Machine Learning Approach for Ground-Level Estimation of Electromagnetic Radiation in the Near Field of 5G Base Stations

Applied Sciences · 2025 · Unclear · Insufficient evidence

← Research stream

UnclearInsufficient evidencePaper 2582

Study snapshot

PublicationApplied Sciences · 2025

Study typeengineering

Reported directionUnclear

Evidence ratingInsufficient

Abstract

Category: Electromagnetic Field Safety, Machine Learning Tags: 5G, electromagnetic radiation, machine learning, near field, exposure assessment, base stations, radiofrequency safety DOI: 10.3390/app15137302 URL: mdpi.com Overview Electromagnetic radiation measurement and management have become essential in the cost-effective deployment of fifth-generation (5G) infrastructure, particularly as 5G emerges as a service-oriented network. The extensive placement of base stations operating in the millimeter-wave range allows 5G to address high bandwidth demands. Findings - To assess ground-level electromagnetic radiation levels close to 5G base stations, a unique machine-learning-based approach is proposed in this study. - The machine learning model is trained using comprehensive data from numerous 5G base stations and effectively estimates electric field strength across various locations and operational scenarios. - Key input parameters include: - Antenna transmit power - Antenna gain - Terminal service modes - Number of 5G terminals - Distance from terminals to base station - Environmental complexity - Experimental results demonstrate the technique’s feasibility and effectiveness with a mean absolute percentage error (MAPE) of about 5.89%, indicating high reliability. - The developed approach is significantly less expensive than direct on-site measurements. Conclusion The estimates provided by the model can help reduce testing costs and provide practical guidance for optimal base station placement. This can enhance management of electromagnetic radiation from 5G base stations and facilitate the optimization of radio wave coverage. It is vital to note that careful management of electromagnetic fields is necessary due to potential links to health risks—comprehensive assessment and mitigation strategies are essential in 5G deployment.

Machine Enhanced Logic

AI evidence extraction

Structured fields below were generated from the paper’s abstract and metadata to make the evidence easier to inspect. Automated extraction may be incomplete or incorrect; verify important details against the original paper.

Study typeengineering

Effect directionunclear

PopulationNot supplied

Sample sizeNot supplied

ExposuremmWave

Evidence strengthInsufficientConfidence: 74% · Peer reviewed: yes

Main findings

The study proposes a machine-learning approach to estimate ground-level electric field strength near 5G base stations using inputs such as transmit power, antenna gain, service modes, number of terminals, distance, and environmental complexity. Experimental results report a mean absolute percentage error of about 5.89%, and the approach is described as less expensive than direct on-site measurements.

Outcomes measured

Ground-level electric field strength estimation near 5G base stations
Model prediction accuracy (mean absolute percentage error, MAPE)
Cost reduction vs direct on-site measurements

View raw extracted JSON

{
  "study_type": "engineering",
  "exposure": {
    "band": "mmWave",
    "source": "5G base station",
    "frequency_mhz": null,
    "sar_wkg": null,
    "duration": null
  },
  "population": null,
  "sample_size": null,
  "outcomes": [
    "Ground-level electric field strength estimation near 5G base stations",
    "Model prediction accuracy (mean absolute percentage error, MAPE)",
    "Cost reduction vs direct on-site measurements"
  ],
  "main_findings": "The study proposes a machine-learning approach to estimate ground-level electric field strength near 5G base stations using inputs such as transmit power, antenna gain, service modes, number of terminals, distance, and environmental complexity. Experimental results report a mean absolute percentage error of about 5.89%, and the approach is described as less expensive than direct on-site measurements.",
  "effect_direction": "unclear",
  "limitations": [],
  "evidence_strength": "insufficient",
  "confidence": 0.74,
  "peer_reviewed_likely": "yes",
  "keywords": [
    "5G",
    "millimeter-wave",
    "base stations",
    "near field",
    "exposure assessment",
    "electric field strength",
    "machine learning",
    "electromagnetic radiation",
    "radiofrequency safety"
  ],
  "suggested_hubs": [
    {
      "slug": "5g-policy",
      "weight": 0.55,
      "reason": "Focuses on 5G base stations and management/assessment of EMF exposure."
    }
  ]
}

AI can be wrong. Always verify against the paper.

AI-extracted fields are generated from the abstract and metadata and may be incomplete or incorrect. This material is for informational purposes and is not medical advice.

Identifiers and source

DOI: 10.3390/app15137302
PubMed: Not supplied

Read the original paper →

Related papers

← Back to the Research Library