EUVIMEDEUVIMED entdecken
Crossref

RF$^{2}$ Transformer: Refocusing Transformer for RF Sensing

Ruiyuan Song, Zhi Lu, Liang Fang, Zhi Wu, Shuai Yang, Dongheng Zhang, Yang Hu, Hui Lin, Yan Chen

IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 13688-13703

DOI: 10.1109/tmc.2026.3673427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Ruiyuan Song und 8 weiteren Autor:innen. Die Arbeit nennt 82 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The learning-based RF sensing methods typically involve signal processing to transform the RF signals into spectrograms, which are then input into neural networks. However, this approach is suboptimal due to the potential degradation caused by the inherent multi-path interference, resulting in blurred RF spectrograms. To tackle this challenge, we introduce a novel R e f ocusing Transformer backbone customized for RF sensing (RF $^{2}$ 2 Transformer). Rather than attempting to precisely model interference using the traditional signal processing techniques, the RF $^{2}$ 2 Transformer utilizes a self-compensation mechanism to treat the interference-induced phase shifts as learnable parameters. This mechanism learns and compensates for the phase shift caused by interference in the complex feature space to obtain refocused and high-quality feature maps of RF spectrograms, thereby improving the performance of downstream tasks. We show that the RF $^{2}$ 2 Transformer is general for various RF sensing tasks by evaluating it on six typical RF sensing tasks using two general RF signals (WiFi and radar). Experimental results indicate that the RF $^{2}$ 2 Transformer takes an important step toward learning-based solutions for RF sensing

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Song, R., Lu, Z., Fang, L., Wu, Z., Yang, S., Zhang, D., Hu, Y., Lin, H., & Chen, Y. (2026). RF$^{2}$ Transformer: Refocusing Transformer for RF Sensing. IEEE Transactions on Mobile Computing, 25(9), 13688-13703. https://doi.org/10.1109/tmc.2026.3673427

Vancouver

Song R, Lu Z, Fang L, Wu Z, Yang S, Zhang D, et al. RF$^{2}$ Transformer: Refocusing Transformer for RF Sensing. IEEE Transactions on Mobile Computing. 2026;25(9):13688-13703. doi:10.1109/tmc.2026.3673427

BibTeX
@article{Song2026,
  author = {Song, Ruiyuan and Lu, Zhi and Fang, Liang and Wu, Zhi and Yang, Shuai and Zhang, Dongheng and Hu, Yang and Lin, Hui and Chen, Yan},
  title = {RF$^2$ Transformer: Refocusing Transformer for RF Sensing},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {9},
  pages = {13688--13703},
  doi = {10.1109/tmc.2026.3673427}
}
Kostenlos starten →