Modulation Classification Based on Signal Constellation Diagrams and Deep Learning

TLDR

Deep learning, a powerful machine‑learning technique, has succeeded in many fields but its application to communications—particularly modulation classification—remains underexplored, despite the abundance of data and its advantage of eliminating manual feature selection. This paper investigates the use of deep learning for modulation classification, a key task in communications systems. The authors employ AlexNet and GoogLeNet CNNs, converting modulated signals into grid‑like image representations, and evaluate how different representations affect classification accuracy while benchmarking against conventional cumulant‑based and machine‑learning algorithms. Experiments show that the deep‑learning approach markedly outperforms traditional methods and is feasible for practical modulation classification.

Abstract

Deep learning (DL) is a new machine learning (ML) methodology that has found successful implementations in many application domains. However, its usage in communications systems has not been well explored. This paper investigates the use of the DL in modulation classification, which is a major task in many communications systems. The DL relies on a massive amount of data and, for research and applications, this can be easily available in communications systems. Furthermore, unlike the ML, the DL has the advantage of not requiring manual feature selections, which significantly reduces the task complexity in modulation classification. In this paper, we use two convolutional neural network (CNN)-based DL models, AlexNet and GoogLeNet. Specifically, we develop several methods to represent modulated signals in data formats with gridlike topologies for the CNN. The impacts of representation on classification performance are also analyzed. In addition, comparisons with traditional cumulant and ML-based algorithms are presented. Experimental results demonstrate the significant performance advantage and application feasibility of the DL-based approach for modulation classification.