Submit to IJERPH Review for IJERPH Propose a Special Issue

Journal Menu

Journal Browser

Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of International Journal of Environmental Research and Public Health (ISSN 1660-4601). This special issue belongs to the section "Environmental Health".

Deadline for manuscript submissions: closed (1 September 2020) | Viewed by 22239

Share This Special Issue

Special Issue Editors

Dr. Gabriella Tognola

E-Mail Website
Guest Editor

CNR National Research Council, Insitute of Electronics, Computer and Telecommunications Engineering IEIIT, 20133 Milano, Italy
Interests: assessment of exposure to electromagnetic fields in humans; modelling of electromagnetic fields for biomedical applications

Dr. Emma Chiaramello

E-Mail Website
Guest Editor

Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), Italian National Research Council (CNR), 20133 Milano, Italy
Interests: electromagnetic fields (EMF) exposure assessment; computational dosimetry; stochastic dosimetry; uncertainty in EMF assessment
Special Issues, Collections and Topics in MDPI journals

Prof. Masao Taki

E-Mail
Guest Editor

National Institute of Information and Communications Technology (NICT)
Interests: electromagnetic fields (EMF); exposure assessment; numerical dosimetry; monitoring; safety guidelines

Prof. Joe Wiart

E-Mail Website
Guest Editor

Télécom ParisTech University
Interests: EMF exposure; experimental and numerical dosimetry; telecommunication; machine learning; uncertainty quantification; stochastic dosimetry

Special Issue Information

Dear Colleagues,

In addition to occupational environments or biomedical applications, exposure to electromagnetic fields (EMF) is also very common in everyday life as a result of the widespread and pervasive use of a variety of EMF sources, ranging from electric lines, electric appliances, wireless devices, mobile communication, etc. It is expected that EMF exposure will be increasing even more in the next years due to the growth of applications based on wireless communication for the exchange of information, such as Internet of Thing (IoT) devices and vehicular communication (vehicle-to-vehicle V2V or vehicle-to-infrastructure V2I).

The assessment of EMF exposure is of crucial importance to go deeper in understanding possible negative health effects, especially by studying exposure in real everyday conditions and in the general population. To achieve this, huge and expensive (in term of time and resources) exposure measurement campaigns to provide the data for the subsequent analyses must be performed or heavy numerical solutions to model exposure must be developed.

This Special Issue is open to scientific studies addressing the application of applied statistics, machine learning, and stochastic dosimetry for EMF exposure assessment. Machine Learning, stochastic dosimetry, and applied statistics are emerging techniques that complement classical exposure analyses, offering the advantage of being able to predict and model the exposure in more generalized environmental scenarios and not only for a particular case under study. This Special Issue is dedicated to works in any frequency area, from static fields up to exposures in the THz region, dealing with exposure assessment, dosimetry, hazard identification, and characterization, risk assessment.

Prof. Gabriella Tognola
Dr. Emma Chiaramello
Prof. Masao Taki
Prof. Joe Wiart
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Environmental Research and Public Health is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2500 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

EMF exposure assessment
Machine learning
Stochastic dosimetry
Applied statistics
Environmental health

Published Papers (6 papers)

Download All Papers

Research

19 pages, 2992 KiB

Open AccessArticle

Design of an Integrated Platform for Mapping Residential Exposure to Rf-Emf Sources

by Corentin Regrain, Julien Caudeville, René de Seze, Mohammed Guedda, Amirreza Chobineh, Philippe de Doncker, Luca Petrillo, Emma Chiaramello, Marta Parazzini, Wout Joseph, Sam Aerts, Anke Huss and Joe Wiart

Int. J. Environ. Res. Public Health 2020, 17(15), 5339; https://doi.org/10.3390/ijerph17155339 - 24 Jul 2020

