Skip to Main content Skip to Navigation
Journal articles

A neural network clustering algorithm for the ATLAS silicon pixel detector

G. Aad 1 S. Albrand 2 J. Brown 2 J. Collot 2 S. Crépé-Renaudin 2 B. Dechenaux 2 P.A. Delsart 2 C. Gabaldon 2 M.H. Genest 2 J.Y. Hostachy 2 B.T. Le 2 F. Ledroit-Guillon 2 A. Lleres 2 A. Lucotte 2 F. Malek 2 C. Monini 2 J. Stark 2 B. Trocmé 2 M. Wu 2 G. Rahal 3 S. Abdel Khalek 4 A. Bassalat 4 C. Becot 4 S. Binet 4 C. Bourdarios 4 D. Charfeddine 4 J.B. de Vivie de Regie 4 L. Duflot 4 M. Escalier 4 L. Fayard 4 D. Fournier 4 J.-F. Grivaz 4 T. Guillemin 4 F. Hariri 4 S. Henrot-Versillé 4 J. Hrivnac 4 L. Iconomidou-Fayard 4 M. Kado 4 A. Lounis 4 N. Makovec 4 L. Poggioli 4 P. Puzo 4 A. Renaud 4 D. Rousseau 4 G. Rybkin 4 A.C. Schaffer 4 E. Scifo 4 L. Serin 4 S. Simion 4 R. Tanaka 4 H.L. Tran 4 D. Zerwas 4 Z. Zhang 4 D. Boumediene 5 Emmanuel Busato 5 D. Calvet 5 S. Calvet 5 J. Donini 5 E. Dubreuil 5 N. Ghodbane 5 G. Gilles 5 Ph. Gris 5 C. Guicheney 5 H. Liao 5 D. Pallin 5 Daniela Paredes Hernández 5 F. Podlyski 5 C. Santoni 5 Timothée Theveneaux-Pelzer 5 Loïc Valery 5 F. Vazeille 5 Z. Barnovska 6 N. Berger 6 M. Delmastro 6 L. Di Ciaccio 6 T.K.O. Doan 6 S. Elles 6 C. Goy 6 T. Hryn'Ova 6 S. Jézéquel 6 H. Keoshkerian 6 I. Koletsou 6 R. Lafaye 6 J. Leveque 6 V.P. Lombardo 6 N. Massol 6 H. Przysiezniak 6 G. Sauvage 6 E. Sauvan 6 M. Schwoerer 6 O. Simard 6 T. Todorov 6 I. Wingerter-Seez 6 L. Alio 1 M. Barbero 1 C. Bertella 1 J. C. Clémens 1 Y. Coadou 1 S. Diglio 1 F. Djama 1 L. Feligioni 1 D. Hoffmann 1 F. Hubaut 1 E. B. F. G. Knoops 1 E. Le Guirriec 1 B. Li 1 D. Madaffari 1 K. Mochizuki 1 E. Monnier 1 S. Muanza 1 Y. Nagai 1 P. Pralavorio 1 A. Rozanov 1 T. Serre 1 M. Talby 1 N. Tannoury 1 E. Tiouchichine 1 S. Tisserant 1 J. Toth 1 F. Touchard 1 M. Ughetto 1, 7 L. Vacavant 1
Abstract : A novel technique to identify and split clusters created by multiple charged particles in the ATLAS pixel detector using a set of artificial neural networks is presented. Such merged clusters are a common feature of tracks originating from highly energetic objects, such as jets. Neural networks are trained using Monte Carlo samples produced with a detailed detector simulation. This technique replaces the former clustering approach based on a connected component analysis and charge interpolation. The performance of the neural network splitting technique is quantified using data from proton--proton collisions at the LHC collected by the ATLAS detector in 2011 and from Monte Carlo simulations. This technique reduces the number of clusters shared between tracks in highly energetic jets by up to a factor of three. It also provides more precise position and error estimates of the clusters in both the transverse and longitudinal impact parameter resolution.
Document type :
Journal articles
Complete list of metadatas

http://hal.in2p3.fr/in2p3-01024297
Contributor : Emmanuelle Vernay <>
Submitted on : Wednesday, July 16, 2014 - 7:52:43 AM
Last modification on : Thursday, February 25, 2021 - 10:58:33 AM

Links full text

Identifiers

Citation

G. Aad, S. Albrand, J. Brown, J. Collot, S. Crépé-Renaudin, et al.. A neural network clustering algorithm for the ATLAS silicon pixel detector. Journal of Instrumentation, IOP Publishing, 2014, 9, pp.09009. ⟨10.1088/1748-0221/9/09/P09009⟩. ⟨in2p3-01024297⟩

Share

Metrics

Record views

610