Few-Shot Metric Learning with Time-Frequency Fusion for Specific Emitter Identification
Remote Sensing · 2024-12-11 · 16 (24) · 4635
DOI: 10.3390/rs16244635 ↗At a glance
Journal article in Remote Sensing, published online on 2024-12-11. Written by Shiyuan Mu and 5 co-authors. Cited 7 times so far (Crossref); 35 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Qin chuangyuan “Scientist + Engineer” Team Construction Project of Shaanxi Province.
Abstract (original language)
Specific emitter identification (SEI) is a promising physical-layer authentication technique that serves as a crucial complement to upper-layer authentication mechanisms. SEI capitalizes on the inherent radio frequency fingerprints stemming from circuit discrepancies, which are intrinsic hardware properties and challenging to counterfeit. Recently, various deep learning (DL)-based SEI methods have been proposed, achieving outstanding performance. However, collecting and annotating substantial data for novel or unknown radiation sources is not only time-consuming but also cost-intensive. To address this issue, this paper proposes a few-shot (FS) metric learning-based time-frequency fusion network. To enhance the discriminative capability for radiation source signals, the model employs a convolutional block attention module (CBAM) and feature transformation to effectively fuse the raw signal’s time domain and time-frequency domain representations. Furthermore, to improve the extraction of discriminative features under FS scenarios, the proxy-anchor loss and center loss are introduced to reinforce intra-class compactness and inter-class separability. Experiments on the ADS-B and Wi-Fi datasets demonstrate that the proposed TFAF-Net consistently outperforms existing models in FS-SEI tasks. On the ADS-B dataset, TFAF-Net achieves a 9.59% higher accuracy in 30-way 1-shot classification compared to the second-best model, and reaches an accuracy of 85.02% in 10-way classification. On the Wi-Fi dataset, TFAF-Net attains 90.39% accuracy in 5-way 1-shot classification, outperforming the next best model by 6.28%, and shows a 13.18% improvement in 6-way classification.
Funding
- National Natural Science Foundation of China
- Qin chuangyuan “Scientist + Engineer” Team Construction Project of Shaanxi Province
Cite
APA
Mu, S., Zu, Y., Chen, S., Yang, S., Feng, Z., & Zhang, J. (2024). Few-Shot Metric Learning with Time-Frequency Fusion for Specific Emitter Identification. Remote Sensing, 16(24), 4635. https://doi.org/10.3390/rs16244635
Vancouver
Mu S, Zu Y, Chen S, Yang S, Feng Z, Zhang J. Few-Shot Metric Learning with Time-Frequency Fusion for Specific Emitter Identification. Remote Sensing. 2024;16(24):4635. doi:10.3390/rs16244635
BibTeX
@article{Mu2024,
author = {Mu, Shiyuan and Zu, Yong and Chen, Shuai and Yang, Shuyuan and Feng, Zhixi and Zhang, Junyi},
title = {Few-Shot Metric Learning with Time-Frequency Fusion for Specific Emitter Identification},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {24},
pages = {4635},
doi = {10.3390/rs16244635}
}
EUVIMED