通信学报2025，Vol.46Issue(8)：78-89,12.DOI:10.11959/j.issn.1000-436x.2025137
基于多尺度卷积融合编码网络的调制识别方法
Modulation recognition method based on multiscale convolutional fusion coding networks
摘要
Abstract
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 intro-duced 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 achieves over 96%classification accuracy at 10 dB.关键词
卷积神经网络/调制识别/Transformer/多尺度融合/多层感知器Key words
convolutional neural network/modulation classification/Transformer/multi-scale fusion/multilayer perceptron分类
信息技术与安全科学引用本文复制引用
李国军,朱思源,郑建忠,王杰,叶昌荣..基于多尺度卷积融合编码网络的调制识别方法[J].通信学报,2025,46(8):78-89,12.基金项目
国家自然科学基金资助项目(No.U22A2006,No.62201106) （No.U22A2006,No.62201106）
重庆市基础研究与前沿探索项目(No.cstc2021ycjh-bgzxm0072)The National Natural Science Foundation of China(No.U22A2006,No.62201106),The Chongqing Basic Re-search and Frontier Exploration Project(No.cstc2021ycjh-bgzxm0072) （No.cstc2021ycjh-bgzxm0072）
