Title :

EME-CNTK: Infinite Limits of Convolutional Neural Network for Urban Electromagnetic Field Exposure Reconstruction

Author(s) :

Mallik, Mohammed [Auteur correspondant]
Télécommunication, Interférences et Compatibilité Electromagnétique - IEMN [TELICE - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Allaert, Benjamin [Auteur]
Centre for Digital Systems [CERI SN - IMT Nord Europe]
Egea-Lopez, E. [Auteur]
Universidad Politécnica de Cartagena / Technical University of Cartagena [UPCT]
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]
Wiart, J. [Auteur]
Département Communications & Electronique [COMELEC]
Radio-Fréquences Microondes et Ondes Millimétriques [RFM2]
Chaire Modélisation, Caractérisation et Maîtrise des expositions aux ondes électromagnétiques [C2M]
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]

Journal title :

IEEE Access

Pages :

49476 - 49488

Publisher :

IEEE

Publication date :

2024-03-22

ISSN :

2169-3536

English keyword(s) :

5G EMF exposure
Kernel regression
Neural tangent kernel
Infinite width convolutional neural network
Semi-supervised learning

HAL domain(s) :

Informatique [cs]
Physique [physics]
Sciences de l'ingénieur [physics]

English abstract : [en]

Electromagnetic field (EMF) exposure has grown to be a critical concern as a consequence of the ongoing installation of fifth-generation cellular networks (5G). The lack of measurements makes it difficult to accurately ...
Show more >Electromagnetic field (EMF) exposure has grown to be a critical concern as a consequence of the ongoing installation of fifth-generation cellular networks (5G). The lack of measurements makes it difficult to accurately assess the EMF in a specific urban area, as Spectrum cartography (SC) relies on a set of measurements recorded by spatially distributed sensors for the generation of exposure maps. However, when the spatial sampling rate is limited, significant estimation errors occur. To overcome this issue, the exposure map estimation is addressed as a missing data imputation task. We compute a convolutional neural tangent kernel (CNTK) for an infinitely wide convolutional neural network whose training dynamics can be completely described by a closed-form formula. This CNTK is employed to impute the target matrix and estimate EMF exposure from few sensors sparsely located in an urban environment. Experimental results show that the kernel, even when only sparse sensor data are available, can produce accurate estimates. It is a promising solution for exposure map reconstruction that does not require large training sets. The proposed method is compared with other deep learning approaches and Gaussian Process regression.Show less >

Language :

Anglais

Popular science :

Non

ANR Project :

Pilotage et gouvernance du programme 5G et les réseaux du futur

Collections :

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

Source :

Harvested from HAL