T-PRIME: Real-Time Deployment of a Transformer-Based Protocol Identification for Machine-Learning at the Edge
IEEE Transactions on Networking · 2026 · 34 · 6428-6440
DOI: 10.1109/ton.2026.3715224 ↗Kurz gefasst
Studienprotokoll in der Zeitschrift IEEE Transactions on Networking, 2026. Verfasst von Mauro Belgiovine und 6 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: Defence Science and Technology Laboratory, U.K. Ministry of Defence, National Science Foundation through AI Edge.
Abstract (Originalsprache)
Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this paradigm continues to spread, wireless systems must also evolve to identify active transmitters and unauthorized waveforms in real time under preamble corruption due to spectral overlap and co-channel interference, extremely low signal-to-noise ratios and challenging channel conditions. We overcome limitations of correlation-based preamble matching methods in such conditions through the design of T-PRIME: a Transformer-based machine learning approach. T-PRIME learns the structural design of transmitted frames through its attention mechanism, looking at sequence patterns that go beyond the preamble alone. The paper makes three contributions: First, it compares Transformer models and demonstrates their superiority over traditional methods and state-of-the-art neural networks. Second, it rigorously analyzes T-PRIME’s real-time feasibility on DeepWave’s AIR-T platform. Third, it utilizes an extensive 66 GB dataset of over-the-air (OTA) WiFi transmissions collected in single-protocol and double-protocol interference configurations, which is used to train T-PRIME models and released along with the code for community use. Results reveal nearly perfect (i.e. > 98%) classification accuracy under simulated scenarios, showing 100% detection improvement over legacy methods in low SNR ranges. For OTA datasets, proposed approach achieve 99.3% classification accuracy for single-protocol transmissions and up to 79.5% (average 70.3%) exact double-protocol classification accuracy for all interference scenarios.
Förderung
- Defence Science and Technology Laboratory
- U.K. Ministry of Defence
- National Science Foundation through AI Edge
Zitieren
APA
Belgiovine, M., Groen, J., Sirera, M., Tassie, C., Yildiz, A. Y., Ioannidis, S., & Chowdhury, K. (2026). T-PRIME: Real-Time Deployment of a Transformer-Based Protocol Identification for Machine-Learning at the Edge. IEEE Transactions on Networking, 34, 6428-6440. https://doi.org/10.1109/ton.2026.3715224
Vancouver
Belgiovine M, Groen J, Sirera M, Tassie C, Yildiz AY, Ioannidis S, et al. T-PRIME: Real-Time Deployment of a Transformer-Based Protocol Identification for Machine-Learning at the Edge. IEEE Transactions on Networking. 2026;34:6428-6440. doi:10.1109/ton.2026.3715224
BibTeX
@article{Belgiovine2026,
author = {Belgiovine, Mauro and Groen, Joshua and Sirera, Miquel and Tassie, Chinenye and Yildiz, Ayberk Yarkin and Ioannidis, Stratis and Chowdhury, Kaushik},
title = {T-PRIME: Real-Time Deployment of a Transformer-Based Protocol Identification for Machine-Learning at the Edge},
journal = {IEEE Transactions on Networking},
year = {2026},
volume = {34},
pages = {6428--6440},
doi = {10.1109/ton.2026.3715224}
}
EUVIMED