Modulation recognition method based on multiscale convolutional fusion coding networks

To address the issue of insufficient feature extraction in existing modulation recognition methods that limited classification accuracy, a Transformer-based modulation recognition method was proposed. Convolutional kernels of varying sizes were employed to enhance multi-scale signal feature extracti...

Full description

Saved in:
Bibliographic Details
Main Authors: LI Guojun, ZHU Siyuan, ZHENG Jianzhong, WANG Jie, YE Changrong
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2025-01-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025137/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849227164862382080
author LI Guojun
ZHU Siyuan
ZHENG Jianzhong
WANG Jie
YE Changrong
author_facet LI Guojun
ZHU Siyuan
ZHENG Jianzhong
WANG Jie
YE Changrong
author_sort LI Guojun
collection DOAJ
description To address the issue of insufficient feature extraction in existing modulation recognition methods that limited classification accuracy, a Transformer-based modulation recognition method was proposed. Convolutional kernels of varying sizes were employed to enhance multi-scale signal feature extraction, followed by feature fusion to strengthen learning capability while reducing computational demands. A multi-head self-attention mechanism was utilized to enable parallel processing for capturing diverse signal characteristics. A dual-branch multilayer perceptron structure was introduced to further improve adaptability and diversity learning while accelerating operational speed. Experimental results demonstrated the model's robust stability and generalization capability, showing minimal performance variation under different test batch sizes with fixed training batches. On the RML2018.01A dataset, the proposed model achieve over 96% classification accuracy at 10 dB.
format Article
id doaj-art-842e92169f324f8f945aedd8f77681e5
institution Kabale University
issn 1000-436X
language zho
publishDate 2025-01-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-842e92169f324f8f945aedd8f77681e52025-08-23T19:00:08ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-01-01112123248161Modulation recognition method based on multiscale convolutional fusion coding networksLI GuojunZHU SiyuanZHENG JianzhongWANG JieYE ChangrongTo address the issue of insufficient feature extraction in existing modulation recognition methods that limited classification accuracy, a Transformer-based modulation recognition method was proposed. Convolutional kernels of varying sizes were employed to enhance multi-scale signal feature extraction, followed by feature fusion to strengthen learning capability while reducing computational demands. A multi-head self-attention mechanism was utilized to enable parallel processing for capturing diverse signal characteristics. A dual-branch multilayer perceptron structure was introduced to further improve adaptability and diversity learning while accelerating operational speed. Experimental results demonstrated the model's robust stability and generalization capability, showing minimal performance variation under different test batch sizes with fixed training batches. On the RML2018.01A dataset, the proposed model achieve over 96% classification accuracy at 10 dB.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025137/convolutional neural networkmodulation classificationTransformermulti-scale fusionmultilayer perceptron
spellingShingle LI Guojun
ZHU Siyuan
ZHENG Jianzhong
WANG Jie
YE Changrong
Modulation recognition method based on multiscale convolutional fusion coding networks
Tongxin xuebao
convolutional neural network
modulation classification
Transformer
multi-scale fusion
multilayer perceptron
title Modulation recognition method based on multiscale convolutional fusion coding networks
title_full Modulation recognition method based on multiscale convolutional fusion coding networks
title_fullStr Modulation recognition method based on multiscale convolutional fusion coding networks
title_full_unstemmed Modulation recognition method based on multiscale convolutional fusion coding networks
title_short Modulation recognition method based on multiscale convolutional fusion coding networks
title_sort modulation recognition method based on multiscale convolutional fusion coding networks
topic convolutional neural network
modulation classification
Transformer
multi-scale fusion
multilayer perceptron
url http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025137/
work_keys_str_mv AT liguojun modulationrecognitionmethodbasedonmultiscaleconvolutionalfusioncodingnetworks
AT zhusiyuan modulationrecognitionmethodbasedonmultiscaleconvolutionalfusioncodingnetworks
AT zhengjianzhong modulationrecognitionmethodbasedonmultiscaleconvolutionalfusioncodingnetworks
AT wangjie modulationrecognitionmethodbasedonmultiscaleconvolutionalfusioncodingnetworks
AT yechangrong modulationrecognitionmethodbasedonmultiscaleconvolutionalfusioncodingnetworks