Pixel Detector Background Generation using Generative Adversarial Networks at Belle II

The pixel vertex detector (PXD) is an essential part of the Belle II detector recording particle positions. Data from the PXD and other sensors allow us to reconstruct particle tracks and decay vertices. The effiect of background hits on track reconstruction is simulated by adding measured or simula...

Full description

Bibliographic Details
Main Authors:	Hashemi Hosein, Hartmann Nikolai, Kuhr Thomas, Ritter Martin, Srebre Matej
Format:	Article
Language:	English
Published:	EDP Sciences 2021-01-01
Series:	EPJ Web of Conferences
Online Access:	https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03031.pdf

id	doaj-abed4210cb4047689bcae42de369eaf9
record_format	Article
spelling	doaj-abed4210cb4047689bcae42de369eaf92021-08-26T09:27:25ZengEDP SciencesEPJ Web of Conferences2100-014X2021-01-012510303110.1051/epjconf/202125103031epjconf_chep2021_03031Pixel Detector Background Generation using Generative Adversarial Networks at Belle IIHashemi Hosein0Hartmann Nikolai1Kuhr Thomas2Ritter Martin3Srebre Matej4Faculty of Physics, Ludwig Maximilians University of MunichFaculty of Physics, Ludwig Maximilians University of MunichFaculty of Physics, Ludwig Maximilians University of MunichFaculty of Physics, Ludwig Maximilians University of MunichFaculty of Physics, Ludwig Maximilians University of MunichThe pixel vertex detector (PXD) is an essential part of the Belle II detector recording particle positions. Data from the PXD and other sensors allow us to reconstruct particle tracks and decay vertices. The effiect of background hits on track reconstruction is simulated by adding measured or simulated background hit patterns to the hits produced by simulated signal particles. This model requires a large set of statistically independent PXD background noise samples to avoid a systematic bias of reconstructed tracks. However, data from the fine-grained PXD requires a substantial amount of storage. As an efficient way of producing background noise, we explore the idea of an on-demand PXD background generator using conditional Generative Adversarial Networks (GANs), adapted by the number of PXD sensors in order to both increase the image fidelity and produce sensor-dependent PXD hitmaps.https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03031.pdf
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Hashemi Hosein Hartmann Nikolai Kuhr Thomas Ritter Martin Srebre Matej
spellingShingle	Hashemi Hosein Hartmann Nikolai Kuhr Thomas Ritter Martin Srebre Matej Pixel Detector Background Generation using Generative Adversarial Networks at Belle II EPJ Web of Conferences
author_facet	Hashemi Hosein Hartmann Nikolai Kuhr Thomas Ritter Martin Srebre Matej
author_sort	Hashemi Hosein
title	Pixel Detector Background Generation using Generative Adversarial Networks at Belle II
title_short	Pixel Detector Background Generation using Generative Adversarial Networks at Belle II
title_full	Pixel Detector Background Generation using Generative Adversarial Networks at Belle II
title_fullStr	Pixel Detector Background Generation using Generative Adversarial Networks at Belle II
title_full_unstemmed	Pixel Detector Background Generation using Generative Adversarial Networks at Belle II
title_sort	pixel detector background generation using generative adversarial networks at belle ii
publisher	EDP Sciences
series	EPJ Web of Conferences
issn	2100-014X
publishDate	2021-01-01
description	The pixel vertex detector (PXD) is an essential part of the Belle II detector recording particle positions. Data from the PXD and other sensors allow us to reconstruct particle tracks and decay vertices. The effiect of background hits on track reconstruction is simulated by adding measured or simulated background hit patterns to the hits produced by simulated signal particles. This model requires a large set of statistically independent PXD background noise samples to avoid a systematic bias of reconstructed tracks. However, data from the fine-grained PXD requires a substantial amount of storage. As an efficient way of producing background noise, we explore the idea of an on-demand PXD background generator using conditional Generative Adversarial Networks (GANs), adapted by the number of PXD sensors in order to both increase the image fidelity and produce sensor-dependent PXD hitmaps.
url	https://www.epj-conferences.org/articles/epjconf/pdf/2021/05/epjconf_chep2021_03031.pdf
work_keys_str_mv	AT hashemihosein pixeldetectorbackgroundgenerationusinggenerativeadversarialnetworksatbelleii AT hartmannnikolai pixeldetectorbackgroundgenerationusinggenerativeadversarialnetworksatbelleii AT kuhrthomas pixeldetectorbackgroundgenerationusinggenerativeadversarialnetworksatbelleii AT rittermartin pixeldetectorbackgroundgenerationusinggenerativeadversarialnetworksatbelleii AT srebrematej pixeldetectorbackgroundgenerationusinggenerativeadversarialnetworksatbelleii
_version_	1721195818000580608

Pixel Detector Background Generation using Generative Adversarial Networks at Belle II

Similar Items