Cited by 8 | Viewed by 2545

Abstract

Nowadays, information and communication technologies (mobile phones, connected objects) strongly occupy our daily life. The increasing use of these technologies and the complexity of network infrastructures raise issues about radiofrequency electromagnetic fields (Rf-Emf) exposure. Most previous studies have assessed individual exposure to Rf-Emf, and the next level is to assess populational exposure. In our study, we designed a statistical tool for Rf-Emf populational exposure assessment and mapping. This tool integrates geographic databases and surrogate models to characterize spatiotemporal exposure from outdoor sources, indoor sources, and mobile phones. A case study was conducted on a 100 × 100 m grid covering the 14th district of Paris to illustrate the functionalities of the tool. Whole-body specific absorption rate (SAR) values are 2.7 times higher than those for the whole brain. The mapping of whole-body and whole-brain SAR values shows a dichotomy between built-up and non-built-up areas, with the former displaying higher values. Maximum SAR values do not exceed 3.5 and 3.9 mW/kg for the whole body and the whole brain, respectively, thus they are significantly below International Commission on Non-Ionizing Radiation Protection (ICNIRP) recommendations. Indoor sources are the main contributor to populational exposure, followed by outdoor sources and mobile phones, which generally represents less than 1% of total exposure. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

► Show Figures

Figure 1

27 pages, 686 KiB

Open AccessArticle

Supervised Machine Learning Algorithms for Bioelectromagnetics: Prediction Models and Feature Selection Techniques Using Data from Weak Radiofrequency Radiation Effect on Human and Animals Cells

by Malka N. Halgamuge

Int. J. Environ. Res. Public Health 2020, 17(12), 4595; https://doi.org/10.3390/ijerph17124595 - 26 Jun 2020

Cited by 9 | Viewed by 5207

Abstract

The emergence of new technologies to incorporate and analyze data with high-performance computing has expanded our capability to accurately predict any incident. Supervised Machine learning (ML) can be utilized for a fast and consistent prediction, and to obtain the underlying pattern of the data better. We develop a prediction strategy, for the first time, using supervised ML to observe the possible impact of weak radiofrequency electromagnetic field (RF-EMF) on human and animal cells without performing in-vitro laboratory experiments. We extracted laboratory experimental data from 300 peer-reviewed scientific publications (1990–2015) describing 1127 experimental case studies of human and animal cells response to RF-EMF. We used domain knowledge, Principal Component Analysis (PCA), and the Chi-squared feature selection techniques to select six optimal features for computation and cost-efficiency. We then develop grouping or clustering strategies to allocate these selected features into five different laboratory experiment scenarios. The dataset has been tested with ten different classifiers, and the outputs are estimated using the k-fold cross-validation method. The assessment of a classifier’s prediction performance is critical for assessing its suitability. Hence, a detailed comparison of the percentage of the model accuracy (PCC), Root Mean Squared Error (RMSE), precision, sensitivity (recall), 1 − specificity, Area under the ROC Curve (AUC), and precision-recall (PRC Area) for each classification method were observed. Our findings suggest that the Random Forest algorithm exceeds in all groups in terms of all performance measures and shows AUC = 0.903 where k-fold = 60. A robust correlation was observed in the specific absorption rate (SAR) with frequency and cumulative effect or exposure time with SAR×time (impact of accumulated SAR within the exposure time) of RF-EMF. In contrast, the relationship between frequency and exposure time was not significant. In future, with more experimental data, the sample size can be increased, leading to more accurate work. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

► Show Figures

Figure 1

15 pages, 3524 KiB

Open AccessArticle

Sensor-Aided EMF Exposure Assessments in an Urban Environment Using Artificial Neural Networks

by Shanshan Wang and Joe Wiart

Int. J. Environ. Res. Public Health 2020, 17(9), 3052; https://doi.org/10.3390/ijerph17093052 - 28 Apr 2020

Cited by 20 | Viewed by 3027

Abstract

This paper studies the time and space mapping of the electromagnetic field (EMF) exposure induced by cellular base station antennas (BSA) using artificial neural networks (ANN). The reconstructed EMF exposure map (EEM) in urban environment is obtained by using data from EMF sensor networks, drive testing and information accessible in a public database, e.g., locations and orientations of BSA. The performance of EEM is compared with Exposure Reference Map (ERM) based on simulations, in which parametric path loss models are used to reflect the complexity of urban cities. Then, a new hybrid ANN, which has the advantage of sorting and utilizing inputs from simulations efficiently, is proposed. Using both hybrid ANN and conventional regression ANN, the EEM is reconstructed and compared to the ERM first by the reconstruction approach considering only EMF exposure assessed from sensor networks, where the required number of sensors towards good reconstruction is explored; then, a new reconstruction approach using the sensors information combined with EMF along few streets from drive testing. Both reconstruction approaches use simulations to mimic measurements. The influence of city architecture on EMF exposure reconstruction is analyzed and the addition of noise is considered to test the robustness of ANN as well. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

