An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks
Recently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. Ho...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | http://www.mdpi.com/2076-3417/9/5/1010 |
_version_ | 1811277589600272384 |
---|---|
author | Mingxuan Li Ou Li Guangyi Liu Ce Zhang |
author_facet | Mingxuan Li Ou Li Guangyi Liu Ce Zhang |
author_sort | Mingxuan Li |
collection | DOAJ |
description | Recently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. However, the errors introduced during signal reception and processing will greatly deteriorate the classification performance, which affects the practical application of such methods. Therefore, we first analyze and quantify the errors introduced by signal detection and isolation in noncooperative communication through a baseline convolution neural network. In response to these errors, we then design a signal spatial transformer module based on the attention model to eliminate errors by a priori learning of signal structure. By cascading a signal spatial transformer module in front of the baseline classification network, we propose a method that can adaptively resample the signal capture to adjust time drift, symbol rate, and clock recovery. Besides, it can also automatically add a perturbation on the signal carrier to correct frequency offset. By applying this improved model to automatic modulation recognition, we obtain a significant improvement in classification performance compared with several existing methods. Our method significantly improves the prospect of the application of automatic modulation recognition based on deep learning under nonideal synchronization. |
first_indexed | 2024-04-13T00:18:21Z |
format | Article |
id | doaj.art-d63068ff4fd34b8ba2eaec585ba239d5 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-13T00:18:21Z |
publishDate | 2019-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-d63068ff4fd34b8ba2eaec585ba239d52022-12-22T03:10:51ZengMDPI AGApplied Sciences2076-34172019-03-0195101010.3390/app9051010app9051010An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer NetworksMingxuan Li0Ou Li1Guangyi LiuCe Zhang2PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaRecently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. However, the errors introduced during signal reception and processing will greatly deteriorate the classification performance, which affects the practical application of such methods. Therefore, we first analyze and quantify the errors introduced by signal detection and isolation in noncooperative communication through a baseline convolution neural network. In response to these errors, we then design a signal spatial transformer module based on the attention model to eliminate errors by a priori learning of signal structure. By cascading a signal spatial transformer module in front of the baseline classification network, we propose a method that can adaptively resample the signal capture to adjust time drift, symbol rate, and clock recovery. Besides, it can also automatically add a perturbation on the signal carrier to correct frequency offset. By applying this improved model to automatic modulation recognition, we obtain a significant improvement in classification performance compared with several existing methods. Our method significantly improves the prospect of the application of automatic modulation recognition based on deep learning under nonideal synchronization.http://www.mdpi.com/2076-3417/9/5/1010deep learningautomatic modulation recognitionspatial transformer networkssignal processing |
spellingShingle | Mingxuan Li Ou Li Guangyi Liu Ce Zhang An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks Applied Sciences deep learning automatic modulation recognition spatial transformer networks signal processing |
title | An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks |
title_full | An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks |
title_fullStr | An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks |
title_full_unstemmed | An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks |
title_short | An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks |
title_sort | automatic modulation recognition method with low parameter estimation dependence based on spatial transformer networks |
topic | deep learning automatic modulation recognition spatial transformer networks signal processing |
url | http://www.mdpi.com/2076-3417/9/5/1010 |
work_keys_str_mv | AT mingxuanli anautomaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT ouli anautomaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT guangyiliu anautomaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT cezhang anautomaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT mingxuanli automaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT ouli automaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT guangyiliu automaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks AT cezhang automaticmodulationrecognitionmethodwithlowparameterestimationdependencebasedonspatialtransformernetworks |