引用本文: | 崔天舒,黄永辉,沈明,等.面向射频指纹识别的高效IQ卷积网络结构[J].国防科技大学学报,2022,44(4):180-189.[点击复制] |
CUI Tianshu,HUANG Yonghui,SHEN Ming,et al.High-efficiency IQ convolutional network structure for radio frequency fingerprint identification[J].Journal of National University of Defense Technology,2022,44(4):180-189[点击复制] |
|
|
|
本文已被:浏览 5026次 下载 3986次 |
面向射频指纹识别的高效IQ卷积网络结构 |
崔天舒1,2,黄永辉1,沈明3,张晔1,2,崔凯1,2,赵文杰1,安军社1,2 |
(1. 中国科学院国家空间科学中心 复杂航天系统电子信息技术重点实验室, 北京 100190;2. 中国科学院大学 计算机科学与技术学院, 北京 100049;3. 奥尔堡大学, 丹麦 奥尔堡 DK-9220)
|
摘要: |
现有应用于射频指纹识别的卷积网络对时序同相正交(in-phase and quadrature-phase,IQ)信号的处理都是将其简单视为图像进行的,存在识别准确率低和计算量大的问题。针对以上问题,提出了一种基于IQ相关特征的卷积神经网络结构。该网络分步提取了IQ相关特征及时域特征,通过自适应平均池化获得了各通道特征均值,并用单个全连接层进行分类。实验结果表明,较传统卷积网络结构,所提网络在多种场景下的识别准确率更高,并且计算量更小。 |
关键词: IQ信号 信号特征 射频指纹 卷积神经网络 深度学习 |
DOI:10.11887/j.cn.202204020 |
投稿日期:2020-11-16 |
基金项目:中国科学院复杂航天系统电子信息技术重点实验室自主部署基金资助项目(Y42613A32S) |
|
High-efficiency IQ convolutional network structure for radio frequency fingerprint identification |
CUI Tianshu1,2, HUANG Yonghui1, SHEN Ming3, ZHANG Ye1,2, CUI Kai1,2, ZHAO Wenjie1, AN Junshe1,2 |
(1. Key Laboratory of Electronics and Information Technology for Complex Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190;2. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China;3. Aalborg University, Aalborg DK-9220, Denmark)
|
Abstract: |
Existing convolutional neural networks, which are used for radio frequency fingerprints recognition, process time-sequenced IQ (in-phase and quadrature) signals as images directly, resulting in low recognition accuracy and high computation complexity. IQCNet(convolutional neural network structure based on IQ correlation features), an efficient convolutional network structure, was proposed. IQCNet firstly extracted IQ correlation features and time domain features, then obtained the average value of each channel features through adaptive average pooling, and finally used only one fully connected layer for classification. Experimental results under a variety of channel conditions show that IQCNet improves recognition accuracy greatly with lower computation complexity compared with traditional convolutional neural networks. |
Keywords: IQ signal signal characteristics radio frequency fingerprint convolutional neural network deep learning |
|
|
|
|
|