Symbol denoising in high order M-QAM using residual learning of deep CNN

Khan, Saud, Khan, Komal S., and Shin, Soo Young (2019) Symbol denoising in high order M-QAM using residual learning of deep CNN. In: Proceedings of the 16th IEEE Annual Consumer Communications & Networking Conference. 8651830. From: CCNC 2019: 16th IEEE Annual Consumer Communications & Networking Conference, 11-14 January 2019, Las Vegas, NV, USA.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1109/CCNC.2019.865183...
 
8
1


Abstract

This paper presents an integrating concept of de-noising convolutional neural networks (DnCNN) with quadrature amplitude modulation (QAM) for symbol denoising. DnCNN is used to estimate and denoise the Gaussian noise from the received constellation symbols of QAM with an unknown noise level. The proposed system shows a significant gain in terms of peak signal-to-noise ratio, system throughput and bit-error-rate; in comparison with conventional QAM systems. The basic concept, system-level integration, and simulated performance gains are presented to elucidate the concept.

Item ID: 66220
Item Type: Conference Item (Research - E1)
ISBN: 978-1-5386-5553-5
Keywords: Convolutional neural networks, Quadrature amplitude modulation, Symbol denoising
Copyright Information: (C) IEEE
Funders: National Research Foundation of Korea (NRF)
Projects and Grants: NRF 2018R1A61A303024003
Date Deposited: 18 Mar 2021 03:25
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461104 Neural networks @ 60%
40 ENGINEERING > 4006 Communications engineering > 400602 Data communications @ 40%
SEO Codes: 22 INFORMATION AND COMMUNICATION SERVICES > 2201 Communication technologies, systems and services > 220103 Mobile technologies and communications @ 60%
22 INFORMATION AND COMMUNICATION SERVICES > 2204 Information systems, technologies and services > 220499 Information systems, technologies and services not elsewhere classified @ 40%
Downloads: Total: 1
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page