基于机器学习的热辐射剂量测定剂量评估算法比较分析

IF 2.6 3区 工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY Nuclear Engineering and Technology Pub Date : 2024-08-16 DOI:10.1016/j.net.2024.08.030
Soohyeok Lee , Hyoungtaek Kim , Hwijoon Jung , Kyung Taek Lim
{"title":"基于机器学习的热辐射剂量测定剂量评估算法比较分析","authors":"Soohyeok Lee ,&nbsp;Hyoungtaek Kim ,&nbsp;Hwijoon Jung ,&nbsp;Kyung Taek Lim","doi":"10.1016/j.net.2024.08.030","DOIUrl":null,"url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":19272,"journal":{"name":"Nuclear Engineering and Technology","volume":"56 12","pages":"Pages 5414-5421"},"PeriodicalIF":2.6000,"publicationDate":"2024-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparative analysis of machine learning-based dose assessment algorithms for TL dosimetry\",\"authors\":\"Soohyeok Lee ,&nbsp;Hyoungtaek Kim ,&nbsp;Hwijoon Jung ,&nbsp;Kyung Taek Lim\",\"doi\":\"10.1016/j.net.2024.08.030\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>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.</div></div>\",\"PeriodicalId\":19272,\"journal\":{\"name\":\"Nuclear Engineering and Technology\",\"volume\":\"56 12\",\"pages\":\"Pages 5414-5421\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-08-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Nuclear Engineering and Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1738573324004091\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"NUCLEAR SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Engineering and Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1738573324004091","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NUCLEAR SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

本文探讨了基于机器学习的 TL 剂量评估算法的实施。与传统的 DT 方法相比,本文侧重于 ANN 和 LGBM 的辐射场分类、性能商评估以及浅层和深层剂量当量评估。我们根据 TLD 测量的元素响应数据对这些算法进行了评估。我们建立了一个用于训练的数据集,对测试类别的基本元素响应进行了放大,并在 ±3 % 的范围内归一化为 1 mSv Cs-137。两种算法都由五个子集模型组成,用于对辐射场进行分类和识别混合场的比率。LGBM 在对所考虑的辐射场进行分类时表现出最佳的准确性和最低的性能商数。通过比较三种算法中深剂量和浅剂量当量的容差水平,LGBM 得出的预测剂量当量与真实剂量当量之间的差异最小。这种较小的差异意味着 LGBM 的预期值偏差和标准偏差最小,与传统的 DT 方法相比,其剂量评估的准确性和精确度更高。这项研究的结果进一步推动了基于 ML 算法的 TL 剂量评估的采用,凸显了其在该领域的重要性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
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 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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Nuclear Engineering and Technology
Nuclear Engineering and Technology 工程技术-核科学技术
CiteScore
4.80
自引率
7.40%
发文量
431
审稿时长
3.5 months
期刊介绍: Nuclear Engineering and Technology (NET), an international journal of the Korean Nuclear Society (KNS), publishes peer-reviewed papers on original research, ideas and developments in all areas of the field of nuclear science and technology. NET bimonthly publishes original articles, reviews, and technical notes. The journal is listed in the Science Citation Index Expanded (SCIE) of Thomson Reuters. NET covers all fields for peaceful utilization of nuclear energy and radiation as follows: 1) Reactor Physics 2) Thermal Hydraulics 3) Nuclear Safety 4) Nuclear I&C 5) Nuclear Physics, Fusion, and Laser Technology 6) Nuclear Fuel Cycle and Radioactive Waste Management 7) Nuclear Fuel and Reactor Materials 8) Radiation Application 9) Radiation Protection 10) Nuclear Structural Analysis and Plant Management & Maintenance 11) Nuclear Policy, Economics, and Human Resource Development
期刊最新文献
The impact of pressure rate on the physical, structural and gamma-ray shielding capabilities of novel light-weight clay bricks Towards accurate dose assessment for emergency industrial radiography source retrieval operations: A preliminary study of 4D Monte Carlo dose calculations Technical reviewers for Nuclear Engineering and Technology, 2024 An innovative and efficient implementation of matrix-free Newton krylov method for neutronics/thermal-hydraulics coupling simulation Numerical investigation of welding deformation diminution for double shell structure using the layered inherent strain
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1