Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network

With the rapid development of 釭tificial intelligence, convolutional neural network is more and more applied to the field of communication signal modulation recognition. Aiming at the problem of low recognition accuracy of digital signals at low SNR, a modulation recognition model named lnceptionresn...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Ai-li, ZHANG Jia-wei, JIANG Kai-yuan, WU Hai一bin, Yuji Iwahori
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2021-10-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2020
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849249072573054976
author WANG Ai-li
ZHANG Jia-wei
JIANG Kai-yuan
WU Hai一bin
Yuji Iwahori
author_facet WANG Ai-li
ZHANG Jia-wei
JIANG Kai-yuan
WU Hai一bin
Yuji Iwahori
author_sort WANG Ai-li
collection DOAJ
description With the rapid development of 釭tificial intelligence, convolutional neural network is more and more applied to the field of communication signal modulation recognition. Aiming at the problem of low recognition accuracy of digital signals at low SNR, a modulation recognition model named lnceptionresnetV2-TA was studied by combining InceptionresnetV2 network with migration adaptation to identify the modulation mode of MPSK signals. The results show that when the SNR is 3d8, the recognition rate of InceptionresnetV2-TA for BPSK is 99. 33%, which is 3% higher than that of the suboptimal model lnceptionresnetV2. The recognition rate of QPSK is 95. 33% , which is 2% higher than lnceptionresnetV2. The recognition rate of 8PSK is 86. 33% , which is 5% higher than that of Inceptionresnetv2. The above results indicate that InceptionresnetV2-TA combined with migration adaptation has higher identification accuracy of BPSK, QPSK and 8PSK at low SNR than other comparison methods. At the same time, the validity of the modulation recognition model is verified.
format Article
id doaj-art-4ae52b24ef304de7a66ea14fdd729a21
institution Kabale University
issn 1007-2683
language zho
publishDate 2021-10-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-4ae52b24ef304de7a66ea14fdd729a212025-08-20T03:57:40ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832021-10-0126059710310.15938/j.jhust.2021.05.013Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network WANG Ai-li0ZHANG Jia-wei1JIANG Kai-yuan2WU Hai一bin3Yuji Iwahori4School of Measurement-Conlrol Technology and Communication Engineering, Harbin Unive1-sity of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Conlrol Technology and Communication Engineering, Harbin Unive1-sity of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Conlrol Technology and Communication Engineering, Harbin Unive1-sity of Science and Technology, Harbin 150080, ChinaSchool of Measurement-Conlrol Technology and Communication Engineering, Harbin Unive1-sity of Science and Technology, Harbin 150080, ChinaDepartment of Computer Science, Chubu University, Aichi 487-8501, JapanWith the rapid development of 釭tificial intelligence, convolutional neural network is more and more applied to the field of communication signal modulation recognition. Aiming at the problem of low recognition accuracy of digital signals at low SNR, a modulation recognition model named lnceptionresnetV2-TA was studied by combining InceptionresnetV2 network with migration adaptation to identify the modulation mode of MPSK signals. The results show that when the SNR is 3d8, the recognition rate of InceptionresnetV2-TA for BPSK is 99. 33%, which is 3% higher than that of the suboptimal model lnceptionresnetV2. The recognition rate of QPSK is 95. 33% , which is 2% higher than lnceptionresnetV2. The recognition rate of 8PSK is 86. 33% , which is 5% higher than that of Inceptionresnetv2. The above results indicate that InceptionresnetV2-TA combined with migration adaptation has higher identification accuracy of BPSK, QPSK and 8PSK at low SNR than other comparison methods. At the same time, the validity of the modulation recognition model is verified. https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2020modulation recognitionconvolutional neural nehvorktransfer adaptationlnceptionresnetv2
spellingShingle WANG Ai-li
ZHANG Jia-wei
JIANG Kai-yuan
WU Hai一bin
Yuji Iwahori
Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
Journal of Harbin University of Science and Technology
modulation recognition
convolutional neural nehvork
transfer adaptation
lnceptionresnetv2
title Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
title_full Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
title_fullStr Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
title_full_unstemmed Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
title_short Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
title_sort modulation recognition of mpsk signals based on novel convolutional neural network
topic modulation recognition
convolutional neural nehvork
transfer adaptation
lnceptionresnetv2
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2020
work_keys_str_mv AT wangaili modulationrecognitionofmpsksignalsbasedonnovelconvolutionalneuralnetwork
AT zhangjiawei modulationrecognitionofmpsksignalsbasedonnovelconvolutionalneuralnetwork
AT jiangkaiyuan modulationrecognitionofmpsksignalsbasedonnovelconvolutionalneuralnetwork
AT wuhaiyībin modulationrecognitionofmpsksignalsbasedonnovelconvolutionalneuralnetwork
AT yujiiwahori modulationrecognitionofmpsksignalsbasedonnovelconvolutionalneuralnetwork