An Exposimetric Electromagnetic Comparison of Mobile Phone Emissions: 5G versus 4G Signals Analyses by Means of Statistics and Convolutional Neural Networks Classification

Abstract

Overview

To address the critical issue of non-thermal biological effects of microwaves, this study introduces new metrics and methodologies focusing on peak exposure rather than just average exposure times. It emphasizes analyzing real-life exposure conditions under various parameters with mobile applications on 4G and 5G networks.

Findings

• Introduction of amplitude-time analysis for specific real-life exposure conditions, diverging from simple comparison between general characteristics of 4G and 5G signals.
• Detailed analysis using signal and spectrum analyzers, with findings supported by statistical measurements like amplitude probability density (APD), cumulative distribution functions, and channel power measurements.
• Identification of elevated electric field strengths particularly in 5G emissions, with notable disparities arising during specific mobile application uses, potentially indicating higher exposure rates and subsequent health risks.

Advanced Detection Capabilities

The use of convolutional neural networks facilitates precise recognition and classification of emission types, enhancing understanding of dynamic human exposure.

Significant Observations

• Peak-to-average power ratios indicating potential risks related to higher energy absorption in body tissues, underlining the need for continued research into the health effects of 4G and 5G technologies.

Conclusion

The study offers substantial exposimetric analysis tools, highlighting intricate differences in user exposure across applications and network technologies. It suggests a nuanced understanding of EMF exposure effects, advocating for extended research based on these preliminary findings showing considerable exposure differences.