Publications by authors named "Derugin E"
Article Synopsis
- - The study focuses on using thermoluminescence detectors (TL-DOS) to gather detailed information about radiation exposure, not just the dosage, which helps enhance radiation safety measures.
- - Researchers analyzed glow curves from these novel dosemeters using deep learning to accurately predict the date of a specific radiation exposure (10 mGy) over a 41-day monitoring period.
- - The deep learning algorithm achieves prediction accuracy of 2-5 days, and the study also assesses the significance of various input features using Shapley values, enhancing the understanding of how the neural network makes predictions.
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).
View Article and Find Full Text PDF