信号处理2025，Vol.41Issue(3)：494-503,10.DOI:10.12466/xhcl.2025.03.007
基于多尺度特征融合提取的调制样式识别算法
Modulation Recognition Algorithm Based on Multi-Scale Feature Fusion Extraction
摘要
Abstract
Modulation recognition technology is a crucial component of communication signal reconnaissance,serving as an essential prerequisite for classifying and identifying unknown communication signals and extracting information.Exist-ing deep learning-based modulation recognition methods have poor feature extraction capabilities under low signal-to-noise ratio(SNR)conditions.To address this issue,this study proposes a signal modulation recognition algorithm based on multi-scale feature fusion extraction.The algorithm uses a multi-scale convolution module composed of multiple convolu-tion kernels of different sizes to extract multi-scale features of the signal and fuses these features through convolutional lay-ers to extract key features of the signal's modulation information.Then,a global feature extraction module composed of a multi-head attention mechanism is used to extract global features of the signal,and modulation recognition is achieved through average pooling layers and fully connected layers.To optimize the network parameters and computational complex-ity,this study proposes replacing the standard convolution with group convolution to simplify the model.Results from ex-periments on the RadioML2016.10a dataset show that the proposed method can accurately identify various modulation types,with recognition accuracy exceeding 95%for most modulation types under high SNR conditions.Compared to ex-isting neural network recognition methods,the proposed method improves the recognition rates by 1.47%to 7.26%.Under lower SNR conditions(-6 to 0 dB),it achieves an improvement of 4.73%to 9.09%,demonstrating better noise resis-tance.Additionally,using group convolution instead of standard convolution reduces the network parameters and computa-tional load by 38.9%and 54.9%,respectively,with minimal performance difference.An ablation study was designed to verify the performance improvement of each module in the proposed algorithm.Experimental results validate the effective-ness of the proposed algorithm in terms of recognition accuracy and noise resistance.关键词
调制样式识别/卷积神经网络/多头注意力机制/组卷积Key words
modulation recognition/convolutional neural network/multi-head attention mechanism/group convolution分类
信息技术与安全科学引用本文复制引用
杨嘉豪,张东坡,何劲..基于多尺度特征融合提取的调制样式识别算法[J].信号处理,2025,41(3):494-503,10.基金项目
国家自然科学基金重点项目(61934008) The State Key Program of National Natural Science Foundation of China(61934008) （61934008）
