to design efficient data processing methods for future wireless communication systems (6G and beyond), using physical models to structure, initialize and train frugal artificial intelligence methods.
In the context of military communications, anti-jamming techniques are of paramount importance to protect against potential interferences. Within this framework, the anti-jamming Wiener filter is
that disrupt wideband systems such as Direct-Sequence Spread Spectrum (DSSS) [1]. This method requires estimating the frequency
and power of the jamming components, which can be addressed using either signal processing or machine learning methods. In order to
achieve a satisfying trade-off between these two approaches, modelbased learning has been introduced recently [2] and led to promising
results in various fields of wireless systems [3–7].
2 Objectives
The main objectives of the internship are the following:
(O1) Designing a model-based learning strategy in order to jointly estimate the frequency and power of the
jamming components.
(O2) Comparing the developed method to existing purely data-driven and signal processing approaches.
(O3) (Optional) Adapting the method to exhibit robustness to the most common hardware impairments [8, 9].
One interesting lead for (O1) is to use the structure of the Wiener filter to build a neural network. Regarding
(O3), it is possible to accomodate for impairments by relaxing some constraints of the model, thus introducing
supplementary learnable parameters. If everything go as planned, the results of the internship should lead to the
submission of an article to an international conference.
3 Logistics
The internship will be hosted in the SIGNAL team of the IETR (on the campus of INSA Rennes), for a duration
of six months starting between January and March of 2025. Students in their final year (M2/PFE) with a
background/interest in signal processing, machine learning and applied mathematics are encouraged to apply by
1sending an email to luc.le-magoarou@insa-rennes.fr. The internship is thought of as a preparation for a PhD on a
related topic.
References
[1] Corentin Fonteneau, Matthieu Crussi`ere, Alexis Bazin, and Oudomsack Pierre Pasquero. Rejection capability of anti-jamming
wiener filter for multi-tone interference in dsss systems. In MILCOM 2024 - 2024 IEEE Military Communications Conference
(MILCOM), 2024.
[2] Nir Shlezinger, Jay Whang, Yonina C Eldar, and Alexandros G Dimakis. Model-based deep learning. Proceedings of the IEEE,
2023.
[3] Taha Yassine and Luc Le Magoarou. mpnet: variable depth unfolded neural network for massive mimo channel estimation. IEEE
Transactions on Wireless Communications, 21(7):5703–5714, 2022.
[4] Nhan Thanh Nguyen, Mengyuan Ma, Nir Shlezinger, Yonina C Eldar, AL Swindlehurst, and Markku Juntti. Deep unfolding hybrid
beamforming designs for thz massive mimo systems. arXiv preprint arXiv:2302.12041, 2023.
[5] J ́erˆome Sol, Hugo Prod’Homme, Luc Le Magoarou, and Philipp del Hougne. Experimentally realized physical-model-based wave
control in metasurface-programmable complex media. arXiv preprint arXiv:2308.02349, 2023.
[6] Jos ́e Miguel Mateos-Ramos, Christian H ̈ager, Musa Furkan Keskin, Luc Le Magoarou, and Henk Wymeersch. Model-based
end-to-end learning for multi-target integrated sensing and communication. arXiv preprint arXiv:2307.04111, 2023.
[7] Baptiste Chatelier, Luc Le Magoarou, Vincent Corlay, and Matthieu Crussi`ere. Model-based learning for location-to-channel
mapping. arXiv preprint arXiv:2308.14370, 2023.
[8] Tim Schenk. RF imperfections in high-rate wireless systems: impact and digital compensation. Springer Science & Business
Media, 2008.
[9] Hui Chen, Musa Furkan Keskin, Sina Rezaei Aghdam, Hyowon Kim, Simon Lindberg, Andreas Wolfgang, Traian E Abrudan,
Thomas Eriksson, and Henk Wymeersch. Modeling and analysis of 6g joint localization and communication under hardware
impairments. arXiv preprint arXiv:2301.01042, 2023.