| 113 | 1 | 132 |
| 下载次数 | 被引频次 | 阅读次数 |
调制识别是无线通信中的关键任务，深度学习方法虽已取得显著进展，但在复杂非合作环境下仍面临泛化能力不足的挑战。特别是，变化的信道条件会模糊结构相似的调制方式(如16QAM与64QAM)之间细微的判别性特征，导致识别性能下降。针对这一调制识别领域的特有挑战，提出特征对齐对抗领域自适应(Feature Alignment and Discrimination Domain Adaptation, FADDA)的无监督对抗领域自适应算法。该方法的核心是在对抗训练的基础上，创新性地引入了基于对比学习的特征对齐损失。对抗训练负责学习域不变特征以适应信道变化，特征对齐损失则通过显式地增强类内特征的紧凑性和类间特征的可分性，从而在根本上提升模型对易混淆调制类型的分辨能力。实验验证表明，该方法在缺乏目标域标签的情况下，能够显著增强模型的跨信道调制识别性能，展现出强大的泛化能力。
Abstract：Modulation recognition is a critical task in wireless communications. Although deep learning methods have achieved remarkable progress in this field, they still face the challenge of insufficient generalization ability in complex non-cooperative environments—particularly when confronted with varying channel conditions, which can obscure the subtle discriminative features between structurally similar modulation schemes(e.g.16QAM and 64QAM) and thus degrade recognition performance. To address this unique challenge in the field of modulation recognition, an unsupervised adversarial domain adaptation method named Feature Alignment and Discrimination Domain Adaptation(FADDA) is proposed. The core of FADDA is the introduction of a contrastive learning-based feature alignment loss on the basis of adversarial training.Adversarial training is responsible for learning domain-invariant features to adapt to channel variations, while the feature alignment.loss fundamentally enhances the model's ability to distinguish between easily confused modulation types by explicitly reinforcing the compactness of intra-class features and the separability of inter-class features.Experimental results show that without target-domain labels, this method can significantly improve the model's cross-channel modulation recognition performance and demonstrate strong generalization ability.
[1] SAAD W,BENNIS M,CHEN M Z.A Vision of 6G Wireless Systems:Applications,Trends,Technologies,and Open Research Problems[J].IEEE Network,2019,34(3):134-142.
[2] LETAIEF K B,CHEN W,SHI Y M,et al.The Roadmap to 6G:AI Empowered Wireless Networks[J].IEEE Communications Magazine,2019,57(8):84-90.
[3] ZHANG F X,LUO C B,XU J L,et al.Deep Learning Based Automatic Modulation Recognition:Models,Datasets,and Challenges[J].Digital Signal Processing,2022,129:103650.
[4] WANG Y,YANG J,LIU M,et al.LightAMC:Lightweight Automatic Modulation Classification via Deep Learning and Compressive Sensing[J].IEEE Transactions on Vehicular Technology,2020,69(3):3491-3495.
[5] HO K C,PROKOPIW W,CHAN Y T.Modulation Identification by the Wavelet Transform[C]//Proceedings of MILCOM'95.San Diego:IEEE,1995:886-890.
[6] 张文娜，孙运强，姚爱琴，等.基于高阶累积量的数字调制识别[J].国外电子测量技术，2022,41(7):126-132.
[7] 赵雄文，郭春霞，李景春.基于高阶累积量和循环谱的信号调制方式混合识别算法[J].电子与信息学报，2016,38(3):674-680.
[8] 孔豫京，黄焱，马金全.Alpha稳定分布噪声背景下衰落信号的调制识别方法[J].信号处理，2015,31(8):975-985.
[9] ZHOU R L,LIU F G,GRAVELLE C W.Deep Learning for Modulation Recognition:A Survey with a Demonstration[J].IEEE Access,2020,8:67366-67376.
[10] KUMAR Y,JAJOO G,YADAV S K.2D-FFT Based Modulation Classification Using Deep Convolution Neural Network[C]//2020 IEEE 17th India Council International Conference (INDICON).New Delhi:IEEE,2020:1-6.
[11] ZHANG R,HE C B,JING L Y,et al.A Modulation Recognition System for Underwater Acoustic Communication Signals Based on Higher-order Cumulants and Deep Learning[J].Journal of Marine Science and Engineering,2023,11(8):1632.
[12] 董聪，张传武，高勇.基于残差神经网络的通信混合信号识别[J].无线电工程，2020,50(9):727-731.
[13] 杨梓辰，笪清安，李思照.面向深度学习模型的对抗攻击与防御综述[J].无线电工程，2023,53(6):1328-1341.
[14] LIANG Z,XIE J,YANG X,et al.Self-training Based Adversarial Domain Adaptation for Radio Signal Recognition[J].IEEE Communications Letters,2022,26(11):2646-2650.
[15] ARBEL M,KORBA A,SALIM A,et al.Maximum Mean Discrepancy Gradient Flow[EB/OL].(2019-06-11)[2025-05-11].https://arxiv.org/abs/1906.04370.
[16] SUN B C,SAENKO K.Deep CORAL:Correlation Alignment for Deep Domain Adaptation[C]//European Conference on Computer Vision.Amsterdam:Springer,2016:443-450.
[17] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Nets[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.Montreal:ACM,2014:2672-2680.
[18] LONG M S,CAO Z J,WANG J M,et al.Conditional Adversarial Domain Adaptation[EB/OL].(2017-05-26)[2025-05-11].https://arxiv.org/abs/1705.10667.
基本信息:
中图分类号:TN911.3;TP18
引用信息:
[1]昌硕,胥顺,魏梅英.基于无监督领域自适应的调制识别算法[J].无线电工程,2025,55(11):2153-2162.
基金信息:
预先研究项目(D030307)~~