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 , Hyoungtaek Kim , Hwijoon Jung , 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 , Hyoungtaek Kim , Hwijoon Jung , 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}
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.
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