Home > Published Issues > 2022 > Volume 17, No. 12, December 2022 >

Accuracy Enhancement of Automatic Modulation Recognition Using Deep Learning Paradigm

Salah Ayad Jassim and Ibrahim Khider
Sudan University of Science and Technology, College of Engineering, Dept of Electronics, Sudan

Abstract—Communication systems consist of advanced system performance that enables signal reception at the destination. In such a system, the difficult problem is to restore the original transmission. In this study, Automatic Modulation Recognition (AMR) is used to improve the precision of modulation recognition. This method is essential for advanced communication systems that require a minimal delay, such as Realtime broadcasting. Using paradigms of deep learning, the modulation approach of a received signal is identified. Feedforward neural network with Particle Swarm Optimization (PSO) integration is proposed for this purpose. The suggested model exhibits optimal recognition accuracy of 97.3 percent, as reported.
 
Index Terms—Modulation, Automatic Modulation Classification (AMC), Particle Swarm Optimization (PSO), FFNN, Convolutional Neural Network (CNN), AWGN (Additive White Gaussian Noise), deep learning

Cite: Salah Ayad Jassim and Ibrahim Khider, "Accuracy Enhancement of Automatic Modulation Recognition Using Deep Learning Paradigm," Journal of Communications vol. 17, no. 12, pp. 979-984, December 2022. Doi: 10.12720/jcm.17.12.979-984

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.

PREVIOUS PAPER
Quantum Encryption and Decryption in IBMQ Systems using Quantum Permutation Pad
NEXT PAPER
A Virtual Projection-Based Incentive Routing Protocol for Mobile PFNs in Wireless Sensor Networks