Postdoctoral researcher in AI-based channel estimation and spectrum detection algorithms for realistic channel

L'Université Gustave Eiffel, modèle innovant d'université rassemblant le triptyque université, écoles et organisme de recherche, dispose de plusieurs campus de formation et de recherche implantés sur le territoire national.

L'établissement compte plus de 15000 étudiants et plus de 3000 personnels enseignant (e)s-chercheur(e)s, chercheur(e)s et personnels d'appui au sein de 33 laboratoires, 15 composantes de formation ainsi qu'au sein de services support et de soutien.

L'université œuvre dans de nombreux domaines de recherche et représente à elle seule un quart de la recherche française sur les villes de demain. Elle regroupe des compétences pluridisciplinaires pour conduire des recherches de qualité au service de la société, proposer des formations adaptées au monde socio-économique et accompagner les politiques publiques.

L'Université Gustave Eiffel est également la première université française en apprentissage et forme jeunes, salariés, ou citoyens à tous les niveaux ; apporte des éclairages scientifiques à l'ensemble de la société et vise à contribuer in fine à l'élévation du niveau de qualification de tous.

Visionner le film de présentation :

AI-based algorithms require a large amount of data to train deep learning (DL) models. In addition, the data used for training can be derived from models and must be matched with data from real scenarios. The term data refers here to the radio channel data, in millimeter wave. The aim of this work is twofold. Firstly, to generate sufficient data at the output of the channel in order to train the DL models. We therefore need to generate new data from the database of measured channels (from ANR projects). Two strategies will be considered. The first will be based on the classic statistical generation of channels used in telecommunications, while the second will consider a very new approach using GAN (generative adversial network), which is well known in the field of image processing. The generated channel data will then be used first for training and then for evaluating the various AI-based channel estimation and spectrum detection algorithms in a more realistic context, corresponding to the measured channel data. The position is open in the framework of the Rgional project IMITECH pilar 4 and also in collaboration with IMT-Atlantique in Brest.

Required skills:

• Experience and taste for mathematics developments, statistical modelling and Deep learning methods
• Knowledge of ray-tracing based simulation tools will be highly appreciated
• Strong ability in computer programming (Matlab, C, C++, Python, etc.)
• Ability to communicate and disseminate scientific results
• English written and spoken
• Rigour and autonomy

Education and professional experience:

• PhD degree in wireless communications, signal processing applied to wireless communications

Environment, work context, reporting structure:

The position is open in the framework of the Regional project IMITECH pilar 4 and it will be in collaboration with IMT-Atlantique in Brest. The candidate will be supervised directly by Marion Berbineau, research Director and Yann Cocheril, laboratory Director will be the line manager.

Knowledge: wireless communications, radiowave propagation, mathematics, AI algorithms, English (written, spoken), scientific programming

Expertise: Ray-tracing simulation, Strong ability in computer programming (Matlab, C, C++, Python, etc.), experience with AI algorithms in wireless communications

Attitude: Ability to work in a team, ability to communicate and disseminate scientific results, organisation, rigour and autonomy, curiosity for new research topics

LEOST

Campus de Lille

Contractuel uniquement