No more glowing in the dark: How deep learning improves exposure date estimation in thermoluminescence dosimetry
| Autor: | Jens Weingarten, Florian Mentzel, Jörg Walbersloh, Hannah Jansen, Olaf Nackenhorst, Evelin Derugin, Kevin Kröninger |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Materials science Dosimeter Artificial neural network business.industry Deep learning Detector Public Health Environmental and Occupational Health FOS: Physical sciences General Medicine Physics - Medical Physics Convolutional neural network Confidence interval Machine Learning (cs.LG) Deep Learning Optics Humans Thermoluminescent Dosimetry Thermoluminescence dosimetry Artificial intelligence Irradiation Medical Physics (physics.med-ph) business Waste Management and Disposal |
| DOI: | 10.48550/arxiv.2106.07592 |
| Popis: | The time- or temperature-resolved detector signal from a thermoluminescence dosimeter can reveal additional information about circumstances of an exposure to ionising irradiation. We present studies using deep neural networks to estimate the date of a single irradiation with 12 mSv within a monitoring interval of 42 days from glow curves of novel TL-DOS personal dosimeters developed by the Materialprüfungsamt NRW in cooperation with TU Dortmund University. Using a deep convolutional network, the irradiation date can be predicted from raw time-resolved glow curve data with an uncertainty of roughly 1–2 days on a 68% confidence level without the need for a prior transformation into temperature space and a subsequent glow curve deconvolution (GCD). This corresponds to a significant improvement in prediction accuracy compared to a prior publication, which yielded a prediction uncertainty of 2–4 days using features obtained from a GCD as input to a neural network. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|