Cargando…

EVM Loss: A Loss Function for Training Neural Networks in Communication Systems

Neural networks and their application in communication systems are receiving growing attention from both academia and industry. The authors note that there is a disconnect between the typical objective functions of these neural networks with regards to the context in which the neural network will ev...

Descripción completa

Detalles Bibliográficos
Autores principales: Stainton, Scott, Johnston, Martin, Dlay, Satnam, Haigh, Paul Anthony
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7915422/
https://www.ncbi.nlm.nih.gov/pubmed/33562553
http://dx.doi.org/10.3390/s21041094
_version_ 1783657235322241024
author Stainton, Scott
Johnston, Martin
Dlay, Satnam
Haigh, Paul Anthony
author_facet Stainton, Scott
Johnston, Martin
Dlay, Satnam
Haigh, Paul Anthony
author_sort Stainton, Scott
collection PubMed
description Neural networks and their application in communication systems are receiving growing attention from both academia and industry. The authors note that there is a disconnect between the typical objective functions of these neural networks with regards to the context in which the neural network will eventually be deployed and evaluated. To this end, a new loss function is proposed and shown to increase the performance of neural networks when implemented in a communication system compared to previous methods. It is further shown that a ‘split complex’ approach used by many implementations can be improved via formalisation of the ‘concatenated complex’ approach described herein. Experimental results using the orthogonal frequency division multiplexing (OFDM) and spectrally efficient frequency division multiplexing (SEFDM) modulation formats with varying bandwidth compression factors over a wireless visible light communication (VLC) link validate the efficacy of the proposed method in a real system, achieving the lowest error vector magnitude (EVM), and thus bit error rate (BER), across all experiments, with a 5 dB to 10 dB improvement in the received symbols EVM overall compared to the baseline implementation, with bandwidth compressions down to 40% compared to OFDM, resulting in a spectral efficiency gain of 67%.
format Online
Article
Text
id pubmed-7915422
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79154222021-03-01 EVM Loss: A Loss Function for Training Neural Networks in Communication Systems Stainton, Scott Johnston, Martin Dlay, Satnam Haigh, Paul Anthony Sensors (Basel) Communication Neural networks and their application in communication systems are receiving growing attention from both academia and industry. The authors note that there is a disconnect between the typical objective functions of these neural networks with regards to the context in which the neural network will eventually be deployed and evaluated. To this end, a new loss function is proposed and shown to increase the performance of neural networks when implemented in a communication system compared to previous methods. It is further shown that a ‘split complex’ approach used by many implementations can be improved via formalisation of the ‘concatenated complex’ approach described herein. Experimental results using the orthogonal frequency division multiplexing (OFDM) and spectrally efficient frequency division multiplexing (SEFDM) modulation formats with varying bandwidth compression factors over a wireless visible light communication (VLC) link validate the efficacy of the proposed method in a real system, achieving the lowest error vector magnitude (EVM), and thus bit error rate (BER), across all experiments, with a 5 dB to 10 dB improvement in the received symbols EVM overall compared to the baseline implementation, with bandwidth compressions down to 40% compared to OFDM, resulting in a spectral efficiency gain of 67%. MDPI 2021-02-05 /pmc/articles/PMC7915422/ /pubmed/33562553 http://dx.doi.org/10.3390/s21041094 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Communication
Stainton, Scott
Johnston, Martin
Dlay, Satnam
Haigh, Paul Anthony
EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title_full EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title_fullStr EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title_full_unstemmed EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title_short EVM Loss: A Loss Function for Training Neural Networks in Communication Systems
title_sort evm loss: a loss function for training neural networks in communication systems
topic Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7915422/
https://www.ncbi.nlm.nih.gov/pubmed/33562553
http://dx.doi.org/10.3390/s21041094
work_keys_str_mv AT staintonscott evmlossalossfunctionfortrainingneuralnetworksincommunicationsystems
AT johnstonmartin evmlossalossfunctionfortrainingneuralnetworksincommunicationsystems
AT dlaysatnam evmlossalossfunctionfortrainingneuralnetworksincommunicationsystems
AT haighpaulanthony evmlossalossfunctionfortrainingneuralnetworksincommunicationsystems