Statistical classification techniques in high energy physics (SDDT algorithm)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F16%3A00304798" target="_blank" >RIV/68407700:21340/16:00304798 - isvavai.cz</a>

Výsledek na webu

<a href="http://iopscience.iop.org/1742-6596/738/1/012034" target="_blank" >http://iopscience.iop.org/1742-6596/738/1/012034</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1742-6596/738/1/012034" target="_blank" >10.1088/1742-6596/738/1/012034</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Statistical classification techniques in high energy physics (SDDT algorithm)

Popis výsledku v původním jazyce

We present our proposal of the supervised binary divergence decision tree with nested separation method based on the generalized linear models. A key insight we provide is the clustering driven only by a few selected physical variables. The proper selection consists of the variables achieving the maximal divergence measure between two different classes. Further, we apply our method to Monte Carlo simulations of physics processes corresponding to a data sample of top quark-antiquark pair candidate events in the lepton+jets decay channel. The data sample is produced in pp collisions at root S = 1.96 TeV. It corresponds to an integrated luminosity of 9.7 fb-1 recorded with the D0 detector during Run II of the Fermilab Tevatron Collider. The efficiency of our algorithm achieves 90% AUC in separating signal from background. We also briefly deal with the modification of statistical tests applicable to weighted data sets in order to test homogeneity of the Monte Carlo simulations and measured data. The justification of these modified tests is proposed through the divergence tests.

Název v anglickém jazyce

Statistical classification techniques in high energy physics (SDDT algorithm)

Popis výsledku anglicky

We present our proposal of the supervised binary divergence decision tree with nested separation method based on the generalized linear models. A key insight we provide is the clustering driven only by a few selected physical variables. The proper selection consists of the variables achieving the maximal divergence measure between two different classes. Further, we apply our method to Monte Carlo simulations of physics processes corresponding to a data sample of top quark-antiquark pair candidate events in the lepton+jets decay channel. The data sample is produced in pp collisions at root S = 1.96 TeV. It corresponds to an integrated luminosity of 9.7 fb-1 recorded with the D0 detector during Run II of the Fermilab Tevatron Collider. The efficiency of our algorithm achieves 90% AUC in separating signal from background. We also briefly deal with the modification of statistical tests applicable to weighted data sets in order to test homogeneity of the Monte Carlo simulations and measured data. The justification of these modified tests is proposed through the divergence tests.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Journal of Physics: Conference Series

ISBN

—

ISSN

1742-6588

e-ISSN

1742-6588

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

IOP Publishing Ltd.

Místo vydání

Bristol

Místo konání akce

Athens

Datum konání akce

23. 5. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000403403900034