面向开集场景的辐射源个体识别

王春升; 王永民; 许华; 张悦; 朱丽莉

doi:10.7652/xjtuxb202210013

您当前的位置：

首页 >

文章列表页 >

面向开集场景的辐射源个体识别

—————————————————————— | 更新时间：2025-07-09

- 面向开集场景的辐射源个体识别
- Specific Emitter Identification Under Open Set Scenes
- 西安交通大学学报 2022年56卷第10期页码：130-140
- 作者机构：
  
  空军工程大学信息与导航学院,西安,710077
- 作者简介：
  
  : 2022-04-09。作者简介: 王春升(1994—),男,硕士生
  王永民(通信作者),男,副教授,硕士生导师。基金项目: 国家自然科学基金资助项目(61906156)
- 基金信息：
  
  : 2022-04-09。作者简介: 王春升(1994—),男,硕士生;王永民(通信作者),男,副教授,硕士生导师。基金项目: 国家自然科学基金资助项目(61906156);空军工程大学研究生创新实践基金资助项目(CXJ2021075)
- DOI：10.7652/xjtuxb202210013
  中图分类号： TN975
- 网络首发：2022-10-10，
  
  纸质出版：2022
- 稿件说明：
移动端阅览
王春升, 王永民, 许华, 等. 面向开集场景的辐射源个体识别[J]. 西安交通大学学报, 2022,56(10):130-140.

WANG Chunsheng, WANG Yongmin, XU Hua, et al. Specific Emitter Identification Under Open Set Scenes[J]. 2022, 56(10): 130-140.
王春升, 王永民, 许华, 等. 面向开集场景的辐射源个体识别[J]. 西安交通大学学报, 2022,56(10):130-140. DOI： 10.7652/xjtuxb202210013.

WANG Chunsheng, WANG Yongmin, XU Hua, et al. Specific Emitter Identification Under Open Set Scenes[J]. 2022, 56(10): 130-140. DOI： 10.7652/xjtuxb202210013.

摘要

为解决现有开集场景下辐射源个体识别算法鲁棒性不强、识别性能较低的问题

结合原型网络提出了一种开集场景下适用于一维信号的辐射源个体识别模型。对采集的辐射源I/Q信号进行功率归一化、切片和加噪等预处理操作; 设计用于识别I/Q信号的一维卷积神经网络

并在网络中加入具有注意力机制的压缩激励模块

以此提高网络中有效特征通道的权重; 将该网络结构和原型学习思想相结合

利用预处理的数据集进行训练和测试。在训练过程中

利用距离交叉熵损失函数为每个类别学习一个原型

并将信号特征到原型的距离作为分类依据

同时利用原型损失函数以提高信号类内紧密度的方式增大类间距离

进一步增强分类能力; 在测试过程中

利用自适应距离分类规则为每个类别学习一个自适应的距离阈值

并通过距离阈值完成对已知目标的分类和未知目标的检测。对5种ZigBee设备采集的信号进行实验

结果表明:在信噪比为-10～10 dB之间

所提模型的识别准确率比通常所用的基于极值理论的模型高8%左右。

Abstract

This paper proposes a specific emitter identification model suitable for one-dimensional signals under open set scenes based on prototype network. The model is used to solve the problems of weak robustness and low recognition of existing algorithms for specific emitter identification under open set scenes. Firstly

the I/Q signals collected are preprocessed by power normalization

slicing and noise addition. Then

a one-dimensional convolutional neural network for recognition of I/Q signals is designed

and a squeeze-and-excitation block with attentional mechanism is added to the network to improve the weights of feature channels with high efficiency. Finally

the preprocessed data set is used to train and test the network based on the idea of prototype learning. During the training process

the distance cross entropy loss function is used for prototype learning for each category

taking the distance between the signal features and the prototype as the classification basis. At the same time

the prototype loss function is used to increase the inter-class distance by compacting the intra-class signals

which further enhances the classification ability. During the testing process

the network can learn an adaptive distance threshold for each category by using the adaptive distance classification rule. The distance threshold is used for the classification of known classes and the detection of unknown ones. Experiments are carried out on the signals collected from five ZigBee devices. Simulation results show that the recognition rate of proposed model is about 8% higher than the common models based on extreme value theory between a signal-to-noise ratio from -10 dB to 10 dB.

关键词

Keywords

references

TALBOT K I, DULEY P R, HYATT M H. Specific emitter identification and verification [J]. Technology Review, 2003: 113-133.

BIHL T J, BAUER K W, TEMPLE M A. Feature selection for RF fingerprinting with multiple discriminant analysis and using ZigBee device emissions [J]. IEEE Transactions on Information Forensics and Security, 2016, 11(8): 1862-1874.

YANG Yinsong, GUO Ying, LI Hongguang, et al. Fingerprint feature recognition of frequency hopping based on high order cumulant estimation [C]//2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference(IAEAC). Piscataway, NJ, USA: IEEE, 2018: 2175-2179.

XU Shuhua, HUANG Benxiong, XU Lina, et al. Radio transmitter classification using a new method of stray features analysis combined with PCA [C]//2007 IEEE Military Communications Conference. Piscataway, NJ, USA: IEEE, 2007: 1-5.

刘明骞, 颜志文, 张俊林. 空中目标辐射源的个体识别方法 [J]. 系统工程与电子技术, 2019, 41(11): 2408-2415.

