Modulation Classifier Based on Deep Learning for Beyond 5G Communications

Abstract

In order to stay under a certain block error rate, a fourth generation (4G) or fifth generation (5G) base station chooses the proper modulation and coding scheme based on the channel condition. Beyond 5G (B5G) communications will enable the receiver to receive a signal from a wider range of sources in the future. Consequently, a real-time system is required to recognize and categorize the kind of modulation on the receiver's end. Automatic Modulation Classification (AMC) involves identifying the modulation scheme used in a signal received by communication systems. Recently, deep learning, a method in the field of machine learning, has received considerable attention due to its remarkable ability to categorize complex data patterns. This research investigates the applications of automatic modulation classification using Convolutional Neural Networks (CNNs) as a deep learning method in both civilian and military domains. In this study, the effectiveness of this deep learning methodology in modulation classification is evaluated using the RadioML.2016a dataset. The performance of the developed deep neural network structure is analyzed using different hyperparameters and data formats.