An SNR Estimation Technique Based on Deep Learning
Signal-to-noise ratio (SNR) is a priori information necessary for many signal processing algorithms or techniques. However, there are many problems exsisting in conventional SNR estimation techniques, such as limited application range of modulation types, narrow effective estimation range of signal-...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-10-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/8/10/1139 |
id |
doaj-efc0ed39f6ef4f68923948bb4656a794 |
---|---|
record_format |
Article |
spelling |
doaj-efc0ed39f6ef4f68923948bb4656a7942020-11-24T22:08:49ZengMDPI AGElectronics2079-92922019-10-01810113910.3390/electronics8101139electronics8101139An SNR Estimation Technique Based on Deep LearningKai Yang0Zhitao Huang1Xiang Wang2Fenghua Wang3State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, National University of Defense Technology, Changsha 410073, ChinaSignal-to-noise ratio (SNR) is a priori information necessary for many signal processing algorithms or techniques. However, there are many problems exsisting in conventional SNR estimation techniques, such as limited application range of modulation types, narrow effective estimation range of signal-to-noise ratio, and poor ability to accommodate non-zero timing offsets and frequency offsets. In this paper, an SNR estimation technique based on deep learning (DL) is proposed, which is a non-data-aid (NDA) technique. Second and forth moment (M2M4) estimator is used as a benchmark, and experimental results show that the performance and robustness of the proposed method are better, and the applied ranges of modulation types is wider. At the same time, the proposed method is not only applicable to the baseband signal and the incoherent signal, but can also estimate the SNR of the intermediate frequency signal.https://www.mdpi.com/2079-9292/8/10/1139snr estimationdeep learningm2m4 estimatornda estimatordeep neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kai Yang Zhitao Huang Xiang Wang Fenghua Wang |
spellingShingle |
Kai Yang Zhitao Huang Xiang Wang Fenghua Wang An SNR Estimation Technique Based on Deep Learning Electronics snr estimation deep learning m2m4 estimator nda estimator deep neural network |
author_facet |
Kai Yang Zhitao Huang Xiang Wang Fenghua Wang |
author_sort |
Kai Yang |
title |
An SNR Estimation Technique Based on Deep Learning |
title_short |
An SNR Estimation Technique Based on Deep Learning |
title_full |
An SNR Estimation Technique Based on Deep Learning |
title_fullStr |
An SNR Estimation Technique Based on Deep Learning |
title_full_unstemmed |
An SNR Estimation Technique Based on Deep Learning |
title_sort |
snr estimation technique based on deep learning |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2019-10-01 |
description |
Signal-to-noise ratio (SNR) is a priori information necessary for many signal processing algorithms or techniques. However, there are many problems exsisting in conventional SNR estimation techniques, such as limited application range of modulation types, narrow effective estimation range of signal-to-noise ratio, and poor ability to accommodate non-zero timing offsets and frequency offsets. In this paper, an SNR estimation technique based on deep learning (DL) is proposed, which is a non-data-aid (NDA) technique. Second and forth moment (M2M4) estimator is used as a benchmark, and experimental results show that the performance and robustness of the proposed method are better, and the applied ranges of modulation types is wider. At the same time, the proposed method is not only applicable to the baseband signal and the incoherent signal, but can also estimate the SNR of the intermediate frequency signal. |
topic |
snr estimation deep learning m2m4 estimator nda estimator deep neural network |
url |
https://www.mdpi.com/2079-9292/8/10/1139 |
work_keys_str_mv |
AT kaiyang ansnrestimationtechniquebasedondeeplearning AT zhitaohuang ansnrestimationtechniquebasedondeeplearning AT xiangwang ansnrestimationtechniquebasedondeeplearning AT fenghuawang ansnrestimationtechniquebasedondeeplearning AT kaiyang snrestimationtechniquebasedondeeplearning AT zhitaohuang snrestimationtechniquebasedondeeplearning AT xiangwang snrestimationtechniquebasedondeeplearning AT fenghuawang snrestimationtechniquebasedondeeplearning |
_version_ |
1725814605176897536 |