Machine learning: Hit time finding with a neural network

Belle-II SVD Collaboration

Machine learning: Hit time finding with a neural network

Belle-II SVD Collaboration

Department of Physics

Austrian Academy of Sciences
The University of Tokyo
Tata Institute of Fundamental Research
H. Niewodniczanski Institute of Nuclear Physics
Indian Institute of Technology Bhubaneswar
University of Melbourne
Indian Institute of Technology Madras
University of Pisa
National Institute for Nuclear Physics
Indian Institute of Technology Guwahati
Charles University
University of Trieste
Tohoku University
High Energy Accelerator Research Organization, Tsukuba
Kyungpook National University
Malaviya National Institute of Technology
Punjab Agricultural University

Research output: Contribution to journal › Conference article › peer-review

Abstract

At the High Energy Accelerator Research Organization (KEK) in Tsukuba, Japan, the double-sided silicon strip sub-detector of the Belle II experiment is read out by 1748 APV25 chips. FPGAs perform several calculations on the digitized signals. One of them will be "Hit Time Finding": the determination of the time and amplitude of the signal peaks of each event in real time using pre-programmed neural networks. This work analyses the possibility, precision and reliability of these calculations depending on various parameters.

Original language	English
Journal	Proceedings of Science
Volume	343
State	Published - 2018
Event	2018 Topical Workshop on Electronics for Particle Physics, TWEPP 2018 - Antwerp, Belgium Duration: 17 Sep 2018 → 21 Sep 2018

Cite this

@article{1c43064349a14d90ba94e1563d1dca3d,

title = "Machine learning: Hit time finding with a neural network",

abstract = "At the High Energy Accelerator Research Organization (KEK) in Tsukuba, Japan, the double-sided silicon strip sub-detector of the Belle II experiment is read out by 1748 APV25 chips. FPGAs perform several calculations on the digitized signals. One of them will be {"}Hit Time Finding{"}: the determination of the time and amplitude of the signal peaks of each event in real time using pre-programmed neural networks. This work analyses the possibility, precision and reliability of these calculations depending on various parameters.",

author = "\{Belle-II SVD Collaboration\} and R. Thalmeier and H. Yin and H. Aihara and T. Aziz and S. Bacher and S. Bahinipati and E. Barberio and Ti Baroncelli and To Baroncelli and Basith, \{A. K.\} and G. Batignani and A. Bauer and Behera, \{P. K.\} and V. Bertacchi and S. Bettarini and B. Bhuyan and T. Bilka and F. Bosi and L. Bosisio and A. Bozek and F. Buchsteiner and G. Caria and G. Casarosa and M. Ceccanti and D. Cervenkov and T. Czank and N. Dash and \{de Nuccio\}, M. and Z. Dole{\v z}al and F. Forti and M. Friedl and B. Gobbo and Grimaldo, \{J. A.M.\} and K. Hara and T. Higuchi and C. Irmler and A. Ishikawa and Jeon, \{H. B.\} and C. Joo and M. Kaleta and J. Kandra and N. Kambara and Kang, \{K. H.\} and P. Kody{\v s} and T. Kohriki and S. Koike and I. Komarov and M. Kumar and R. Kumar and W. Kun",

note = "Publisher Copyright: {\textcopyright} Copyright owned by the author(s) under the terms of the Creative Commons.; 2018 Topical Workshop on Electronics for Particle Physics, TWEPP 2018 ; Conference date: 17-09-2018 Through 21-09-2018",

year = "2018",

language = "English",

volume = "343",

journal = "Proceedings of Science",

issn = "1824-8039",

publisher = "Sissa Medialab Srl",

}

TY - JOUR

T1 - Machine learning

T2 - 2018 Topical Workshop on Electronics for Particle Physics, TWEPP 2018

AU - Belle-II SVD Collaboration

AU - Thalmeier, R.

AU - Yin, H.

AU - Aihara, H.

AU - Aziz, T.

AU - Bacher, S.

AU - Bahinipati, S.

AU - Barberio, E.

AU - Baroncelli, Ti

AU - Baroncelli, To

AU - Basith, A. K.

AU - Batignani, G.

AU - Bauer, A.

AU - Behera, P. K.

AU - Bertacchi, V.

AU - Bettarini, S.

AU - Bhuyan, B.

AU - Bilka, T.

AU - Bosi, F.

AU - Bosisio, L.

AU - Bozek, A.

AU - Buchsteiner, F.

AU - Caria, G.

AU - Casarosa, G.

AU - Ceccanti, M.

AU - Cervenkov, D.

AU - Czank, T.

AU - Dash, N.

AU - de Nuccio, M.

AU - Doležal, Z.

AU - Forti, F.

AU - Friedl, M.

AU - Gobbo, B.

AU - Grimaldo, J. A.M.

AU - Hara, K.

AU - Higuchi, T.

AU - Irmler, C.

AU - Ishikawa, A.

AU - Jeon, H. B.

AU - Joo, C.

AU - Kaleta, M.

AU - Kandra, J.

AU - Kambara, N.

AU - Kang, K. H.

AU - Kodyš, P.

AU - Kohriki, T.

AU - Koike, S.

AU - Komarov, I.

AU - Kumar, M.

AU - Kumar, R.

AU - Kun, W.

PY - 2018

Y1 - 2018

N2 - At the High Energy Accelerator Research Organization (KEK) in Tsukuba, Japan, the double-sided silicon strip sub-detector of the Belle II experiment is read out by 1748 APV25 chips. FPGAs perform several calculations on the digitized signals. One of them will be "Hit Time Finding": the determination of the time and amplitude of the signal peaks of each event in real time using pre-programmed neural networks. This work analyses the possibility, precision and reliability of these calculations depending on various parameters.

AB - At the High Energy Accelerator Research Organization (KEK) in Tsukuba, Japan, the double-sided silicon strip sub-detector of the Belle II experiment is read out by 1748 APV25 chips. FPGAs perform several calculations on the digitized signals. One of them will be "Hit Time Finding": the determination of the time and amplitude of the signal peaks of each event in real time using pre-programmed neural networks. This work analyses the possibility, precision and reliability of these calculations depending on various parameters.

UR - https://www.scopus.com/pages/publications/85072866541

M3 - Conference article

AN - SCOPUS:85072866541

SN - 1824-8039

VL - 343

JO - Proceedings of Science

JF - Proceedings of Science

Y2 - 17 September 2018 through 21 September 2018

ER -

Machine learning: Hit time finding with a neural network

Abstract

Other files and links

Fingerprint

Cite this