Share

Artificial Neural Network-Based Uplink Power Prediction From Multi-Floor Indoor Measurement Campaigns in 4G Networks.

Taghrid Mazloum, Shanshan Wang, Maryem Hamdi, Biruk Ashenafi Mulugeta, Joe Wiart

PAPERpubmedFrontiers in public health2021exposure assessmentEffect: unclearEvidence: Insufficient

Abstract

Paving the path toward the fifth generation (5G) of wireless networks with a huge increase in the number of user equipment has strengthened public concerns on human exposure to radio-frequency electromagnetic fields (RF EMFs). This requires an assessment and monitoring of RF EMF exposure, in an almost continuous way. Particular interest goes to the uplink (UL) exposure, assessed through the transmission power of the mobile phone, due to its close proximity to the human body. However, the UL transmit (TX) power is not provided by the off-the-shelf modem and RF devices. In this context, we first conduct measurement campaigns in a multi-floor indoor environment using a drive test solution to record both downlink (DL) and UL connection parameters for Long Term Evolution (LTE) networks. Several usage services (including WhatsApp voice calls, WhatsApp video calls, and file uploading) are investigated in the measurement campaigns. Then, we propose an artificial neural network (ANN) model to estimate the UL TX power, by exploiting easily available parameters such as the DL connection indicators and the information related to an indoor environment. With those easy-accessed input features, the proposed ANN model is able to obtain an accurate estimation of UL TX power with a mean absolute error (MAE) of 1.487 dB.

AI evidence extraction

At a glance
Study type
exposure assessment
Effect direction
unclear
Population
—
Sample size
—
Exposure
RF 100–3000 MHz
Evidence strength
Insufficient
Confidence: 74% · Peer-reviewed: yes

Main findings

Multi-floor indoor LTE measurement campaigns recorded DL and UL connection parameters across several services (WhatsApp voice calls, WhatsApp video calls, file uploading). An artificial neural network model using easily available DL indicators and indoor-environment information estimated UL TX power with a mean absolute error of 1.487 dB.

Outcomes measured

  • Uplink (UL) transmit (TX) power estimation/prediction accuracy (mean absolute error in dB)
  • Recorded downlink (DL) and UL connection parameters in multi-floor indoor LTE measurement campaigns

Limitations

  • No health outcomes were assessed
  • the work focuses on UL TX power estimation for exposure assessment.
  • Frequency band
  • participant characteristics
  • and sample size are not reported in the provided abstract.
  • Results are reported as prediction error (MAE) without additional performance metrics or external validation details in the provided abstract.

Suggested hubs

  • who-icnirp (0.7)
    Mentions public concerns and need for RF EMF exposure assessment/monitoring, but no direct WHO/ICNIRP content is provided.
View raw extracted JSON
{
  "study_type": "exposure_assessment",
  "exposure": {
    "band": "RF",
    "source": "mobile phone",
    "frequency_mhz": null,
    "sar_wkg": null,
    "duration": null
  },
  "population": null,
  "sample_size": null,
  "outcomes": [
    "Uplink (UL) transmit (TX) power estimation/prediction accuracy (mean absolute error in dB)",
    "Recorded downlink (DL) and UL connection parameters in multi-floor indoor LTE measurement campaigns"
  ],
  "main_findings": "Multi-floor indoor LTE measurement campaigns recorded DL and UL connection parameters across several services (WhatsApp voice calls, WhatsApp video calls, file uploading). An artificial neural network model using easily available DL indicators and indoor-environment information estimated UL TX power with a mean absolute error of 1.487 dB.",
  "effect_direction": "unclear",
  "limitations": [
    "No health outcomes were assessed; the work focuses on UL TX power estimation for exposure assessment.",
    "Frequency band, participant characteristics, and sample size are not reported in the provided abstract.",
    "Results are reported as prediction error (MAE) without additional performance metrics or external validation details in the provided abstract."
  ],
  "evidence_strength": "insufficient",
  "confidence": 0.74,
  "peer_reviewed_likely": "yes",
  "keywords": [
    "RF EMF exposure assessment",
    "uplink transmit power",
    "LTE",
    "indoor multi-floor measurements",
    "drive test",
    "artificial neural network",
    "WhatsApp voice call",
    "WhatsApp video call",
    "file uploading"
  ],
  "suggested_hubs": [
    {
      "slug": "who-icnirp",
      "weight": 0.2,
      "reason": "Mentions public concerns and need for RF EMF exposure assessment/monitoring, but no direct WHO/ICNIRP content is provided."
    }
  ]
}

AI can be wrong. Always verify against the paper.

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

Comments

Log in to comment.

No comments yet.

NNEMF synthesis

Synthesis pending.

Original record: rfsafe.org paper 5664

Artificial Neural Network-Based Uplink Power Prediction From Multi-Floor Indoor Measurement Campaigns in 4G Networks. · Non-native EMF