► Show Figures

Figure 1

11 pages, 613 KiB

Open AccessArticle

A Surrogate Model Based on Artificial Neural Network for RF Radiation Modelling with High-Dimensional Data

by Xi Cheng, Clément Henry, Francesco P. Andriulli, Christian Person and Joe Wiart

Int. J. Environ. Res. Public Health 2020, 17(7), 2586; https://doi.org/10.3390/ijerph17072586 - 09 Apr 2020

Cited by 3 | Viewed by 3428

Abstract

This paper focuses on quantifying the uncertainty in the specific absorption rate values of the brain induced by the uncertain positions of the electroencephalography electrodes placed on the patient’s scalp. To avoid running a large number of simulations, an artificial neural network architecture for uncertainty quantification involving high-dimensional data is proposed in this paper. The proposed method is demonstrated to be an attractive alternative to conventional uncertainty quantification methods because of its considerable advantage in the computational expense and speed. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

► Show Figures

Figure 1

13 pages, 629 KiB

Open AccessArticle

Discrepancies of Measured SAR between Traditional and Fast Measuring Systems

by Zicheng Liu, Djamel Allal, Maurice Cox and Joe Wiart

Int. J. Environ. Res. Public Health 2020, 17(6), 2111; https://doi.org/10.3390/ijerph17062111 - 22 Mar 2020

Cited by 3 | Viewed by 3714

Abstract

Human exposure to mobile devices is traditionally measured by a system in which the human body (or head) is modelled by a phantom and the energy absorbed from the device is estimated based on the electric fields measured with a single probe. Such a system suffers from low efficiency due to repeated volumetric scanning within the phantom needed to capture the absorbed energy throughout the volume. To speed up the measurement, fast SAR (specific absorption rate) measuring systems have been developed. However, discrepancies of measured results are observed between traditional and fast measuring systems. In this paper, the discrepancies in terms of post-processing procedures after the measurement of electric field (or its amplitude) are investigated. Here, the concerned fast measuring system estimates SAR based on the reconstructed field of the region of interest while the amplitude and phase of the electric field are measured on a single plane with a probe array. The numerical results presented indicate that the fast SAR measuring system has the potential to yield more accurate estimations than the traditional system, but no conclusion can be made on which kind of system is superior without knowledge of the field-reconstruction algorithms and the emitting source. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

► Show Figures

Figure 1

14 pages, 351 KiB

Open AccessArticle

Cluster Analysis of Residential Personal Exposure to ELF Magnetic Field in Children: Effect of Environmental Variables

by Gabriella Tognola, Emma Chiaramello, Marta Bonato, Isabelle Magne, Martine Souques, Serena Fiocchi, Marta Parazzini and Paolo Ravazzani

Int. J. Environ. Res. Public Health 2019, 16(22), 4363; https://doi.org/10.3390/ijerph16224363 - 08 Nov 2019

Cited by 10 | Viewed by 2171

Abstract

Personal exposure to Extremely Low Frequency Magnetic Fields (ELF MF) in children is a very timely topic. We applied cluster analysis to 24 h indoor personal exposures of 884 children in France to identify possible common patterns of exposures. We investigated how electric networks near child home and other variables potentially affecting residential exposure, such as indoor sources of ELF MF, the age and type of the residence and family size, characterized the magnetic field exposure patterns. We identified three indoor personal exposure patterns: children living near overhead lines of high (63–150 kV), extra-high (225 kV) and ultra-high voltage (400 kV) were characterized by the highest exposures; children living near underground networks of low (400 V) and mid voltage (20 kV) and substations (20 kV/400 V) were characterized by mid exposures; children living far from electric networks had the lowest level of exposure. The harmonic component was not relevant in discriminating the exposure patterns, unlike the 50 Hz or broadband (40–800 Hz) component. Children using electric heating appliances, or living in big buildings or in larger families had generally a higher level of personal indoor exposure. Instead, the age of the residence was not relevant in differentiating the exposure patterns. Full article

(This article belongs to the Special Issue Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment)

Journal Menu

Journal Browser

Machine Learning, Stochastic Modelling and Applied Statistics for EMF Exposure Assessment

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (6 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI