Use of Machine Learning for the Estimation of Down- and Up-Link Field Exposure in Multi-Source Indoor WiFi Scenarios

2021 · Unclear · Insufficient evidence

← Research stream

UnclearInsufficient evidencePaper 1091

Study snapshot

Publicationmanual · 2021

Study typeengineering

Reported directionUnclear

Evidence ratingInsufficient

Abstract

Use of Machine Learning for the Estimation of Down- and Up-Link Field Exposure in Multi-Source Indoor WiFi Scenarios Gabriella Tognola, David Plets, Emma Chiaramello, Silvia Gallucci, Marta Bonato, Serena Fiocchi, Marta Parazzini, Luc Martens, Wout Joseph, Paolo Ravazzani. Use of Machine Learning for the Estimation of Down- and Up-Link Field Exposure in Multi-Source Indoor WiFi Scenarios. Bioelectromagnetics. 2021 Jul 23. doi: 10.1002/bem.22361. Abstract A novel Machine Learning (ML) method based on Neural Networks (NN) is proposed to assess radio-frequency (RF) exposure generated by WiFi sources in indoor scenarios. The aim was to build an NN capable of addressing the complexity and variability of real-life exposure setups, including the effects of not only down-link transmission access points (APs) but also up-link transmission by different sources (e.g. laptop, printers, tablets, and smartphones). The NN was fed with easy to be found data, such as the position and type of WiFi sources (APs, clients, and other users) and the position and material characteristics (e.g. penetration loss) of walls. The NN model was assessed using an additional new layout, distinct from that one used to build and optimize the NN coefficients. The NN model achieved a remarkable field prediction accuracy across exposure conditions in both layouts, with a median prediction error of -0.4 to 0.6 dB and a root mean square error of 2.5-5.1 dB, compared with the target electric field estimated by a deterministic indoor network planner. The proposed approach performs well for the different layouts and is thus generally used to assess RF exposure in indoor scenarios. Open access paper: onlinelibrary.wiley.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

Evidence strengthInsufficientConfidence: 78% · Peer reviewed: yes

Main findings

A neural-network-based machine learning method was proposed to estimate RF exposure from multiple indoor WiFi sources, including down-link access points and up-link client devices. When evaluated on an additional distinct layout, the model showed median prediction error of -0.4 to 0.6 dB and root mean square error of 2.5–5.1 dB versus target electric fields estimated by a deterministic indoor network planner.

Outcomes measured

Electric field exposure estimation/prediction accuracy for indoor WiFi scenarios (down-link and up-link)

Limitations

Frequency and other detailed exposure parameters (e.g., specific WiFi bands) not stated in the abstract
Target electric field values were based on a deterministic indoor network planner rather than direct measurements (as described in the abstract)
No health outcomes assessed; study focuses on exposure estimation methodology

View raw extracted JSON

{
  "study_type": "engineering",
  "exposure": {
    "band": "RF",
    "source": "wi-fi",
    "frequency_mhz": null,
    "sar_wkg": null,
    "duration": null
  },
  "population": null,
  "sample_size": null,
  "outcomes": [
    "Electric field exposure estimation/prediction accuracy for indoor WiFi scenarios (down-link and up-link)"
  ],
  "main_findings": "A neural-network-based machine learning method was proposed to estimate RF exposure from multiple indoor WiFi sources, including down-link access points and up-link client devices. When evaluated on an additional distinct layout, the model showed median prediction error of -0.4 to 0.6 dB and root mean square error of 2.5–5.1 dB versus target electric fields estimated by a deterministic indoor network planner.",
  "effect_direction": "unclear",
  "limitations": [
    "Frequency and other detailed exposure parameters (e.g., specific WiFi bands) not stated in the abstract",
    "Target electric field values were based on a deterministic indoor network planner rather than direct measurements (as described in the abstract)",
    "No health outcomes assessed; study focuses on exposure estimation methodology"
  ],
  "evidence_strength": "insufficient",
  "confidence": 0.78,
  "peer_reviewed_likely": "yes",
  "keywords": [
    "machine learning",
    "neural networks",
    "RF exposure",
    "WiFi",
    "indoor scenarios",
    "downlink",
    "uplink",
    "electric field",
    "exposure assessment"
  ],
  "suggested_hubs": [
    {
      "slug": "school-wi-fi",
      "weight": 0.55,
      "reason": "Focuses on indoor WiFi RF exposure estimation; could be relevant to WiFi-in-indoor-environments discussions."
    }
  ]
}

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: 10.1002/bem.22361
PubMed: Not supplied

Read the original paper →

Related papers

← Back to the Research Library