Jordan D Noey, Colin J Stewart, Wenjin Yu, Kimberlee J Kearfott
{"title":"Implementation of Stochastic Gradient Descent in an Automated Glow Peak Identification Software for Multiple Thermoluminescent Dosimeter Types.","authors":"Jordan D Noey, Colin J Stewart, Wenjin Yu, Kimberlee J Kearfott","doi":"10.1097/HP.0000000000001931","DOIUrl":null,"url":null,"abstract":"<p><strong>Abstract: </strong>A glow-curve analysis code was previously developed in C++ to analyze thermoluminescent dosimeter glow curves using automated peak detection while applying a first-order kinetics model. A newer version of this code was implemented to improve the automated peak detection and curve fitting models. The Stochastic Gradient Descent Algorithm was introduced to replace the prior approach of taking first and second-order derivatives for peak detection. Additionally, early stopping mechanisms were invoked to improve the previously used Levenberg-Marquardt Algorithm employed for curve fitting. The two software versions were compared through glow curve analysis of different thermoluminescent dosimeter materials and calculation of the corresponding figures of merit. Overall improvements were shown, namely an increase in the number of peaks detected and a reduction of the mean figure of merit by approximately 46%.</p>","PeriodicalId":12976,"journal":{"name":"Health physics","volume":" ","pages":"393-398"},"PeriodicalIF":1.0000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Health physics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/HP.0000000000001931","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/10 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract: A glow-curve analysis code was previously developed in C++ to analyze thermoluminescent dosimeter glow curves using automated peak detection while applying a first-order kinetics model. A newer version of this code was implemented to improve the automated peak detection and curve fitting models. The Stochastic Gradient Descent Algorithm was introduced to replace the prior approach of taking first and second-order derivatives for peak detection. Additionally, early stopping mechanisms were invoked to improve the previously used Levenberg-Marquardt Algorithm employed for curve fitting. The two software versions were compared through glow curve analysis of different thermoluminescent dosimeter materials and calculation of the corresponding figures of merit. Overall improvements were shown, namely an increase in the number of peaks detected and a reduction of the mean figure of merit by approximately 46%.
期刊介绍：
Health Physics, first published in 1958, provides the latest research to a wide variety of radiation safety professionals including health physicists, nuclear chemists, medical physicists, and radiation safety officers with interests in nuclear and radiation science. The Journal allows professionals in these and other disciplines in science and engineering to stay on the cutting edge of scientific and technological advances in the field of radiation safety. The Journal publishes original papers, technical notes, articles on advances in practical applications, editorials, and correspondence. Journal articles report on the latest findings in theoretical, practical, and applied disciplines of epidemiology and radiation effects, radiation biology and radiation science, radiation ecology, and related fields.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
