RF Safe

Study on field strength prediction using different models on time series from urban continuous RF-

Expert Systems with Applications · 2025 · Unclear · Insufficient evidence

← Research stream
UnclearInsufficient evidencePaper 184

Using two-year RF-EMF monitoring time series from EMF-sensitive urban areas in Novi Sad (two kindergartens and an elementary school), six prediction models (SARIMA, CNN, LSTM, ELM, PLS, Transformer) were compared. The partial least squares (PLS) model showed …

Study snapshot

PublicationExpert Systems with Applications · 2025
Study typeengineering
Reported directionUnclear
Evidence ratingInsufficient

Abstract

Study on field strength prediction using different models on time series from urban continuous RF- EMF monitoring Song X, Feng W, Yang C, Djuric N, Kljajic D, Djuric S. Study on field strength prediction using different models on time series from urban continuous RF-EMF monitoring. Expert Systems with Applications. 2025. doi: 10.1016/j.eswa.2025.126963. Abstract State-of-the-art electromagnetic field (EMF) monitoring networks, such as the latest one – the Serbian EMF RATEL system, are able to provide continuous and daily monitoring of radio-frequency (RF) EMF levels, which is especially important for urban areas where people may spend many hours and, consequently, experience increased sensitivity to RF-EMF exposure. By generating considerable time series sets of RF-EMF data, these monitoring networks are initiating a new research topic – near-future RF-EMF prediction, which is valuable for a number of public health activities, from supplementing EMF monitoring in high-risk areas, to proactively reducing exposure times, and towards advancing pre-testing of EMF compliance. This paper investigates the impact of different models on the prediction of field strength in urban environments, where Seasonal Auto-Regressive Integrated Moving Average (SARIMA), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Extreme Learning Machine (ELM), Partial Least Squares Regression (PLS) and Transformer models are considered. The prediction performance of each model is analyzed on a case study of EMF-sensitive areas in the Serbian city of Novi Sad, i.e., two kindergartens and an elementary school; however, the established framework has strong potential for generalization to other urban environments. Based on two-year long monitoring data sets, a comprehensive comparison of the six models on prediction accuracy, performance degradation rate, extreme value prediction accuracy, and training time is made, showing that the PLS model outperforms other models in predicting EMF exposure. This preliminary study may be a valuable reference for large- scale deployment in real-time monitoring systems for public health protection and may trigger additional research on this ultimate EMF topic. sciencedirect.com

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
ExposureRF · continuous daily monitoring; two-year monitoring data sets
Evidence strengthInsufficientConfidence: 74% · Peer reviewed: yes

Main findings

Using two-year RF-EMF monitoring time series from EMF-sensitive urban areas in Novi Sad (two kindergartens and an elementary school), six prediction models (SARIMA, CNN, LSTM, ELM, PLS, Transformer) were compared. The partial least squares (PLS) model showed the best performance for predicting EMF exposure (field strength) across the evaluated metrics.

Outcomes measured

  • RF-EMF field strength prediction accuracy
  • performance degradation rate
  • extreme value prediction accuracy
  • training time

Limitations

  • Frequency range and measurement units for field strength are not specified in the abstract.
  • No quantitative performance results (e.g., error metrics) are provided in the abstract.
  • Study is described as preliminary and based on a case study of three locations in one city.
View raw extracted JSON
{
  "study_type": "engineering",
  "exposure": {
    "band": "RF",
    "source": "urban continuous RF-EMF monitoring network (Serbian EMF RATEL system)",
    "frequency_mhz": null,
    "sar_wkg": null,
    "duration": "continuous daily monitoring; two-year monitoring data sets"
  },
  "population": null,
  "sample_size": null,
  "outcomes": [
    "RF-EMF field strength prediction accuracy",
    "performance degradation rate",
    "extreme value prediction accuracy",
    "training time"
  ],
  "main_findings": "Using two-year RF-EMF monitoring time series from EMF-sensitive urban areas in Novi Sad (two kindergartens and an elementary school), six prediction models (SARIMA, CNN, LSTM, ELM, PLS, Transformer) were compared. The partial least squares (PLS) model showed the best performance for predicting EMF exposure (field strength) across the evaluated metrics.",
  "effect_direction": "unclear",
  "limitations": [
    "Frequency range and measurement units for field strength are not specified in the abstract.",
    "No quantitative performance results (e.g., error metrics) are provided in the abstract.",
    "Study is described as preliminary and based on a case study of three locations in one city."
  ],
  "evidence_strength": "insufficient",
  "confidence": 0.74,
  "peer_reviewed_likely": "yes",
  "keywords": [
    "RF-EMF",
    "field strength prediction",
    "time series",
    "urban monitoring",
    "EMF RATEL",
    "SARIMA",
    "CNN",
    "LSTM",
    "Extreme Learning Machine",
    "Partial Least Squares Regression",
    "Transformer",
    "Novi Sad",
    "kindergarten",
    "elementary school"
  ],
  "suggested_hubs": [
    {
      "slug": "school-wi-fi",
      "weight": 0.42,
      "reason": "Case study includes two kindergartens and an elementary school (EMF-sensitive areas), though the RF sources are not specified as Wi‑Fi."
    }
  ]
}
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: 10.1016/j.eswa.2025.126963
PubMed: Not supplied

Read the original paper →

Related papers

← Back to the Research Library