Stochastic Dosimetry and Machine Learning: Innovative Approaches for Facing Challenges in Exposure Assessment in Realistic Scenarios

Innovative approaches, such as stochastic dosimetry and Machine Learning, can be complementary to traditional methods for electromagnetic field (EMF) exposure assessment, overcoming limitations and allowing extraction of new/deeper information. In this study, two examples of innovative EMF exposure assessment approaches are presented: (i) a stochastic approach based on low rank tensor approximations to assess indoor exposure to WLAN access point with unknown location and (ii) an application of Machine Learning to characterize indoor residential exposures to ELF magnetic field in children by considering the type of electric networks near the child home, the age and type of the child home, the type of heating and the family size.

[1]  Joe Wiart,et al.  Stochastic Dosimetry Based on Low Rank Tensor Approximations for the Assessment of Children Exposure to WLAN Source , 2018, IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology.

[2]  Jacques Lambrozo,et al.  Exposure of children to extremely low frequency magnetic fields in France: Results of the EXPERS study , 2017, Journal of Exposure Science and Environmental Epidemiology.

[3]  C Gabriel,et al.  The dielectric properties of biological tissues: I. Literature survey. , 1996, Physics in medicine and biology.

[4]  Niels Kuster,et al.  Development of a new generation of high-resolution anatomical models for medical device evaluation: the Virtual Population 3.0 , 2014, Physics in medicine and biology.

[5]  Joe Wiart,et al.  Surrogate models for uncertainty quantification: An overview , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[6]  Peter J. Rousseeuw,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1990 .

[7]  Joe Wiart,et al.  Children exposure to femtocell in indoor environments estimated by sparse low-rank tensor approximations , 2018, Ann. des Télécommunications.

[8]  Gabriella Tognola,et al.  Cluster Analysis of Residential Personal Exposure to ELF Magnetic Field in Children: Effect of Environmental Variables , 2019, International journal of environmental research and public health.

[9]  Joe Wiart,et al.  Statistical analysis and surrogate modeling of indoor exposure induced from a WLAN source , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[10]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[11]  Joe Wiart,et al.  Radio-Frequency Human Exposure Assessment: From Deterministic to Stochastic Methods , 2016 .

[12]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[13]  Joe Wiart,et al.  Stochastic Dosimetry for Radio-Frequency Exposure Assessment in Realistic Scenarios , 2018, Uncertainty Modeling for Engineering Applications.

[14]  W. Marsden.  I and J , 2012 .

[15]  Bruno Sudret,et al.  Polynomial meta-models with canonical low-rank approximations: Numerical insights and comparison to sparse polynomial chaos expansions , 2015, J. Comput. Phys..

[16]  Gabriella Tognola,et al.  Use of Machine Learning in the Analysis of Indoor ELF MF Exposure in Children , 2019, International journal of environmental research and public health.

[17]  L. Le Brusquet,et al.  Methodology of a study on the French population exposure to 50 Hz magnetic fields. , 2010, Radiation protection dosimetry.