Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint featur...Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint features to a data-driven technique and fur-ther reduces the adaptability of the technique to other datasets. To address this issue, the mechanism how the phase noise of high-frequency oscillators and the nonlinearity of power ampli-fiers affect the kurtosis of communication signals is investigated. Mathematical models are derived for intentional modulation (IM) and unintentional modulation (UIM). Analysis indicates that the phase noise of high-frequency oscillators and the nonlinearity of power amplifiers affect the kurtosis frequency and amplitude, respectively. A novel SEI method based on frequency and ampli-tude of the signal kurtosis (FA-SK) is further proposed. Simula-tion and real-world experiments validate theoretical analysis and also confirm the efficiency and effectiveness of the proposed method.展开更多
Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emi...Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emitters and complicate the procedures of identification.In this paper,we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints(RFFs),namely,RFFsNet-SEI.Particularly,we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition(VMD)and Hilbert transform(HT).The physical RFFs and I-Q data are formed into the balanced-RFFs,which are then used to train RFFsNet-SEI.As introducing model-aided RFFs into neural network,the hybrid-driven scheme including physical features and I-Q data is constructed.It improves physical interpretability of RFFsNet-SEI.Meanwhile,since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end,it accelerates SEI implementation and simplifies procedures of identification.Moreover,as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI,identification accuracy is improved.Finally,we compare RFFsNet-SEI with the counterparts in terms of identification accuracy,computational complexity,and prediction speed.Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.展开更多
针对目前敌我识别辐射源个体识别(Specific Emitter Identification of Identification Friend or Foe,SEI-IFF)研究不足的问题,提出了一种基于多维特征与Transformer网络的SEI-IFF方法。该方法首先从单个脉冲及信号全局等多维度获取如...针对目前敌我识别辐射源个体识别(Specific Emitter Identification of Identification Friend or Foe,SEI-IFF)研究不足的问题,提出了一种基于多维特征与Transformer网络的SEI-IFF方法。该方法首先从单个脉冲及信号全局等多维度获取如相位、幅度、时间、功率谱密度等信号特征,结合Transformer网络进一步提取不同IFF辐射源个体特征中如前后关联特性的细微特征并最终实现SEI-IFF。试验结果表明,所提方法针对20个目标搭载的IFF辐射源个体的平均识别正确率达95.3%,可较准确地完成SEI-IFF,有助于提升战场SEI-IFF效率。展开更多
基金supported by the Youth Science and Technology Innovation Award of National University of Defense Technology (18/19-QNCXJ)the National Science Foundation of China (62271494)
文摘Extensive experiments suggest that kurtosis-based fingerprint features are effective for specific emitter identification (SEI). Nevertheless, the lack of mechanistic explanation restricts the use of fingerprint features to a data-driven technique and fur-ther reduces the adaptability of the technique to other datasets. To address this issue, the mechanism how the phase noise of high-frequency oscillators and the nonlinearity of power ampli-fiers affect the kurtosis of communication signals is investigated. Mathematical models are derived for intentional modulation (IM) and unintentional modulation (UIM). Analysis indicates that the phase noise of high-frequency oscillators and the nonlinearity of power amplifiers affect the kurtosis frequency and amplitude, respectively. A novel SEI method based on frequency and ampli-tude of the signal kurtosis (FA-SK) is further proposed. Simula-tion and real-world experiments validate theoretical analysis and also confirm the efficiency and effectiveness of the proposed method.
基金supported by the National Natural Science Foundation of China(62061003)Sichuan Science and Technology Program(2021YFG0192)the Research Foundation of the Civil Aviation Flight University of China(ZJ2020-04,J2020-033)。
文摘Existing specific emitter identification(SEI)methods based on hand-crafted features have drawbacks of losing feature information and involving multiple processing stages,which reduce the identification accuracy of emitters and complicate the procedures of identification.In this paper,we propose a deep SEI approach via multidimensional feature extraction for radio frequency fingerprints(RFFs),namely,RFFsNet-SEI.Particularly,we extract multidimensional physical RFFs from the received signal by virtue of variational mode decomposition(VMD)and Hilbert transform(HT).The physical RFFs and I-Q data are formed into the balanced-RFFs,which are then used to train RFFsNet-SEI.As introducing model-aided RFFs into neural network,the hybrid-driven scheme including physical features and I-Q data is constructed.It improves physical interpretability of RFFsNet-SEI.Meanwhile,since RFFsNet-SEI identifies individual of emitters from received raw data in end-to-end,it accelerates SEI implementation and simplifies procedures of identification.Moreover,as the temporal features and spectral features of the received signal are both extracted by RFFsNet-SEI,identification accuracy is improved.Finally,we compare RFFsNet-SEI with the counterparts in terms of identification accuracy,computational complexity,and prediction speed.Experimental results illustrate that the proposed method outperforms the counterparts on the basis of simulation dataset and real dataset collected in the anechoic chamber.
文摘针对目前敌我识别辐射源个体识别(Specific Emitter Identification of Identification Friend or Foe,SEI-IFF)研究不足的问题,提出了一种基于多维特征与Transformer网络的SEI-IFF方法。该方法首先从单个脉冲及信号全局等多维度获取如相位、幅度、时间、功率谱密度等信号特征,结合Transformer网络进一步提取不同IFF辐射源个体特征中如前后关联特性的细微特征并最终实现SEI-IFF。试验结果表明,所提方法针对20个目标搭载的IFF辐射源个体的平均识别正确率达95.3%,可较准确地完成SEI-IFF,有助于提升战场SEI-IFF效率。
文摘特定辐射源识别(Specific emitter identification,SEI)通过分析设备信号硬件特征保障物联网数据安全。现有的深度学习方法在进行特定辐射源识别时,样本数量受限,过于依赖大量已标记样本,无法做到高区分度表征,存在识别性能差的问题。针对这些问题,提出了基于样本插值(Mixup)增强的少样本SEI方法。首先采用Mixup的增强方式来扩展无线电信号样本的数量解决标注样本不足的问题;其次,基于孪生神经网络与复数神经网络(Complex-valued neural networks,CVNN)构建变体三元组网络(Triplet margin network based on CVNN,CVNN-TMN)提高模型的泛化能力和区分度,实现了少样本场景下特定辐射源的精准识别。实验结果表明,与现有多种先进SEI方法对比,在训练集和测试集样本划分比例不同情况下,提出的CVNN-TMN识别精度整体有5%~30%的提升,表明所构建的CVNN-TMN模型在区分度上的优异表现。