LIU Mingqian, YAN Zhiwen, ZHANG Junlin. Specific emitter identification method for aerial target [J]. Systems Engineering and Electronics, 2019, 41(11): 2408-2415.

HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023.

PAN Yiwei, YANG Sihan, PENG Hua, et al. Specific emitter identification based on deep residual networks [J]. IEEE Access, 2019, 7: 54425-54434.

PENG Linning, ZHANG Junqing, LIU Ming, et al. Deep learning based RF fingerprint identification using differential constellation trace figure [J]. IEEE Transactions on Vehicular Technology, 2020, 69(1): 1091-1095.

牛伟宇, 许华, 刘英辉, 等. 基于PACGAN与差分星座轨迹图的辐射源个体识别 [J]. 信号处理, 2021, 37(8): 1559-1567.

NIU Weiyu, XU Hua, LIU Yinghui, et al. Individual identification method based on PACGAN and differential constellation trace figure [J]. Signal Processing, 2021, 37(8): 1559-1567.

王春升, 王永民, 许华, 等. 基于残差原型网络的辐射源个体识别 [J/OL]. 系统工程与电子技术 [2022-06-06]. http://kns.cnki.net/kcms/detail/11.2422.TN.20220419.1641.002.html.

WANG Chunsheng, WANG Yongmin, XU Hua, et al. Specific emitter identification based on residual prototype network [J/OL]. Systems Engineering and Electronics [2022-06-06]. http://kns.cnki.net/kcms/detail/11.2422.TN.20220419.1641.002.html.

刘明骞, 李建英, 李兵兵, 等. 认知无线电Underlay模式下MQAM信号的调制识别 [J]. 西安交通大学学报, 2018, 52(2): 52-57.

LIU Mingqian, LI Jianying, LI Bingbing, et al. Modulation identification of MQAM signals in Underlay cognitive radios [J]. Journal of Xi'an Jiaotong University, 2018, 52(2): 52-57.

李彬, 徐怡杭, 罗杰. 采用残差神经网络的无人机遥控信号识别监测算法 [J]. 西安交通大学学报, 2021, 55(12): 146-154.

LI Bin, XU Yihang, LUO Jie. A recognition and monitoring algorithm for drone remote control signals using residual neural network [J]. Journal of Xi'an Jiaotong University, 2021, 55(12): 146-154.

QING Guangwei, WANG Huifang, ZHANG Tingping. Radio frequency fingerprinting identification for Zigbee via lightweight CNN [J]. Physical Communication, 2021, 44: 101250.

ZHOU Xinyu, HU Aiqun, LI Guyue, et al. A robust radio-frequency fingerprint extraction scheme for practical device recognition [J]. IEEE Internet of Things Journal, 2021, 8(14): 11276-11289.

LIU Yinghui, XU Hua, QI Zisen, et al. Specific emitter identification against unreliable features interference based on time-series classification network structure [J]. IEEE Access, 2020, 8: 200194-200208.

WANG Yu, GUI Guan, GACANIN H, et al. An efficient specific emitter identification method based on complex-valued neural networks and network compression [J]. IEEE Journal on Selected Areas in Communications, 2021, 39(8): 2305-2317.

CHEN Wei, WANG Yanhua, SONG Jia, et al. Open set HRRP recognition based on convolutional neural network [J]. The Journal of Engineering, 2019, 2019(21): 7701-7704.

HANNA S, KARUNARATNE S, CABRIC D. Open set wireless transmitter authorization: deep learning approaches and dataset considerations [J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(1): 59-72.

BENDALE A, BOULT T E. Towards open set deep networks [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2016: 1563-1572.

林万杰. 基于深度学习的未知辐射源个体识别的研究 [D]. 成都: 电子科技大学, 2021.

林子榆, 王翔, 孙丽婷, 等. 基于深度自编码器的辐射源个体开集识别 [J/OL]. 太赫兹科学与电子信息学报 [2022-06-06]. http://kns.cnki.net/kcms/detail/51.1746.TN.20211222.1033.002.html.

LIN Ziyu, WANG Xiang, SUN Liting, et al. Open set recognition of specific emitter identification based on deep auto-encoder [J/OL]. Journal of Terahertz Science and Electronic Information Technology [2022-06-06]. http://kns.cnki.net/kcms/detail/51.1746.TN.20211222.1033.002.html.

DRAGANOV A, BROWN C, MATTEI E, et al. Open set recognition through unsupervised and class-distance learning [C]//Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning. New York, NY, USA: ACM, 2020: 7-12.[23] JI Zhong, CHAI Xingliang, YU Yunlong, et al. Improved prototypical networks for few-shot learning [J]. Pattern Recognition Letters, 2020, 140: 81-87.

YANG Hongming, ZHANG Xuyao, YIN Fei, et al. Robust classification with convolutional prototype learning [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 3474-3482.

YANG Hongming, ZHANG Xuyao, YIN Fei, et al. Convolutional prototype network for open set recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(5): 2358-2370.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

蜉蝣优化双通道网络在齿轮箱故障诊断中的应用

一种适用于混合三端直流输电线路的故障定位方法

采用格拉姆角场-卷积神经网络-时序卷积网络混合模型的锂离子电池健康状态估计

一种基于FPGA的卷积神经网络协处理器设计

一种高分辨率遥感图像视感知目标检测算法