Semi-empirical Model of Global Exposure using Stochastic Geometry

Gontier, Quentin; Petrillo, Luca; Rottenberg, François; Horlin, François; Wiart, Joe; Oestges, Claude; Doncker, Philippe De

doi:10.1109/iccworkshops50388.2021.9473645

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous works have used it, including localization, automobile radar [31], and cumulated interference power [32]. Stochastic geometry is a useful tool to provide the mean exposure or Cumulative Distribution Function (CDF) of exposure [33]. However, this estimated information is not directly related to the spatial location of the user or the specific spot to be studied.…”

Section: B Stochastic Geometry Approachmentioning

confidence: 99%

See 1 more Smart Citation

Infinite Limits of Convolutional Neural Network for Urban Electromagnetic Field Exposure Reconstruction

Mallik,

Allaert,

Egea-Lopez

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Electromagnetic field exposure (EMF) 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. 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 a few sensor-measured values 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 machine learning approaches and Gaussian Process regression.INDEX TERMS 5G EMF exposure, kernel regression, neural tangent kernel, infinite width convolutional neural network, semi-supervised learning.

show abstract

Section: B Stochastic Geometry Approachmentioning

confidence: 99%

“…However, this estimated information is not directly related to the spatial location of the user or the specific spot to be studied. Measurements obtained from a drive test are used to parameterize the models [33]- [35] and the outcome is a single map representing the mean exposure rather than a dynamic map.…”

Section: B Stochastic Geometry Approachmentioning

confidence: 99%