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:在许多现代软件定义的无线电中,自动调制分类是一个理想的特征。近年来,为对观测到的信号暴中使用的调制进行自动分类,提出了若干革命性的深层学习结构,然而,尚未对这些不同的结构以及每个设计要素的重要性进行全面分析。因此,不清楚这些变压神经网络的不同设计之间有何平衡。在这项研究中,我们调查了自动调制分类的许多结构,并进行了全面的调控研究,以调查各种超参数和设计要素对自动调制分类性能的影响。我们表明,利用研究过的设计要素中的一组可以实现新的性能状态。特别是,我们表明,变相共变、统计数据汇集和挤压和喷雾装置的组合导致最强的分解器。我们进一步根据各种其他标准调查这一最佳表现,包括短信号暴发、常见的分类以及不同调制类别和模式的性能。