{"title":"基于软多数投票的监督学习算法的异构集成,用于更可靠地识别基于塑性闪烁体光谱的伽马发射放射性同位素","authors":"Khalil Moshkbar-Bakhshayesh","doi":"10.1016/j.radphyschem.2025.113081","DOIUrl":null,"url":null,"abstract":"<div><div>The identification of gamma-emitting radioisotopes plays a critical role in various applications, including nuclear security, environmental monitoring, and medical diagnostics. However, the low energy resolution of plastic scintillators presents challenges in accurate radioisotope identification. This study proposes a heterogeneous ensemble of supervised learning (HEL) algorithms, incorporating logistic regression (LR), decision tree (DT), and k-nearest neighbors (k-NN), to enhance identification performance. The ensemble method leverages the strengths of each individual algorithm through soft majority voting (SMV(. Experimental gamma spectra from Co-60, Cs-137, Na-22, and Am-241 are analyzed, with extracted features applied to improve classification accuracy. Additionally, this study extends the methodology to identify mixture spectra containing multiple isotopes, a crucial challenge in radiation detection. The probabilistic outputs of HEL enable more precise characterization of mixed radiation sources. Performance evaluation, based on accuracy, precision, recall, and F1-score, demonstrated that HEL outperforms individual algorithms, exhibiting superior robustness against noise/uncertainties. The results confirm that the proposed ensemble method significantly enhances the reliability of gamma-emitting radioisotope identification compared to individual algorithms.</div></div>","PeriodicalId":20861,"journal":{"name":"Radiation Physics and Chemistry","volume":"237 ","pages":"Article 113081"},"PeriodicalIF":2.8000,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Heterogeneous ensemble of supervised learning algorithms with soft majority voting for more reliable identification of gamma-emitting radioisotopes based on plastic scintillator spectra\",\"authors\":\"Khalil Moshkbar-Bakhshayesh\",\"doi\":\"10.1016/j.radphyschem.2025.113081\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The identification of gamma-emitting radioisotopes plays a critical role in various applications, including nuclear security, environmental monitoring, and medical diagnostics. However, the low energy resolution of plastic scintillators presents challenges in accurate radioisotope identification. This study proposes a heterogeneous ensemble of supervised learning (HEL) algorithms, incorporating logistic regression (LR), decision tree (DT), and k-nearest neighbors (k-NN), to enhance identification performance. The ensemble method leverages the strengths of each individual algorithm through soft majority voting (SMV(. Experimental gamma spectra from Co-60, Cs-137, Na-22, and Am-241 are analyzed, with extracted features applied to improve classification accuracy. Additionally, this study extends the methodology to identify mixture spectra containing multiple isotopes, a crucial challenge in radiation detection. The probabilistic outputs of HEL enable more precise characterization of mixed radiation sources. Performance evaluation, based on accuracy, precision, recall, and F1-score, demonstrated that HEL outperforms individual algorithms, exhibiting superior robustness against noise/uncertainties. The results confirm that the proposed ensemble method significantly enhances the reliability of gamma-emitting radioisotope identification compared to individual algorithms.</div></div>\",\"PeriodicalId\":20861,\"journal\":{\"name\":\"Radiation Physics and Chemistry\",\"volume\":\"237 \",\"pages\":\"Article 113081\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-06-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiation Physics and Chemistry\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0969806X25005730\",\"RegionNum\":3,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiation Physics and Chemistry","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0969806X25005730","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
Heterogeneous ensemble of supervised learning algorithms with soft majority voting for more reliable identification of gamma-emitting radioisotopes based on plastic scintillator spectra
The identification of gamma-emitting radioisotopes plays a critical role in various applications, including nuclear security, environmental monitoring, and medical diagnostics. However, the low energy resolution of plastic scintillators presents challenges in accurate radioisotope identification. This study proposes a heterogeneous ensemble of supervised learning (HEL) algorithms, incorporating logistic regression (LR), decision tree (DT), and k-nearest neighbors (k-NN), to enhance identification performance. The ensemble method leverages the strengths of each individual algorithm through soft majority voting (SMV(. Experimental gamma spectra from Co-60, Cs-137, Na-22, and Am-241 are analyzed, with extracted features applied to improve classification accuracy. Additionally, this study extends the methodology to identify mixture spectra containing multiple isotopes, a crucial challenge in radiation detection. The probabilistic outputs of HEL enable more precise characterization of mixed radiation sources. Performance evaluation, based on accuracy, precision, recall, and F1-score, demonstrated that HEL outperforms individual algorithms, exhibiting superior robustness against noise/uncertainties. The results confirm that the proposed ensemble method significantly enhances the reliability of gamma-emitting radioisotope identification compared to individual algorithms.
期刊介绍:
Radiation Physics and Chemistry is a multidisciplinary journal that provides a medium for publication of substantial and original papers, reviews, and short communications which focus on research and developments involving ionizing radiation in radiation physics, radiation chemistry and radiation processing.
The journal aims to publish papers with significance to an international audience, containing substantial novelty and scientific impact. The Editors reserve the rights to reject, with or without external review, papers that do not meet these criteria. This could include papers that are very similar to previous publications, only with changed target substrates, employed materials, analyzed sites and experimental methods, report results without presenting new insights and/or hypothesis testing, or do not focus on the radiation effects.