Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques. / The CMS collaboration.
в: Journal of Instrumentation, Том 15, № 6, P06005, 01.06.2020.Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование
}
TY - JOUR
T1 - Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
AU - The CMS collaboration
AU - Sirunyan, A. M.
AU - Tumasyan, A.
AU - Adam, W.
AU - Ambrogi, F.
AU - Bergauer, T.
AU - Dragicevic, M.
AU - Erö, J.
AU - Del Valle, A. Escalante
AU - Flechl, M.
AU - Frühwirth, R.
AU - Jeitler, M.
AU - Krammer, N.
AU - Krätschmer, I.
AU - Liko, D.
AU - Madlener, T.
AU - Mikulec, I.
AU - Rad, N.
AU - Schieck, J.
AU - Schöfbeck, R.
AU - Spanring, M.
AU - Waltenberger, W.
AU - Wulz, C. E.
AU - Zarucki, M.
AU - Drugakov, V.
AU - Mossolov, V.
AU - Gonzalez, J. Suarez
AU - Darwish, M. R.
AU - De Wolf, E. A.
AU - Di Croce, D. D.
AU - Janssen, X.
AU - Lelek, A.
AU - Pieters, M.
AU - Sfar, H. Rejeb
AU - Van Haevermaet, H.
AU - Van Mechelen, P.
AU - Van Putte, S.
AU - Van Remortel, N.
AU - Blekman, F.
AU - Bols, E. S.
AU - Chhibra, S. S.
AU - D'Hondt, J.
AU - De Clercq, J. D.
AU - Lontkovskyi, D.
AU - Lowette, S.
AU - Marchesini, I.
AU - Barnyakov, A.
AU - Blinov, V.
AU - Dimova, T.
AU - Kardapoltsev, L.
AU - Skovpen, Y.
PY - 2020/6/1
Y1 - 2020/6/1
N2 - Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
AB - Machine-learning (ML) techniques are explored to identify and classify hadronic decays of highly Lorentz-boosted W/Z/Higgs bosons and top quarks. Techniques without ML have also been evaluated and are included for comparison. The identification performances of a variety of algorithms are characterized in simulated events and directly compared with data. The algorithms are validated using proton-proton collision data at s = 13TeV, corresponding to an integrated luminosity of 35.9 fb-1. Systematic uncertainties are assessed by comparing the results obtained using simulation and collision data. The new techniques studied in this paper provide significant performance improvements over non-ML techniques, reducing the background rate by up to an order of magnitude at the same signal efficiency.
KW - Large detector-systems performance
KW - Pattern recognition, cluster finding, calibration and fitting methods
KW - ANNIHILATION
KW - ALGORITHMS
UR - http://www.scopus.com/inward/record.url?scp=85088524436&partnerID=8YFLogxK
U2 - 10.1088/1748-0221/15/06/P06005
DO - 10.1088/1748-0221/15/06/P06005
M3 - Article
AN - SCOPUS:85088524436
VL - 15
JO - Journal of Instrumentation
JF - Journal of Instrumentation
SN - 1748-0221
IS - 6
M1 - P06005
ER -
ID: 24871219