| This Paper:Browse 176 Download 96 |
|
| 基于射频指纹多分辨率特征融合的辐射源个体识别方法 |
| 余江,陈川,贾勇,姚光乐,王琛,张喜娟,陈亚锋 |
|
|
| (1.成都理工大学 a.机电工程学院;b.计算机与网络安全学院,成都 610059;2.成都飞机工业集团有限责任公司，成都 610073;3.四川酷比通信设备有限公司,成都 644000) |
|
| 摘要: |
| 针对辐射源分类任务存在的特征信息表达有限和分类精度低等问题，提出了一种基于多分辨率特征融合的辐射源个体识别方法。该方法利用短时傅里叶变换3种不同分辨率的时频域谱图表达辐射源个体特征。使用ResNext50构建多通道卷积神经网络，提取不同时频分辨率的特征。在网络中引入多通道特征加权融合机制，对不同通道的特征进行加权融合，组合不同分辨率下的特征信息。实验证明，这种方法提升了辐射源信号的细微指纹信息表达能力,相比特征层融合方法和单一特征表达方法两种方法，识别准确率分别提升2.15%和6.8%。 |
| 关键词: 辐射源个体识别 射频指纹 多分辨率特征融合 短时傅里叶变换 |
| DOI：10.20079/j.issn.1001-893x.240806002 |
|
| 基金项目:国家自然科学基金资助项目（U20B2070；四川省重点研发项目（2022YFS0531;成都市“揭榜挂帅”科技项目（2023-JB00-00023-GX |
|
| Individual Radiation Source Recognition Based on Multi-resolution Fusion of Radio Frequency Fingerprints |
| YU Jianga,CHEN Chuana,JIA Yonga,YAO Guangleb,WANG Chenb,ZHANG Xijuan,CHENG Yafeng |
| (1a.School of Mechanical and Electrical Engineering;1b.School of Computer and Cyber Security,Chengdu University of Technology,Chengdu 610059,China;2.Chengdu Aircraft IndustrialGroup Co.,Ltd,Chengdu 610073,China;3.Sichuan Koobee Communication Company Limited,Chengdu 644000,China) |
| Abstract: |
| For the problems of limited expression of characteristic information and low classification accuracy in radiation source classification tasks,an individual radiation source recognition method based on multi-resolution feature fusion is proposed.In this method,the individual characteristics of the radiation source are expressed by using three time-frequency spectra with different resolutions obtained through the Short-Time Fourier Transform.Multi-channel convolutional neural networks are constructed using ResNext50 to extract features with different time-frequency resolutions.A multi-channel feature weighted fusion mechanism is introduced into the network,and the features of different channels are fused by feature weighted fusion,combining the feature information from different resolutions.Experiments show that this method improves the ability to express the subtle fingerprint information of the radiation source signal,and compared with that of the feature layer fusion method and the single feature expression method,the recognition accuracy is improved by 2.15% and 6.8%,respectively. |
| Key words: individual radiation source recognition RF fingerprint multi-resolution feature fusion short-time Fourier transform |
