利用深度机器学习确定装饰事件中μ子的多重性

IF 0.3 4区物理与天体物理 Q4 PHYSICS, NUCLEAR

Physics of Atomic Nuclei Pub Date : 2025-03-05 DOI:10.1134/S1063778824100326

E. A. Miroshnichenko, V. S. Vorobev

{"title":"利用深度机器学习确定装饰事件中μ子的多重性","authors":"E. A. Miroshnichenko, V. S. Vorobev","doi":"10.1134/S1063778824100326","DOIUrl":null,"url":null,"abstract":"<p>The DECOR coordinate-tracking detector is designed to register charged cosmic ray particles in wide zenith angles. Measurements by the installation are currently analyzed manually, affecting its performance. The use of deep machine learning allows automated processing and larger samples of processed data. The artificial neural network (ANN) architectures considered in this work have displayed high accuracy in counting the multiplicity of muons in data from the DECOR facility. Estimates are given of ANN performance for events with different muon multiplicities. The accuracy is 1 track for 5–6 particles and 7 tracks for more than 100 particles.</p>","PeriodicalId":728,"journal":{"name":"Physics of Atomic Nuclei","volume":"87 12","pages":"1830 - 1835"},"PeriodicalIF":0.3000,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Determining the Multiplicities of Muons in DECOR Events by Means of Deep Machine Learning\",\"authors\":\"E. A. Miroshnichenko, V. S. Vorobev\",\"doi\":\"10.1134/S1063778824100326\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The DECOR coordinate-tracking detector is designed to register charged cosmic ray particles in wide zenith angles. Measurements by the installation are currently analyzed manually, affecting its performance. The use of deep machine learning allows automated processing and larger samples of processed data. The artificial neural network (ANN) architectures considered in this work have displayed high accuracy in counting the multiplicity of muons in data from the DECOR facility. Estimates are given of ANN performance for events with different muon multiplicities. The accuracy is 1 track for 5–6 particles and 7 tracks for more than 100 particles.</p>\",\"PeriodicalId\":728,\"journal\":{\"name\":\"Physics of Atomic Nuclei\",\"volume\":\"87 12\",\"pages\":\"1830 - 1835\"},\"PeriodicalIF\":0.3000,\"publicationDate\":\"2025-03-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Physics of Atomic Nuclei\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://link.springer.com/article/10.1134/S1063778824100326\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"PHYSICS, NUCLEAR\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physics of Atomic Nuclei","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1134/S1063778824100326","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PHYSICS, NUCLEAR","Score":null,"Total":0}

引用次数: 0

摘要

DECOR坐标跟踪探测器设计用于记录宽天顶角的带电宇宙射线粒子。安装的测量结果目前是手动分析的，这会影响其性能。使用深度机器学习可以实现自动化处理和更大的处理数据样本。本文所考虑的人工神经网络（ANN）架构在计算来自DECOR设备的数据中的μ子的多重性方面显示出很高的准确性。对具有不同介子多重度事件的人工神经网络性能进行了估计。5-6个粒子精度为1道，100个以上粒子精度为7道。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Determining the Multiplicities of Muons in DECOR Events by Means of Deep Machine Learning

查看原文本刊更多论文

Determining the Multiplicities of Muons in DECOR Events by Means of Deep Machine Learning

The DECOR coordinate-tracking detector is designed to register charged cosmic ray particles in wide zenith angles. Measurements by the installation are currently analyzed manually, affecting its performance. The use of deep machine learning allows automated processing and larger samples of processed data. The artificial neural network (ANN) architectures considered in this work have displayed high accuracy in counting the multiplicity of muons in data from the DECOR facility. Estimates are given of ANN performance for events with different muon multiplicities. The accuracy is 1 track for 5–6 particles and 7 tracks for more than 100 particles.

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

Physics of Atomic Nuclei 物理-物理：核物理

CiteScore

0.60

自引率

25.00%

发文量

审稿时长

3-6 weeks

期刊介绍： Physics of Atomic Nuclei is a journal that covers experimental and theoretical studies of nuclear physics: nuclear structure, spectra, and properties; radiation, fission, and nuclear reactions induced by photons, leptons, hadrons, and nuclei; fundamental interactions and symmetries; hadrons (with light, strange, charm, and bottom quarks); particle collisions at high and superhigh energies; gauge and unified quantum field theories, quark models, supersymmetry and supergravity, astrophysics and cosmology.