Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams

Signal-to-noise ratio (SNR) estimation is a fundamental task of spectrum management and data transmission. Existing methods for SNR estimation usually suffer from significant estimation errors when SNR is low. This paper proposes a deep learning (DL) based SNR estimation algorithm using constellatio...

Full description

Bibliographic Details
Main Authors: Xiaojuan Xie, Shengliang Peng, Xi Yang
Format: Article
Language:English
Published: Hindawi Limited 2020-01-01
Series:Mobile Information Systems
Online Access:http://dx.doi.org/10.1155/2020/8840340
id doaj-04e521e75c9a452e9c8505758c72e34e
record_format Article
spelling doaj-04e521e75c9a452e9c8505758c72e34e2021-07-02T12:57:01ZengHindawi LimitedMobile Information Systems1574-017X1875-905X2020-01-01202010.1155/2020/88403408840340Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation DiagramsXiaojuan Xie0Shengliang Peng1Xi Yang2College of Information Science and Engineering, Huaqiao University, Xiamen 361021, ChinaCollege of Information Science and Engineering, Huaqiao University, Xiamen 361021, ChinaCollege of Information Science and Engineering, Jishou University, Jishou 416000, ChinaSignal-to-noise ratio (SNR) estimation is a fundamental task of spectrum management and data transmission. Existing methods for SNR estimation usually suffer from significant estimation errors when SNR is low. This paper proposes a deep learning (DL) based SNR estimation algorithm using constellation diagrams. Since the constellation diagrams exhibit different patterns at different SNRs, the proposed algorithm achieves SNR estimation via constellation diagram recognition, which can be easily handled based on DL. Three DL networks, AlexNet, InceptionV1, and VGG16, are utilized for DL based SNR estimation. Experimental results show that the proposed algorithm always performs well, especially in low SNR scenarios.http://dx.doi.org/10.1155/2020/8840340
collection DOAJ
language English
format Article
sources DOAJ
author Xiaojuan Xie
Shengliang Peng
Xi Yang
spellingShingle Xiaojuan Xie
Shengliang Peng
Xi Yang
Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
Mobile Information Systems
author_facet Xiaojuan Xie
Shengliang Peng
Xi Yang
author_sort Xiaojuan Xie
title Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
title_short Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
title_full Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
title_fullStr Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
title_full_unstemmed Deep Learning-Based Signal-To-Noise Ratio Estimation Using Constellation Diagrams
title_sort deep learning-based signal-to-noise ratio estimation using constellation diagrams
publisher Hindawi Limited
series Mobile Information Systems
issn 1574-017X
1875-905X
publishDate 2020-01-01
description Signal-to-noise ratio (SNR) estimation is a fundamental task of spectrum management and data transmission. Existing methods for SNR estimation usually suffer from significant estimation errors when SNR is low. This paper proposes a deep learning (DL) based SNR estimation algorithm using constellation diagrams. Since the constellation diagrams exhibit different patterns at different SNRs, the proposed algorithm achieves SNR estimation via constellation diagram recognition, which can be easily handled based on DL. Three DL networks, AlexNet, InceptionV1, and VGG16, are utilized for DL based SNR estimation. Experimental results show that the proposed algorithm always performs well, especially in low SNR scenarios.
url http://dx.doi.org/10.1155/2020/8840340
work_keys_str_mv AT xiaojuanxie deeplearningbasedsignaltonoiseratioestimationusingconstellationdiagrams
AT shengliangpeng deeplearningbasedsignaltonoiseratioestimationusingconstellationdiagrams
AT xiyang deeplearningbasedsignaltonoiseratioestimationusingconstellationdiagrams
_version_ 1721329509677924352