Automatic modulation classification is a desired feature in many modern software-defined radios. In recent years, a number of convolutional deep learning architectures have been proposed for automatically classifying the modulation used on observed signal bursts. However, a comprehensive analysis of these differing architectures and importance of each design element has not been carried out. Thus it is unclear what tradeoffs the differing designs of these convolutional neural networks might have. In this research, we investigate numerous architectures for automatic modulation classification and perform a comprehensive ablation study to investigate the impacts of varying hyperparameters and design elements on automatic modulation classification performance. We show that a new state of the art in performance can be achieved using a subset of the studied design elements. In particular, we show that a combination of dilated convolutions, statistics pooling, and squeeze-and-excitation units results in the strongest performing classifier. We further investigate this best performer according to various other criteria, including short signal bursts, common misclassifications, and performance across differing modulation categories and modes.

翻译：自动调制分类是许多现代软件定义无线电中的理想功能。近年来，已有多项卷积深度学习架构被提出用于自动识别观测信号突发所使用的调制方式。然而，针对这些不同架构及各设计要素重要性的全面分析尚未开展，因此不同卷积神经网络设计间的权衡仍不明确。本研究对多种自动调制分类架构进行了系统探究，并通过全面的消融实验分析了超参数及设计要素变化对自动调制分类性能的影响。研究表明，采用所研究设计要素的子集可实现新的最佳性能：具体而言，结合空洞卷积、统计池化与压缩-激励模块的分类器取得了最强性能。我们进一步根据短信号突发、常见误分类、不同调制类别及模式下的性能等多个准则，对该最优方案进行了深入分析。