Radar specific emitter identification based on open-selective kernel residual network

Han, Xiao; Chen, Shiwen; Chen, Meng; Yang, Jincheng

doi:10.1016/j.dsp.2023.103913

Cited by 13 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is composed of the SK module proposed in our previous study. [15] Three branches with different convolutional kernel sizes of 1 × 3, 1 × 5 and 1 × 7 were used in the SK module. The input features were passed through three ResNet Blocks of convolution kernels of different sizes to obtain the features on these branches.…”

Section: Methodsmentioning

confidence: 99%

“…To further verify the effectiveness of the proposed method, another experiment was conducted using individual radar signals collected at a high sampling rate. [15] A high performance receiver was used to collect a similar type of radar signals emitted by five USRPs, one AWG, and one EXG. In the initial training stage, we randomly designated three emitters as known classes and trained the model.…”

Section: Performance In Open-set Scenariomentioning

confidence: 99%

See 1 more Smart Citation

Prototype‐based method for incremental radar emitter identification

Han

Chen

Xie

et al. 2023

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

With the widespread use of radars, different types of radar emitters are being used in the real electromagnetic environment. Radar emitter identification (REI) is an important technique in spectrum management. Methods based on deep learning have been successful in REI. However, they are difficult to be updated with signals from newly available categories. Additionally, two issues that must be considered in a real REI task. First, signals from new unknown radar emitters may appear in the identification stage. Hence the model used in REI must have an open‐set recognition capability. Second, obtaining numerous labelled samples in time are difficult in the incremental stage of the model. Thus, it is important to keep the model performance stable under conditions of small samples. To solve these problems, a one‐dimensional neural network is designed combined with ArcFace loss in the initial training stage to reserve more embedding space for future new classes, thereby facilitating the update of the model and open‐set recognition. An unbiased cosine similarity classifier was adopted, and the historical categories were memorised by their prototypes. When a new category is added, the prototype was calculated and the classifier weights were updated. The proposed method can identify unknown classes and add them to the model when given new labels, thereby resulting in an increase of the model's identifiable types. Extensive experiments were performed. The results show that the proposed model is highly efficient and requires small sample sizes, thereby making it suitable for REI.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Performance In Open-set Scenariomentioning

confidence: 99%

Prototype‐based method for incremental radar emitter identification

Han

Chen

Xie

et al. 2023

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNNs) are one of the most effective learning algorithms for understanding image content, capable of e ciently classifying and recognizing subtle differences in attributes between different sets of images. Its convolutional structure reduces the amount of memory consumed by deep networks, greatly improving recognition speed [21].…”

Section: Deep Learning Algorithmmentioning

confidence: 99%

Identification of subtle features of communication radiation sources based on point density "painting"

Sun,

Li,

Zhang

2024

Preprint

View full text Add to dashboard Cite

In the face of the increasingly complex wireless communication environment, the traditional communication radiation source individual subtle feature recognition algorithm has the defects of poor real-time performance and low accuracy when dealing with the radiation source signal of small samples. Aiming at this problem, a subtle feature recognition method for communication radiation sources based on point density "painting" is proposed. Firstly, a signal feature extraction algorithm based on improved heat map is proposed to improve the accuracy and real-time performance of the traditional algorithm in extracting features when dealing with small sample signals. Second, based on the I/Q scatterplot, a fusion feature extraction algorithm based on the signal heatmap and scatterplot is proposed, which combines the region division strategy and the clustering fusion algorithm to extract the fusion features of the signal in an early fusion manner. Again, to address the problem of low recognition rate of fusion features, we introduce the concept of user portrait in the marketing field, and innovatively propose an algorithm for recognizing individual subtle features of communication radiation sources based on point density "portrait". Finally, a convolutional neural network (CNN) model is constructed to train the extracted point density image data of different classes of complex baseband signals, and the measured WIFI data collected in the darkroom environment of the laboratory is used to verify the effectiveness of the algorithm. The simulation results show that the algorithm can improve the accuracy by 1–4%, with a recognition rate of 100%, and exhibits good stability compared to the feature extraction algorithm based on the fusion feature map of signal heat map, I/Q scatter plot and signal heatmap .This provides an effective and reliable solution for the accurate identification of individual subtle features of communication radiation sources with small samples in complex environments.

show abstract

“…Radar emitter individual identification is known as specific emitter identification (SEI) or fingerprint identification [8], which is an advanced task in radar signal identification in addition to radar signal model identification, type identification, and waveform identification [9,10]. Specifically, it refers to analyzing and processing the radar signals received by the receiver; extracting the unique fingerprint features in the signal due to personal reasons such as the equipment platform, etc.…”

Section: Introductionmentioning

confidence: 99%

Attention-Enhanced Dual-Branch Residual Network with Adaptive L-Softmax Loss for Specific Emitter Identification under Low-Signal-to-Noise Ratio Conditions

Jing,

Li,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

To address the issue associated with poor accuracy rates for specific emitter identification (SEI) under low signal-to-noise ratio (SNR) conditions, where the single-dimension radar signal characteristics are severely affected by noise, we propose an attention-enhanced dual-branch residual network structure based on the adaptive large-margin Softmax (ALS). Initially, we designed a dual-branch network structure to extract features from one-dimensional intermediate frequency data and two-dimensional time–frequency images, respectively. By assigning different attention weights according to their importance, these features are fused into an enhanced joint feature for further training. This approach enables the model to extract distinctive features across multiple dimensions and achieve good recognition performance even when the signal is affected by noise. In addition, we have introduced L-Softmax to replace the original Softmax and propose the ALS. This approach adaptively calculates the classification margin decision parameter based on the angle between samples and the classification boundary and adjusts the margin values of the sample classification boundaries; it reduces the intra-class distance for the same class while increasing the inter-class distance between different classes without the need for cumbersome experiments to determine the optimal value of decision parameters. Our experimental findings revealed that, in comparison to alternative methods, our proposed approach markedly enhances the model’s capability to extract features from signals and classify them in low-SNR environments, thereby effectively diminishing the influence of noise. Notably, it achieves the highest recognition rate across a range of low-SNR conditions, registering an average increase in recognition rate of 4.8%.

show abstract

Radar specific emitter identification based on open-selective kernel residual network

Cited by 13 publications

References 54 publications

Prototype‐based method for incremental radar emitter identification

Prototype‐based method for incremental radar emitter identification

Identification of subtle features of communication radiation sources based on point density "painting"

Attention-Enhanced Dual-Branch Residual Network with Adaptive L-Softmax Loss for Specific Emitter Identification under Low-Signal-to-Noise Ratio Conditions

Contact Info

Product

Resources

About