Fast neural-net based fake track rejection in the LHCb reconstruction

A neural-network based algorithm to identify fake tracks in the LHCb pattern recognition is presented. This algorithm, called ghost probability, retains more than 99 % of well reconstructed tracks while reducing the number of fake tracks by 60 %. It is fast enough to fit into the CPU time budget of...

Descripción completa

Detalles Bibliográficos
Autores principales: De Cian, Michel, Farry, Stephen, Seyfert, Paul, Stahl, Sascha
Lenguaje:eng
Publicado: 2017
Materias:
Particle Physics - Experiment
Acceso en línea:http://cds.cern.ch/record/2255039
_version_ 1780953682030886912
author De Cian, Michel
Farry, Stephen
Seyfert, Paul
Stahl, Sascha
author_facet De Cian, Michel
Farry, Stephen
Seyfert, Paul
Stahl, Sascha
author_sort De Cian, Michel
collection CERN
description A neural-network based algorithm to identify fake tracks in the LHCb pattern recognition is presented. This algorithm, called ghost probability, retains more than 99 % of well reconstructed tracks while reducing the number of fake tracks by 60 %. It is fast enough to fit into the CPU time budget of the software trigger farm and thus reduces the combinatorics of the decay reconstructions, as well as the number of tracks that need to be processed by the particle identification algorithms. As a result, it strongly contributes to the achievement of having the same reconstruction online and offline in the LHCb experiment in Run II of the LHC.
id cern-2255039
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2017
record_format invenio
spelling cern-22550392019-09-30T06:29:59Zhttp://cds.cern.ch/record/2255039engDe Cian, MichelFarry, StephenSeyfert, PaulStahl, SaschaFast neural-net based fake track rejection in the LHCb reconstructionParticle Physics - ExperimentA neural-network based algorithm to identify fake tracks in the LHCb pattern recognition is presented. This algorithm, called ghost probability, retains more than 99 % of well reconstructed tracks while reducing the number of fake tracks by 60 %. It is fast enough to fit into the CPU time budget of the software trigger farm and thus reduces the combinatorics of the decay reconstructions, as well as the number of tracks that need to be processed by the particle identification algorithms. As a result, it strongly contributes to the achievement of having the same reconstruction online and offline in the LHCb experiment in Run II of the LHC.LHCb-PUB-2017-011CERN-LHCb-PUB-2017-011oai:cds.cern.ch:22550392017-03-08
spellingShingle Particle Physics - Experiment
De Cian, Michel
Farry, Stephen
Seyfert, Paul
Stahl, Sascha
Fast neural-net based fake track rejection in the LHCb reconstruction
title Fast neural-net based fake track rejection in the LHCb reconstruction
title_full Fast neural-net based fake track rejection in the LHCb reconstruction
title_fullStr Fast neural-net based fake track rejection in the LHCb reconstruction
title_full_unstemmed Fast neural-net based fake track rejection in the LHCb reconstruction
title_short Fast neural-net based fake track rejection in the LHCb reconstruction
title_sort fast neural-net based fake track rejection in the lhcb reconstruction
topic Particle Physics - Experiment
url http://cds.cern.ch/record/2255039
work_keys_str_mv AT decianmichel fastneuralnetbasedfaketrackrejectioninthelhcbreconstruction
AT farrystephen fastneuralnetbasedfaketrackrejectioninthelhcbreconstruction
AT seyfertpaul fastneuralnetbasedfaketrackrejectioninthelhcbreconstruction
AT stahlsascha fastneuralnetbasedfaketrackrejectioninthelhcbreconstruction

Ejemplares similares