中，我们通过引入类激活向量来可视化不同的基于深度学习的无线电调制分类器。具体来说，分别研究了基于卷积神经网络（CNN）的分类器和基于长短期记忆（LSTM）的分类器，并将它们提取的无线电特征可视化。我们通过广泛的数值评估探索了不同的超参数设置，并表明基于 CNN 的分类器和基于 LSTM 的分类器都提取了与调制参考点相关的类似无线电特征。特别是，对于基于 LSTM 的分类器，其获得的无线电特征与人类专家的知识相似。我们的数值结果表明，基于深度学习的分类器提取的无线电特征很大程度上取决于无线电信号携带的内容，而短的无线电样本可能会导致错误分类。