Wireless Communication Project Modulation Classification using Deep Learning

Wireless Communication Project Modulation Classification using Deep Learning

MATLABSolutions demonstrate how to use the MATLAB software for simulation of This paper represents the Wireless Communication Project Modulation Classification using Deep Learning. Deep learning (DL) is a powerful classification technique that has great success in many application domains.

Abstract

Deep learning (DL) is a powerful classification technique that has great success in many application domains. However, its usage in communication systems has not been well explored. In this paper, we address the issue of using DL in communication systems, especially for modulation classification. Convolutional neural network (CNN) is utilized to complete the classification task. We convert the raw modulated signals into images that have a grid-like topology and feed them to CNN for network training. Two existing approaches, including cumulant and support vector machine (SVM) based classification algorithms, are involved for performance comparison. Simulation results indicate that the proposed CNN based modulation clas- sification approach achieves comparable classification accuracy without the necessity of manual feature selection.

Introduction

Deep learning (DL) is a branch of machine learning (ML) that has state-of-the-art capability for classification. Re- cently, it has attracted great attention and been applied in various fields. During the competition of ImageNet Large Scale Visual Recognition Challenge (ILSVRC), many research teams submitted various DL algorithms for object detection and image classification, and the latest top-5 accuracy of identifying objects from 1000 categories reaches 95%. In, the authors show that DL network can be trained to implement accurate, inexpensive and scalable economics survey with satellite imagery in developing countries. More- over, bioinformatics can also benefit from DL. Splice junctions can be discovered from DNA sequences, finger joints can be recognized from X-ray images, lapses can be detected from electroencephalography signals, and so on.

Although DL is flourishing everywhere, communications field seems to be an exception. It is noticed that some traditional ML algorithms, e.g., Supported Vector Machine (SVM) and K-Nearest Neighbor (KNN), have been utilized for media access control (MAC) protocol identification and modulation classification. In this paper, we focus on the issue of using DL in communications systems, especially for modulation classification.

The use of DL in communications systems has multiple advantages. Firstly, because of the huge amount of communi- cations devices and the high communications data rate, massive data, which is required by DL, are available in communications systems. Secondly, DL is able to extract features autonomously and avoids the challenging task of manual feature selection. Thirdly, since DL is evolving rapidly, there will be considerable potential to other communications applications besides modulation classification.