Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 1.88 MB
Add to list
  1. Search results
  2. Over-the-air aggregation-based federa...

Over-the-air aggregation-based federated learning for technology recognition in multi-RAT networks

Merkebu Girmay (UGent) , Mohamed Seif Eddin, Vasilis Maglogiannis (UGent) , Dries Naudts (UGent) , Adnan Shahid (UGent) , H. Vincent Poor and Ingrid Moerman (UGent)
(2024) 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024. In IEEE International Symposium on Dynamic Spectrum Access Networks p.465-472
Author
Organization
Abstract
With the continuous evolution of wireless communication and the explosive growth in data traffic, decentralized spectrum sensing has become essential for the optimal utilization of wireless resources. In this direction, we propose an over-the-air aggregation-based Federated Learning (FL) for a technology recognition model that can identify signals from multiple Radio Access Technologies (RATs), including Wi-Fi, Long Term Evolution (LTE), 5G New Radio (NR), Cellular Vehicle-to-Everything PC5 (C-V2X PC5), and Intelligent Transport Systems G5 (ITS-G5). In the proposed FL-based technology recognition framework, we consider edge network elements as clients to train local models and a central server to create the global model. In each client, a Convolutional Neural Network (CNN)-based model is trained from Inphase and Quadrature (IQ) samples collected from a certain combination of RATs. The possible combination of RATs considered in the clients is selected based on the capabilities of the real-world network elements that can be used as a client. The FL framework involves a process where multiple clients periodically send updates derived from local data to a central server, which then integrates these contributions to enhance a shared global model. This method ensures that the system stays current with the evolving real-world environment while also minimizing bandwidth required for training data transfer and allowing for the maintenance of personalized local models on each client's end.
Keywords
Federated Learning, multi-RAT, Technology Recognition, Spectrum Sensing

Downloads

  • Download
    8681 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 877.77 KB
  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 999.72 KB

Citation

Please use this url to cite or link to this publication:

MLA
Girmay, Merkebu, et al. “Over-the-Air Aggregation-Based Federated Learning for Technology Recognition in Multi-RAT Networks.” 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024, IEEE, 2024, pp. 465–72, doi:10.1109/DySPAN60163.2024.10632825.
APA
Girmay, M., Seif Eddin, M., Maglogiannis, V., Naudts, D., Shahid, A., Poor, H. V., & Moerman, I. (2024). Over-the-air aggregation-based federated learning for technology recognition in multi-RAT networks. 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024, 465–472. https://doi.org/10.1109/DySPAN60163.2024.10632825
Chicago author-date
Girmay, Merkebu, Mohamed Seif Eddin, Vasilis Maglogiannis, Dries Naudts, Adnan Shahid, H. Vincent Poor, and Ingrid Moerman. 2024. “Over-the-Air Aggregation-Based Federated Learning for Technology Recognition in Multi-RAT Networks.” In 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024, 465–72. IEEE. https://doi.org/10.1109/DySPAN60163.2024.10632825.
Chicago author-date (all authors)
Girmay, Merkebu, Mohamed Seif Eddin, Vasilis Maglogiannis, Dries Naudts, Adnan Shahid, H. Vincent Poor, and Ingrid Moerman. 2024. “Over-the-Air Aggregation-Based Federated Learning for Technology Recognition in Multi-RAT Networks.” In 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024, 465–472. IEEE. doi:10.1109/DySPAN60163.2024.10632825.
Vancouver
1.
Girmay M, Seif Eddin M, Maglogiannis V, Naudts D, Shahid A, Poor HV, et al. Over-the-air aggregation-based federated learning for technology recognition in multi-RAT networks. In: 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024. IEEE; 2024. p. 465–72.
IEEE
[1]
M. Girmay et al., “Over-the-air aggregation-based federated learning for technology recognition in multi-RAT networks,” in 2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024, Washington, DC, USA, 2024, pp. 465–472.
@inproceedings{01JBV9R6M5S3NMJWQHZK3RT064,
  abstract     = {{With the continuous evolution of wireless communication and the explosive growth in data traffic, decentralized spectrum sensing has become essential for the optimal utilization of wireless resources. In this direction, we propose an over-the-air aggregation-based Federated Learning (FL) for a technology recognition model that can identify signals from multiple Radio Access Technologies (RATs), including Wi-Fi, Long Term Evolution (LTE), 5G New Radio (NR), Cellular Vehicle-to-Everything PC5 (C-V2X PC5), and Intelligent Transport Systems G5 (ITS-G5). In the proposed FL-based technology recognition framework, we consider edge network elements as clients to train local models and a central server to create the global model. In each client, a Convolutional Neural Network (CNN)-based model is trained from Inphase and Quadrature (IQ) samples collected from a certain combination of RATs. The possible combination of RATs considered in the clients is selected based on the capabilities of the real-world network elements that can be used as a client. The FL framework involves a process where multiple clients periodically send updates derived from local data to a central server, which then integrates these contributions to enhance a shared global model. This method ensures that the system stays current with the evolving real-world environment while also minimizing bandwidth required for training data transfer and allowing for the maintenance of personalized local models on each client's end.}},
  author       = {{Girmay, Merkebu and Seif Eddin, Mohamed and Maglogiannis, Vasilis and Naudts, Dries and Shahid, Adnan and Poor, H. Vincent and Moerman, Ingrid}},
  booktitle    = {{2024 IEEE INTERNATIONAL SYMPOSIUM ON DYNAMIC SPECTRUM ACCESS NETWORKS, DYSPAN 2024}},
  isbn         = {{9798350317657}},
  issn         = {{2334-3125}},
  keywords     = {{Federated Learning,multi-RAT,Technology Recognition,Spectrum Sensing}},
  language     = {{eng}},
  location     = {{Washington, DC, USA}},
  pages        = {{465--472}},
  publisher    = {{IEEE}},
  title        = {{Over-the-air aggregation-based federated learning for technology recognition in multi-RAT networks}},
  url          = {{http://doi.org/10.1109/DySPAN60163.2024.10632825}},
  year         = {{2024}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: