Semi-Supervised Specific Emitter Identification Based on Bispectrum Feature Extraction CGAN in Multiple Communication Scenarios

Tan, Kaiwen; Yan, Wenjun; Zhang, Limin; Ling, Qing; Xu, Congan

doi:10.1109/taes.2022.3184619

Cited by 22 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sankhe et al [25] presented a novel system based on convolutional neural networks (CNNs) to identify a unique radio from a large pool of devices by deep learning the fine-grained hardware impairments imposed by radio circuitry on physical-layer I/Q samples. Tan et al [26] introduced semi-supervised learning into SEI and proposed a self-classification generative adversarial network (GAN) using bispectrum-based feature extraction. The aforementioned approaches can learn the inherent features of different emitters: underscoring the ascendancy of deep learning in SEI.…”

Section: Related Workmentioning

confidence: 99%

Research on an Enhanced Multimodal Network for Specific Emitter Identification

Peng,

Xie,

Zou

2024

Electronics

View full text Add to dashboard Cite

Specific emitter identification (SEI) refers to the task of distinguishing similar emitters, especially those of the same type and transmission parameters, which is one of the most critical tasks of electronic warfare. However, SEI is still a challenging task when a feature has low physical representation. Feature representation largely determines the recognition results. Therefore, this article expects to move toward robust feature representation for SEI. Efficient multimodal strategies have great potential for applications using multimodal data and can further improve the performance of SEI. In this research, we introduce a multimodal emitter identification method that explores the application of multimodal data, time-series radar signals, and feature vector data to an enhanced transformer, which employs a conformer block to embed the raw data and integrates an efficient multimodal feature representation module. Moreover, we employ self-knowledge distillation to mitigate overconfident predictions and reduce intra-class variations. Our study reveals that multimodal data provide sufficient information for specific emitter identification. Simultaneously, we propose the CV-CutMixOut method to augment the time-domain signal. Extensive experiments on real radar datasets indicate that the proposed method achieves more accurate identification results and higher feature discriminability.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on an Enhanced Multimodal Network for Specific Emitter Identification

Peng,

Xie,

Zou

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Gong et al [30] proposed an unsupervised SEI framework based on information maximisation GAN (InfoGAN) and RFF embedding, adding loss functions to the training of GAN to maximise mutual information between generated data and potential input of emitter. The existing GAN-based SEI framework [31] focuses on using its unique structural advantages to solve the problem of insufficient labelling training samples in non-cooperative scenarios.…”

Section: Introductionmentioning

confidence: 99%

Dynamic open set specific emitter identification via multi‐channel reconstructive discriminant network

Tan¹,

Yan²,

Zhang³

et al. 2023

IET Radar Sonar & Navi

Self Cite

View full text Add to dashboard Cite

Specific emitter identification (SEI) is an emerging device authentication technology, which depends on the inherent hardware characteristics of wireless devices. By analysing the received signal, the hardware characteristics of a specific emitter can be extracted at the receiver and used for device authentication and association. Most of the existing SEI schemes focus on the identification under closed sets. In view of the explosive growth of the number of IoT devices, based on generative adversarial networks, this study proposes a method that considers the identification of unknown emitters. The reconstruction network to reconstruct the signals of the known class and fully train the feature space of the signals of the known class is designed. In the discriminator, two channels are specifically designed to perform anomaly detection for unknown signals and end‐to‐end closed‐set classification for known signals. In order to better reject unknown signals and accept known signals, Receiver operating characteristic curve and Youden index are used to determine the optimal threshold for anomaly detection. Under the given optimal threshold conditions, the identified threshold points have larger True Positive Rate. In addition, the time‐frequency feature combination vector is designed to reveal the essential characteristics of emitters. The experimental results on the real‐world datasets collected from universal software radio peripherals in short‐range communication scenario show that compared with the existing open‐set recognition methods such as C2AE, Openmax and SoftMax, the average recognition accuracy of the proposed framework improved by 0.08, 0.15, and 0.2 respectively, and the Marco‐F1 score improved by 0.05, 0.1, and 0.16, respectively, which proves the superiority of the proposed framework. In addition to identifying unknown and known Universal software radio peripherals in this article, some potential and widespread applications of the proposed framework include access user security authentication in IoT, such as Hack RF and Blue tooth devices. In addition, as a relatively general signal processing framework, the model can be used for air safety management and maritime ship identity authentication in civil aspects. In the military aspect, it can be used in electronic support and various signal reconnaissance scenarios, such as automatic signal modulation recognition in open set scenarios, individual identity determination of radar emitter and unknown working state identification of transmitters, which proves reference for subsequent research on open‐set signal recognition.

show abstract

“…Liu et al [18] proposed a method called Class Reconstruction Classification Network with Adversarial Training (CRCN-AT), enhancing recognition performance and robustness in a few-shot scenario without the support of auxiliary datasets. Tan et al [19] employed dual-spectrum features and selfsupervised GAN for unsupervised classification learning of communication signals. They conducted experiments with 12 USRPs and achieved promising accuracy levels.However, most relevant methods utilize traditional feature fingerprint extraction methods combined with GAN for data augmentation.…”

Section: Introductionmentioning

confidence: 99%

Generative Adversarial Networks with Gramian Angular Field for Handling Imbalanced Data in Specific Emitter Identification

Zhang,

Zhou,

2023

Preprint

View full text Add to dashboard Cite

Specific Emitter Identification (SEI) is a methodology employed to identify emitters by exploiting the hardware impairments inherent in transmitting devices. In the real world, there are challenges in performing SEI on radiation source signals, such as serious imbalance among samples, leading to low model accuracy, poor generalization, and limited practical application. These challenges widely occur in modern military, security, and other fields, but related research works have been conducted relatively late. In this paper, we propose a Generative Adversarial Network (GAN) with the Gramian Angular Field (GAF) method to address few-shot case data. Specifically, the proposed method employs GAF transformation to convert temporal radar data into a two-dimensional image format and utilizes an enhanced GAN to improve the classifier for imbalanced data based on the characteristics of GAF through training on both augmented and original samples. The experiments were conducted on real-world Automatic Dependent Surveillance-Broadcast (ADS-B) signals, demonstrating the effectiveness of the proposed method. The method could significantly improve the performance of the SEI model in inter-class imbalanced scenarios.

show abstract

Semi-Supervised Specific Emitter Identification Based on Bispectrum Feature Extraction CGAN in Multiple Communication Scenarios

Cited by 22 publications

References 33 publications

Research on an Enhanced Multimodal Network for Specific Emitter Identification

Research on an Enhanced Multimodal Network for Specific Emitter Identification

Dynamic open set specific emitter identification via multi‐channel reconstructive discriminant network

Generative Adversarial Networks with Gramian Angular Field for Handling Imbalanced Data in Specific Emitter Identification

Contact Info

Product

Resources

About