Scholarlink

Abstract <p>Study of the strangeness production in heavy-ion collisions is one of the primary goals of the MPD experiment at the NICA collider. To collect sufficient statistics of (multi)strange particle decays, their efficient selection from the high combinatorial background is required. Presumably, solution of such a task can greatly benefit from multivariate analyses based on machine learning techniques. In this work, results of application of the machine learning approaches, implemented in the TMVA package of the ROOT framework, are presented for Monte Carlo-simulated event samples of heavy-ion collisions and compared with the results of the topological cuts selection method.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Monte Carlo Study of the MPD Performance for Hyperon Selection Using Machine Learning Techniques

  • 期刊论文

  • 发表日期：

    2025年10月1日

查看全文
  • J. R. Drnoyan,
  • V. I. Kolesnikov,
  • D. A. Suvarieva,
  • V. A. Vasendina,
  • A. I Zinchenko,
  • R. A. Zinchenko

摘要

Abstract

Study of the strangeness production in heavy-ion collisions is one of the primary goals of the MPD experiment at the NICA collider. To collect sufficient statistics of (multi)strange particle decays, their efficient selection from the high combinatorial background is required. Presumably, solution of such a task can greatly benefit from multivariate analyses based on machine learning techniques. In this work, results of application of the machine learning approaches, implemented in the TMVA package of the ROOT framework, are presented for Monte Carlo-simulated event samples of heavy-ion collisions and compared with the results of the topological cuts selection method.