Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods

Mostrar otras versiones (1)

During the second phase upgrade program developed for LHC and its experiments, the main hadronic calorimeter of ATLAS (TileCal) will redesign completely its readout electronics, but the optical signal pathway will be kept unchanged. However, there is a technical possibility for improving increasing...

Descripción completa

Detalles Bibliográficos
Autores principales: Do Nascimento Gaspar, Philipp, Seixas, Jose
Lenguaje:eng
Publicado: 2019
Materias:
Particle Physics - Experiment
Acceso en línea:http://cds.cern.ch/record/2674913
_version_ 1780962587724218368
author Do Nascimento Gaspar, Philipp
Seixas, Jose
author_facet Do Nascimento Gaspar, Philipp
Seixas, Jose
author_sort Do Nascimento Gaspar, Philipp
collection CERN
description During the second phase upgrade program developed for LHC and its experiments, the main hadronic calorimeter of ATLAS (TileCal) will redesign completely its readout electronics, but the optical signal pathway will be kept unchanged. However, there is a technical possibility for improving increasing of the calorimeter granularity through the introduction of Multi-Anode Photomultiplier Tubes (MA-PMTs) on its readout chain. This paper presents the latest results from using a Generative Adversarial Network (GAN) to generate synthetic images, which simulate real images formed in the MA-PMT. After the classification of cell sub regions, preliminary results show a classification accuracy of more than 98% on the test set.
id cern-2674913
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2019
record_format invenio
spelling cern-26749132019-09-30T06:29:59Zhttp://cds.cern.ch/record/2674913engDo Nascimento Gaspar, PhilippSeixas, JoseTowards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning MethodsParticle Physics - ExperimentDuring the second phase upgrade program developed for LHC and its experiments, the main hadronic calorimeter of ATLAS (TileCal) will redesign completely its readout electronics, but the optical signal pathway will be kept unchanged. However, there is a technical possibility for improving increasing of the calorimeter granularity through the introduction of Multi-Anode Photomultiplier Tubes (MA-PMTs) on its readout chain. This paper presents the latest results from using a Generative Adversarial Network (GAN) to generate synthetic images, which simulate real images formed in the MA-PMT. After the classification of cell sub regions, preliminary results show a classification accuracy of more than 98% on the test set.ATL-TILECAL-PROC-2019-003oai:cds.cern.ch:26749132019-05-17
spellingShingle Particle Physics - Experiment
Do Nascimento Gaspar, Philipp
Seixas, Jose
Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title_full Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title_fullStr Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title_full_unstemmed Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title_short Towards the Increase in Granularity for the Main Hadronic ATLAS Calorimeter: Exploiting Deep Learning Methods
title_sort towards the increase in granularity for the main hadronic atlas calorimeter: exploiting deep learning methods
topic Particle Physics - Experiment
url http://cds.cern.ch/record/2674913
work_keys_str_mv AT donascimentogasparphilipp towardstheincreaseingranularityforthemainhadronicatlascalorimeterexploitingdeeplearningmethods
AT seixasjose towardstheincreaseingranularityforthemainhadronicatlascalorimeterexploitingdeeplearningmethods

Ejemplares similares