用神经网络分辨原初宇宙线成分

Translated title of the contribution: Distinguishing Primary Cosmic-Ray Composition with Artificial Neural Networks

Hualou Liang, Wei Xie, Jingru Ren, Taijie Wang, Guiliang Dai

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

尝试在高山乳胶室实验中用神经网络的方法区分超高能区原初宇宙线当中的质子和原子核,对模拟数据的分析结果表明,当族事例观测能量大于500TeV时,对质子和原子核的分辨率均能稳定在80%附近:而当族事例观测能量在100TeV 和500TeV 之间时,对质子和原子核的分辨率均大于70%.

We used artificial neural networks (ANN) to distinguish superhigh energy cosmic-ray proton (p) and nucleus (N) with Monte Carlo family data in mountain emulsion chamber experiment. The result shows that when visible energy of a family is larger than 500TeV, about 80% of p and N can be correctly selected, and more than 70% can be selected in the region between 100 and 500TeV.

Translated title of the contributionDistinguishing Primary Cosmic-Ray Composition with Artificial Neural Networks
Original languageChinese (Simplified)
Pages (from-to)209-210
Number of pages2
JournalKao Neng Wu Li Yu Ho Wu Li/High Energy Physics and Nuclear Physics
Volume21
Issue number3
Publication statusPublished - Mar 1997
Externally publishedYes

Keywords

  • Genetic algorithm
  • Mountain emulsion chamber
  • Neural networks
  • Primary cosmic-ray composition
  • 神经网络
  • 遗传算法
  • 原初宇宙线成分
  • 高山乳胶室

ASJC Scopus subject areas

  • Nuclear and High Energy Physics
  • General Physics and Astronomy

Fingerprint

Dive into the research topics of 'Distinguishing Primary Cosmic-Ray Composition with Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this