Automatic Modulation Classification: Convolutional Deep Learning Neural Networks Approaches

Abstract

In this study, automatic modulation classification (AMC), a key part of both civilian and military applications, is looked at using a deep learning method .A lot of research has been done on feature-based (FB) AM algorithms in particular. In this paper, a robust AMC strategy based on convolutional neural networks (CNN) is proposed to solve the issue that current FB AMC methods frequently target a small set of modulations and lack generalisation capability. In total, 11 different modulation types are taken into consideration. Conventional AMCs can be categorised into maximum likelihood (ML)-based (ML-AMC) and feature-based AMCs. This paper proposes a robust convolutional neural network (CNN)-based automatic modulation classification (AMC) technique. The recommended method may automatically identify the characteristics of the incoming signals and classify them without the need for feature extraction. A comparison study was done for the proposed CNN-based AMCs with two different optimizers at two different signal-to-noise ratios to select the best one of them based on performance.