通信学报2026，Vol.47Issue(2)：46-60,15.DOI:10.11959/j.issn.1000-436x.2026029
基于时序注意力的不平衡辐射源个体识别方法
Method for imbalanced specific emitter identification based on temporal attention
摘要
Abstract
To address the problems of prominent long-tailed data distribution and high-dimensional sampling features in specific emitter identification(SEI),an improved SEI algorithm based on temporal attention was proposed.By construct-ing a multi-scale feature fusion module to integrate feature information under different temporal granularities,and de-signing an identity-aware temporal attention module that generates and embeds identity-adaptive attention weights,the model was encouraged to focus on individuals with a small number of tail samples and identity-related temporal features.Experiments on the self-collected AIS dataset and public ADS-B dataset demonstrate that the proposed algorithm achieves recognition accuracies of 94.89%and 93.23%respectively,and the accuracy decreases by less than 2%under a low signal-to-noise ratio(SNR)of 3 dB.关键词
辐射源个体识别/长尾分布/时序注意力/IQ信号/特征学习Key words
specific emitter identification/long-tailed distribution/temporal attention/IQ signal/feature learning分类
信息技术与安全科学引用本文复制引用
高龙,吕友彬,王甍娇,张威,李湉雨,徐从安..基于时序注意力的不平衡辐射源个体识别方法[J].通信学报,2026,47(2):46-60,15.基金项目
国家资助博士后人员计划基金资助项目(No.GZC20233554) （No.GZC20233554）
国家自然科学基金资助项目(No.62271499) （No.62271499）
山东省泰山学者基金资助项目(No.tsqn202312258) The National Funded Postdoctoral Program(No.GZC20233554),The National Natural Science Foundation of China(No.62271499),The Taishan Scholar(No.tsqn202312258) （No.tsqn202312258）
