Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424038" target="_blank" >RIV/00216208:11320/20:10424038 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=KmqdVdbn8L" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=KmqdVdbn8L</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1748-0221/15/06/P06005" target="_blank" >10.1088/1748-0221/15/06/P06005</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques

Popis výsledku v původním jazyce

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 root S = 13 TeV, 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.

Název v anglickém jazyce

Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques

Popis výsledku anglicky

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 root S = 13 TeV, 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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10304 - Nuclear physics

Projekt

<a href="/cs/project/LM2018104" target="_blank" >LM2018104: Výzkumná infrastruktura pro experimenty v CERN</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of Instrumentation [online]

ISSN

1748-0221

e-ISSN

—

Svazek periodika

15

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

87

Strana od-do

P06005

Kód UT WoS článku

000545350900005

EID výsledku v databázi Scopus

—