A method is presented to reduce the size of a classification problem by automatically ranking the relative importance of available features. The variables are importance-sorted with a decision tree algorithm and correlated ones are removed after ranking. We tested the approach with the case of highly boosted di-jet resonances decaying to two b-quarks, to be selected against an overwhelming QCD background with a deep neural network (DNN). We make the relation between different importance rankings obtained with different algorithms explicit. We also show how the signal-to-background ratio changes, varying the number of features in input to the DNN.

Automatic selection of observables for the analysis of high-energy particle jets / Di Luca, A.; Cristoforetti, M.; Follega, F. M.; Iuppa, R.. - In: IL NUOVO CIMENTO C. - ISSN 2037-4909. - ELETTRONICO. - 44:2-3(2021). [10.1393/ncc/i2021-21042-5]

Automatic selection of observables for the analysis of high-energy particle jets

Di Luca A.;Follega F. M.;Iuppa R.
2021

Abstract

A method is presented to reduce the size of a classification problem by automatically ranking the relative importance of available features. The variables are importance-sorted with a decision tree algorithm and correlated ones are removed after ranking. We tested the approach with the case of highly boosted di-jet resonances decaying to two b-quarks, to be selected against an overwhelming QCD background with a deep neural network (DNN). We make the relation between different importance rankings obtained with different algorithms explicit. We also show how the signal-to-background ratio changes, varying the number of features in input to the DNN.
2-3
Di Luca, A.; Cristoforetti, M.; Follega, F. M.; Iuppa, R.
Automatic selection of observables for the analysis of high-energy particle jets / Di Luca, A.; Cristoforetti, M.; Follega, F. M.; Iuppa, R.. - In: IL NUOVO CIMENTO C. - ISSN 2037-4909. - ELETTRONICO. - 44:2-3(2021). [10.1393/ncc/i2021-21042-5]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/320432
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact