Title :

GLIP: Electromagnetic Field Exposure Map Completion by Deep Generative Networks

Author(s) :

Mallik, Mohammed [Auteur]
Institut National des Sciences Appliquées de Lyon [INSA Lyon]
Gaillot, Davy [Auteur]
Institut de Recherche sur les Composants logiciels et matériels pour l'Information et la Communication Avancée - UAR 3380 [IRCICA]
Télécommunication, Interférences et Compatibilité Electromagnétique - IEMN [TELICE - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Clavier, Laurent [Auteur]
Circuits Systèmes Applications des Micro-ondes - IEMN [CSAM - IEMN ]
Institut de Recherche sur les Composants logiciels et matériels pour l'Information et la Communication Avancée - UAR 3380 [IRCICA]
Centre for Digital Systems [CERI SN - IMT Nord Europe]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]

Conference title :

2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

City :

Valencia

Country :

Italie

Start date of the conference :

2024-09-02

Publisher :

IEEE

Publication date :

2024-05-06

HAL domain(s) :

Informatique [cs]

English abstract : [en]

<div><p>In Spectrum cartography (SC), the generation of exposure maps for radio frequency electromagnetic fields (RF-EMF) spans dimensions of frequency, space, and time, which relies on a sparse collection of sensor data, ...
Show more ><div><p>In Spectrum cartography (SC), the generation of exposure maps for radio frequency electromagnetic fields (RF-EMF) spans dimensions of frequency, space, and time, which relies on a sparse collection of sensor data, posing a challenging ill-posed inverse problem. Cartography methods based on models integrate designed priors, such as sparsity and low-rank structures, to refine the solution of this inverse problem. In our previous work, EMF exposure map reconstruction was achieved by Generative Adversarial Networks (GANs) where physical laws or structural constraints were employed as a prior, but they require a large amount of labeled data or simulated full maps for training to produce efficient results. In this paper, we present a method to reconstruct EMF exposure maps using only the generator network in GANs which does not require explicit training, thus overcoming the limitations of GANs, such as using reference full exposure maps. This approach uses a prior from sensor data as Local Image Prior (LIP) captured by deep convolutional generative networks independent of learning the network parameters from images in an urban environment. Experimental results show that, even when only sparse sensor data are available, our method can produce accurate estimates.</p></div>Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

European Project :

Beyond5G

Comment :

BEST PAPER AWARD

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL