Applying artificial neural network and deep learning in PP and PP - collisions cross section

Amr Radi, Mudhaher Al Ajmi, Zakiya Al Ruqeishi

Research output: Contribution to journalArticle

Abstract

In recent years, Deep Learning (DL) has become visible and operable framework with many applications in High Energy Physics. In this paper we use DL to calculate, the total cross section (σ_tot) of both proton-proton (PP) and proton-antiproton (PP) collisions from low to ultra-high energy regions as function of center of mass energy (√s) and the Type of Particle Collision (TPC). √s and TPC are used as inputs in DL and σ_tot is the desired output. DL has been trained to construct a function that studies the relation between σ_tot ((√s), TPC). The trained DL model has shown a high degree of performance in matching the trained distributions. The DL is used to forecast with σ_tot that is not given in the training set. The predicted σ_tot had been combined the experimental data effectively.

Original languageEnglish
Pages (from-to)1939-1944
Number of pages6
JournalJournal of Advanced Research in Dynamical and Control Systems
Volume10
Issue number13
Publication statusPublished - Jan 1 2018

Fingerprint

Protons
Neural networks
High energy physics
Deep learning

Keywords

  • Artificial neural network (ANN)
  • Center of mass energy √s
  • Control system
  • Deep learning
  • Pp collision
  • Pp collision
  • Total cross section σ_tot

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Applying artificial neural network and deep learning in PP and PP - collisions cross section . / Radi, Amr; Al Ajmi, Mudhaher; Al Ruqeishi, Zakiya.

In: Journal of Advanced Research in Dynamical and Control Systems, Vol. 10, No. 13, 01.01.2018, p. 1939-1944.

Research output: Contribution to journalArticle

@article{f52858ded86c453ea91fc32031b3f98f,
title = "Applying artificial neural network and deep learning in PP and PP - collisions cross section",
abstract = "In recent years, Deep Learning (DL) has become visible and operable framework with many applications in High Energy Physics. In this paper we use DL to calculate, the total cross section (σ_tot) of both proton-proton (PP) and proton-antiproton (PP) collisions from low to ultra-high energy regions as function of center of mass energy (√s) and the Type of Particle Collision (TPC). √s and TPC are used as inputs in DL and σ_tot is the desired output. DL has been trained to construct a function that studies the relation between σ_tot ((√s), TPC). The trained DL model has shown a high degree of performance in matching the trained distributions. The DL is used to forecast with σ_tot that is not given in the training set. The predicted σ_tot had been combined the experimental data effectively.",
keywords = "Artificial neural network (ANN), Center of mass energy √s, Control system, Deep learning, Pp collision, Pp collision, Total cross section σ_tot",
author = "Amr Radi and {Al Ajmi}, Mudhaher and {Al Ruqeishi}, Zakiya",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "10",
pages = "1939--1944",
journal = "Journal of Advanced Research in Dynamical and Control Systems",
issn = "1943-023X",
publisher = "Institute of Advanced Scientific Research",
number = "13",

}

TY - JOUR

T1 - Applying artificial neural network and deep learning in PP and PP - collisions cross section

AU - Radi, Amr

AU - Al Ajmi, Mudhaher

AU - Al Ruqeishi, Zakiya

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, Deep Learning (DL) has become visible and operable framework with many applications in High Energy Physics. In this paper we use DL to calculate, the total cross section (σ_tot) of both proton-proton (PP) and proton-antiproton (PP) collisions from low to ultra-high energy regions as function of center of mass energy (√s) and the Type of Particle Collision (TPC). √s and TPC are used as inputs in DL and σ_tot is the desired output. DL has been trained to construct a function that studies the relation between σ_tot ((√s), TPC). The trained DL model has shown a high degree of performance in matching the trained distributions. The DL is used to forecast with σ_tot that is not given in the training set. The predicted σ_tot had been combined the experimental data effectively.

AB - In recent years, Deep Learning (DL) has become visible and operable framework with many applications in High Energy Physics. In this paper we use DL to calculate, the total cross section (σ_tot) of both proton-proton (PP) and proton-antiproton (PP) collisions from low to ultra-high energy regions as function of center of mass energy (√s) and the Type of Particle Collision (TPC). √s and TPC are used as inputs in DL and σ_tot is the desired output. DL has been trained to construct a function that studies the relation between σ_tot ((√s), TPC). The trained DL model has shown a high degree of performance in matching the trained distributions. The DL is used to forecast with σ_tot that is not given in the training set. The predicted σ_tot had been combined the experimental data effectively.

KW - Artificial neural network (ANN)

KW - Center of mass energy √s

KW - Control system

KW - Deep learning

KW - Pp collision

KW - Pp collision

KW - Total cross section σ_tot

UR - http://www.scopus.com/inward/record.url?scp=85062976257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062976257&partnerID=8YFLogxK

M3 - Article

VL - 10

SP - 1939

EP - 1944

JO - Journal of Advanced Research in Dynamical and Control Systems

JF - Journal of Advanced Research in Dynamical and Control Systems

SN - 1943-023X

IS - 13

ER -