Generic neural network model for estimating exposure levels in industrial environments

Abstract

J Radiol Prot . 2026 May 22;46(2). doi: 10.1088/1361-6498/ae6c32. Generic neural network model for estimating exposure levels in industrial environments David Plets 1, Christos Apostolidis 2, Shanshan Wang 3, Blaž Valič 4, Luc Martens 1, Theodoros Samaras 2, Peter Gajšek 4 Affiliations Expand PMID: 42119573 DOI: 10.1088/1361-6498/ae6c32 Abstract This study describes a neural network-based method for estimating exposure levels in industrial environments, without requiring detailed technical inputs, allowing usage of the model by layman people or by workers active in these areas. A pipeline based on Blender environments and MATLAB ray-tracing simulations is created and after defining a set of 11 candidate input parameters for the model, more than 20 000 different wireless configurations are simulated, varying the different environmental and wireless input parameters. A correlation analysis shows that main inputs influencing the exposure levels in the industrial area are the transmit power of the antennas, the density of clutter in the area, the density of transmitters in the area, and the height and location of the transmitters. A multi-layer fully connected neural network regression model is developed to predict median (E50) and 95th percentile (E95) exposure levels in industrial areas. Testing the obtained model on an unseen dataset of environments withE50values between 0 and 3.25 V m-1andE95values between 0 and 7 V m-1, demonstrates the good prediction performance of the model: root-mean-square error values below 0.173 V m-1andR2values above 95% are obtained. Subsequently, the model is validated with measurement data collected in three distinct realistic industrial environments. The average absolute deviation of the model predictions with respect to the measurements is limited to 20.4%. This novel and broadly accessible approach demonstrates that it is possible to reliably estimate exposure levels in realistic environments without having to rely on external experts or on dedicated complex software. Keywords: EMF RF exposure; industrial environments; industry 4.0; modelling; neural networks; validation.

AI evidence extraction

Main findings

The neural network model predicted median and 95th percentile exposure levels with root-mean-square errors below 0.173 V/m and R2 values above 95%. Validation with measurements in three industrial environments showed an average absolute deviation of 20.4%.

Outcomes measured

• median (E50) exposure level in V/m
• 95th percentile (E95) exposure level in V/m

Limitations

• Model predictions validated only in three industrial environments
• Exposure frequency and SAR not specified
• No health outcomes assessed

Suggested hubs

• occupational-exposure (0.9)
  Study focuses on estimating EMF exposure levels in industrial workplaces relevant to occupational exposure.

{
    "study_type": "exposure_assessment",
    "exposure": {
        "band": null,
        "source": "industrial wireless transmitters",
        "frequency_mhz": null,
        "sar_wkg": null,
        "duration": null
    },
    "population": "workers in industrial environments",
    "sample_size": null,
    "outcomes": [
        "median (E50) exposure level in V/m",
        "95th percentile (E95) exposure level in V/m"
    ],
    "main_findings": "The neural network model predicted median and 95th percentile exposure levels with root-mean-square errors below 0.173 V/m and R2 values above 95%. Validation with measurements in three industrial environments showed an average absolute deviation of 20.4%.",
    "effect_direction": "no_effect",
    "limitations": [
        "Model predictions validated only in three industrial environments",
        "Exposure frequency and SAR not specified",
        "No health outcomes assessed"
    ],
    "evidence_strength": "moderate",
    "confidence": 0.6999999999999999555910790149937383830547332763671875,
    "peer_reviewed_likely": "yes",
    "keywords": [
        "EMF RF exposure",
        "industrial environments",
        "modelling",
        "neural networks",
        "validation"
    ],
    "suggested_hubs": [
        {
            "slug": "occupational-exposure",
            "weight": 0.90000000000000002220446049250313080847263336181640625,
            "reason": "Study focuses on estimating EMF exposure levels in industrial workplaces relevant to occupational exposure."
        }
    ]
}

Comments

Log in to comment.

No comments yet.