(2023) An Exposimetric Electromagnetic Comparison of Mobile Phone Emissions: 5G versus 4G Signals Analyses by Means of Statistics and Convolutional Neural Networks Classification
Miclaus et al · 2023
View Original AbstractPeak EMF exposure from phones varies significantly between 4G and 5G networks depending on specific app usage patterns.
Plain English Summary
Romanian researchers used advanced signal analyzers to compare real-time electromagnetic emissions from phones running apps on 4G versus 5G networks. They measured peak exposure levels (not just averages) during file downloads, uploads, video streaming, and video calls at 10 cm distance. The study developed AI methods to classify these different emission patterns with high accuracy.
Why This Matters
This research represents a crucial shift in how we measure EMF exposure from mobile devices. Instead of relying on simplified average measurements, the scientists analyzed peak exposure levels and real-time signal variations during actual phone use. What this means for you is significant: your exposure varies dramatically based on which apps you're running and whether you're on 4G or 5G networks. The study's focus on specific usage scenarios like video calls and streaming reflects how we actually use our phones today, not the basic calling scenarios used in outdated safety testing. The researchers' ability to classify these different exposure patterns using AI suggests that 4G and 5G create distinctly different electromagnetic signatures in our environment.
Exposure Information
Specific exposure levels were not quantified in this study.
Show BibTeX
@article{2023_an_exposimetric_electromagnetic_comparison_of_mobile_phone_emissions_5g_versus_4g_signals_analyses_by_means_of_statistics_and_convolutional_neural_networks_classification_ce4696,
author = {Miclaus et al},
title = {(2023) An Exposimetric Electromagnetic Comparison of Mobile Phone Emissions: 5G versus 4G Signals Analyses by Means of Statistics and Convolutional Neural Networks Classification},
year = {2023},
doi = {10.3390/technologies11050113},
url = {https://bit.ly/3ParNO5},
}