Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry

This paper explores the implementation of machine learning-based algorithms for TL dose assessment. It focuses on the radiation field classification, performance quotient evaluation, and shallow and deep dose equivalent assessment of ANN and LGBM, in comparison to the traditional method of DT. We ev...

Full description

Saved in:
Bibliographic Details
Main Authors: Soohyeok Lee, Hyoungtaek Kim, Hwijoon Jung, Kyung Taek Lim
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Nuclear Engineering and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1738573324004091
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165807864741888
author Soohyeok Lee
Hyoungtaek Kim
Hwijoon Jung
Kyung Taek Lim
author_facet Soohyeok Lee
Hyoungtaek Kim
Hwijoon Jung
Kyung Taek Lim
author_sort Soohyeok Lee
collection DOAJ
description This paper explores the implementation of machine learning-based algorithms for TL dose assessment. It focuses on the radiation field classification, performance quotient evaluation, and shallow and deep dose equivalent assessment of ANN and LGBM, in comparison to the traditional method of DT. We evaluate these algorithms based on the element response data measured by TLD. A data set was built for training, and the base element responses of test categories were amplified, and normalized to 1 mSv Cs-137 within the range of ±3 %. Both algorithms consist of five subset models for classifying radiation fields and identifying ratios of mixed fields. The LGBM showed the best accuracy in classifying considered radiation fields and the lowest performance quotients. By comparing the tolerance levels of deep dose and shallow dose equivalents among the three algorithms, the LGBM yields the smallest difference between the predicted and true dose equivalents. This smaller difference implies the LGBM offers the least bias and standard deviation in the expected value, giving higher accuracy and precision in dose assessment over the traditional DT method. The findings from this study further contribute to the adoption of ML-based algorithms for TL dose assessment, underscoring its importance in the field.
format Article
id doaj-art-08ccc6a66d3742b5b808c5f32beeca64
institution Kabale University
issn 1738-5733
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Nuclear Engineering and Technology
spelling doaj-art-08ccc6a66d3742b5b808c5f32beeca642024-11-17T04:51:42ZengElsevierNuclear Engineering and Technology1738-57332024-12-01561254145421Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetrySoohyeok Lee0Hyoungtaek Kim1Hwijoon Jung2Kyung Taek Lim3Department of Quantum and Nuclear Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul, 05006, Republic of KoreaRadiation Safety Management Division, Korea Atomic Energy Research Institute, Daedeok-daero 989-111. Yuseong-gu, Daejeon, 34057, Republic of KoreaDepartment of Quantum and Nuclear Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul, 05006, Republic of KoreaDepartment of Quantum and Nuclear Engineering, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul, 05006, Republic of Korea; Corresponding author.This paper explores the implementation of machine learning-based algorithms for TL dose assessment. It focuses on the radiation field classification, performance quotient evaluation, and shallow and deep dose equivalent assessment of ANN and LGBM, in comparison to the traditional method of DT. We evaluate these algorithms based on the element response data measured by TLD. A data set was built for training, and the base element responses of test categories were amplified, and normalized to 1 mSv Cs-137 within the range of ±3 %. Both algorithms consist of five subset models for classifying radiation fields and identifying ratios of mixed fields. The LGBM showed the best accuracy in classifying considered radiation fields and the lowest performance quotients. By comparing the tolerance levels of deep dose and shallow dose equivalents among the three algorithms, the LGBM yields the smallest difference between the predicted and true dose equivalents. This smaller difference implies the LGBM offers the least bias and standard deviation in the expected value, giving higher accuracy and precision in dose assessment over the traditional DT method. The findings from this study further contribute to the adoption of ML-based algorithms for TL dose assessment, underscoring its importance in the field.http://www.sciencedirect.com/science/article/pii/S1738573324004091Dose assessment algorithmANNLightGBMTLDMachine LearningDosimetry
spellingShingle Soohyeok Lee
Hyoungtaek Kim
Hwijoon Jung
Kyung Taek Lim
Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
Nuclear Engineering and Technology
Dose assessment algorithm
ANN
LightGBM
TLD
Machine Learning
Dosimetry
title Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
title_full Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
title_fullStr Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
title_full_unstemmed Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
title_short Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry
title_sort comparative analysis of machine learning based dose assessment algorithms for tl dosimetry
topic Dose assessment algorithm
ANN
LightGBM
TLD
Machine Learning
Dosimetry
url http://www.sciencedirect.com/science/article/pii/S1738573324004091
work_keys_str_mv AT soohyeoklee comparativeanalysisofmachinelearningbaseddoseassessmentalgorithmsfortldosimetry
AT hyoungtaekkim comparativeanalysisofmachinelearningbaseddoseassessmentalgorithmsfortldosimetry
AT hwijoonjung comparativeanalysisofmachinelearningbaseddoseassessmentalgorithmsfortldosimetry
AT kyungtaeklim comparativeanalysisofmachinelearningbaseddoseassessmentalgorithmsfortldosimetry