A neural network clustering algorithm for the ATLAS silicon pixel detector
2014
Аутори
Aad, G.Agatonović-Jovin, Tatjana
Ćirković, Predrag
Dimitrievska, A.
Krstić, Jugoslav B.
Mamužić, Judita
Marjanović, M.
Popović, D. S.
Sijacki, Dj.
Simić, Lj.
Vranješ, Nenad
Vranješ Milosavljević, Marija
ATLAS Collaboration (ukupan broj autora: 2877)
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
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.
Кључне речи:
Particle tracking detectors / Particle tracking detectors (Solid-state detectors)Извор:
Journal of Instrumentation, 2014, 9Финансирање / пројекти:
- ANPCyT, Argentina, YerPhI, Armenia, ARC, Australia, BMWF, Austria, FWF, Austria, ANAS, Azerbaijan, SSTC, Belarus, CNPq, Brazil, FAPESP, Brazil, NSERC, Canada, NRC, Canada, CFI, Canada, CERN, CONICYT, Chile, CAS, China, MOST, China, NSFC, China, COLCIENCIAS, Colombia, MSMT CR, Czech Republic, MPO CR, Czech Republic, VSC CR, Czech Republic, DNRF, Denmark, DNSRC, Denmark, Lundbeck Foundation, Denmark, EPLANET, European Union, ERC, European Union, NSRF, European Union, IN2P3-CNRS, France, CEA-DSM/IRFU, France, GNSF, Georgia, BMBF, Germany, DFG, Germany, HGF, Germany, MPG, Germany, AvH Foundation, Germany, GSRT, Greece, NSRF, Greece, ISF, Israel, MINERVA, Israel, GIF, Israel, I-CORE, Israel, Benoziyo Center, Israel, INFN, Italy, MEXT, Japan, JSPS, Japan, CNRST, Morocco, FOM, Netherlands, NWO, Netherlands, BRF, Norway, RCN, Norway, MNiSW, Poland, NCN, Poland, GRICES, Portugal, FCT, Portugal, MNE/IFA, Romania, MES of Russia, ROSATOM, Russian Federation, JINR, MSTD, Serbia, MSSR, Slovakia, ARRS, Slovenia, MIZS, Slovenia, DST/NRF, South Africa, MINECO, Spain, SRC, Sweden, Wallenberg Foundation, Sweden, SER, Switzerland, SNSF, Switzerland, Canton of Bern, Switzerland, Canton of Geneva, Switzerland, NSC, Taiwan, TAEK, Turkey, STFC, United Kingdom, Royal Society, United Kingdom, Leverhulme Trust, United Kingdom, DOE, United States of America, NSF, United States of America, ICREA
DOI: 10.1088/1748-0221/9/09/P09009
ISSN: 1748-0221
WoS: 000343281300046
Scopus: 2-s2.0-84907683450
Колекције
Институција/група
VinčaTY - JOUR AU - Aad, G. AU - Agatonović-Jovin, Tatjana AU - Ćirković, Predrag AU - Dimitrievska, A. AU - Krstić, Jugoslav B. AU - Mamužić, Judita AU - Marjanović, M. AU - Popović, D. S. AU - Sijacki, Dj. AU - Simić, Lj. AU - Vranješ, Nenad AU - Vranješ Milosavljević, Marija PY - 2014 UR - https://vinar.vin.bg.ac.rs/handle/123456789/175 AB - 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. T2 - Journal of Instrumentation T1 - A neural network clustering algorithm for the ATLAS silicon pixel detector VL - 9 DO - 10.1088/1748-0221/9/09/P09009 ER -
@article{ author = "Aad, G. and Agatonović-Jovin, Tatjana and Ćirković, Predrag and Dimitrievska, A. and Krstić, Jugoslav B. and Mamužić, Judita and Marjanović, M. and Popović, D. S. and Sijacki, Dj. and Simić, Lj. and Vranješ, Nenad and Vranješ Milosavljević, Marija", year = "2014", 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.", journal = "Journal of Instrumentation", title = "A neural network clustering algorithm for the ATLAS silicon pixel detector", volume = "9", doi = "10.1088/1748-0221/9/09/P09009" }
Aad, G., Agatonović-Jovin, T., Ćirković, P., Dimitrievska, A., Krstić, J. B., Mamužić, J., Marjanović, M., Popović, D. S., Sijacki, Dj., Simić, Lj., Vranješ, N.,& Vranješ Milosavljević, M.. (2014). A neural network clustering algorithm for the ATLAS silicon pixel detector. in Journal of Instrumentation, 9. https://doi.org/10.1088/1748-0221/9/09/P09009
Aad G, Agatonović-Jovin T, Ćirković P, Dimitrievska A, Krstić JB, Mamužić J, Marjanović M, Popović DS, Sijacki D, Simić L, Vranješ N, Vranješ Milosavljević M. A neural network clustering algorithm for the ATLAS silicon pixel detector. in Journal of Instrumentation. 2014;9. doi:10.1088/1748-0221/9/09/P09009 .
Aad, G., Agatonović-Jovin, Tatjana, Ćirković, Predrag, Dimitrievska, A., Krstić, Jugoslav B., Mamužić, Judita, Marjanović, M., Popović, D. S., Sijacki, Dj., Simić, Lj., Vranješ, Nenad, Vranješ Milosavljević, Marija, "A neural network clustering algorithm for the ATLAS silicon pixel detector" in Journal of Instrumentation, 9 (2014), https://doi.org/10.1088/1748-0221/9/09/P09009 . .