Automatic Modulation Classification in Deep Learning
Khawla A. Alnajjar, Sara Ghunaim, Sam Ansari
Abstract
Due to the evolution and availability of vast amounts of data for transferring, receiving, and detection, the field of signal recognition and modulation classification has become vital in various fields and applications. Additionally, the classical approaches to machine learning (ML) no more can satisfy the current needs. Hence, this urged researchers to apply deep learning (DL) algorithms that have a very strong ability to train, learn, and automatically classify types of modulation categories. This paper focuses on three vital DL network algorithms, which are deep neural networks (DNN), convolutional neural networks (CNN), and deep belief networks (DBN). The mentioned algorithms are widely used in many applications for automatic modulation classification/recognition (AMC/AMR). Additionally, an empirical study is performed in this paper to compare a large number of different methods for the performance and recognition percentage of each considered technique.