Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting
IEEE Internet of Things Journal · 15.10.2025 · 12 (20) · 42728-42740
DOI: 10.1109/jiot.2025.3594571 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.10.2025. Verfasst von Kaijie Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: natural Science Research of Jiangsu Higher Education Institutes of China.
Abstract (Originalsprache)
The widespread use of uncrewed aerial vehicles (UAVs) brings both convenience and potential security risks, posing significant challenges for accurate UAV identification. To address the limitations of existing deep learning-based radio frequency (RF) fingerprinting methods in terms of computational complexity and model adaptability, this article proposes an innovative hybrid model that combines Convolutional Neural Networks and Transformers to exploit both local and global features of RF signals fully. Our model consists of a Local Block and a Global Block. The Local Block employs partial convolution for feature extraction, pointwise convolution to enhance feature representation, and the squeeze-and-excitation module to adaptively emphasize critical features, thereby improving local feature expressiveness. The Global Block comprises Unfold, super token transformer Block, and Fold, which together enable effective modeling of global dependencies through signal unfolding, spatiotemporal transformations, and reconstruction. Experimental results show that under signal-to-noise ratio (SNR) conditions ranging from –5 to 20 dB, our method achieves an average recognition accuracy of 96.89%, with powerful performance under low SNR conditions. Furthermore, experiments demonstrate the model’s robustness with limited data. Even with only 1000 training samples, the model maintains an accuracy of 92.14%. When incorporating Mixup data augmentation, high classification performance is sustained with just 500 training samples. These results highlight the method’s strong adaptability and practical potential in complex environments. Our codes and models are available at https://github.com/Zhoukaijie-hy/hybrid-model.
Förderung
- natural Science Research of Jiangsu Higher Education Institutes of China
Zitieren
APA
Zhou, K., Li, Q., Cao, P., Cai, Z., Shi, X., & Wang, F. (2025). Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting. IEEE Internet of Things Journal, 12(20), 42728-42740. https://doi.org/10.1109/jiot.2025.3594571
Vancouver
Zhou K, Li Q, Cao P, Cai Z, Shi X, Wang F. Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting. IEEE Internet of Things Journal. 2025;12(20):42728-42740. doi:10.1109/jiot.2025.3594571
BibTeX
@article{Zhou2025,
author = {Zhou, Kaijie and Li, Qingbo and Cao, Peipei and Cai, Zhenxin and Shi, Xinyi and Wang, Fan},
title = {Lightweight and Efficient Hybrid Network for UAV Identification Using Radio Frequency Fingerprinting},
journal = {IEEE Internet of Things Journal},
year = {2025},
volume = {12},
number = {20},
pages = {42728--42740},
doi = {10.1109/jiot.2025.3594571}
}
EUVIMED