prikaz prve stranice dokumenta Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja
  Download
PDF 4.49 MB
master's thesis
Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja
Split: University of Split, University of Split, Faculty of science, 2020. urn:nbn:hr:166:806797
Šarić, Toni
University of Split
Faculty of Science
Department of Physics

Institutional repository: Repository of Faculty of Science

Cite this document

Šarić, T. (2020). Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:806797

Šarić, Toni. "Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:806797

Šarić, Toni. "Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja." Master's thesis, University of Split, Faculty of Science, 2020. https://urn.nsk.hr/urn:nbn:hr:166:806797

Šarić, T. (2020). 'Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja', Master's thesis, University of Split, Faculty of Science, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:166:806797

Šarić T. Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja [Master's thesis]. Split: University of Split, Faculty of Science; 2020 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:166:806797

T. Šarić, "Identifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja", Master's thesis, University of Split, Faculty of Science, Split, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:166:806797

Metadata
TitleIdentifikacija miona u CMS detektoru pri proton-proton sudarima energije \(\sqrt{s}=13\) TeV metodama strojnog učenja
Title (english)Identification of muons with the CMS detector in proton-proton collisions at \(\sqrt{s}=13\) TeV using machine-learning methods
AuthorToni Šarić
MentorMarko Kovač (mentor)
MentorHrvoje Kalinić (pomoć pri izradi, neposredni voditelj)
Committee memberMarko Kovač (predsjednik povjerenstva)
Committee memberHrvoje Kalinić (član povjerenstva)
Committee memberNikola Godinović (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Physics)
Split
Defense date and country2020-07-02, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Physics
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom diplomskom radu napravljena je identifikacija objekata dobivenih simulacijom Drell-Yan procesa. Rekonstruirani objekti podijeljeni su u dvije klase: u klasu signalnih i u klasu pozadinskih objekata koji su zatim spremljeni u skup podataka. Signalni objekti su mioni najvjerojatnije nastali u primarnom verteksu, dok su pozadina objekti pogrešno rekonstruirani kao mioni. Analize podataka na CERN-u nerijetko koriste takozvane cut based ID metode za identifikaciju objekata, stoga ovaj rad razmatra mogućnost zamjene tog pristupa pristupom strojnog učenja. Strojno učenje uči model razlikovati objekte treniranjem na već klasificiranim podacima da bi bio sposoban identificirati signal u eksperimentalnim podacima prikupljenim radom CMS detektora. Želeći imitirati ovaj proces, kreirani skup podataka dijeli se na skup podatka za treniranje i na skup za testiranje. Glavnu prepreku u ostvarenju cilja predstavlja neuravnoteženost klasa jer je broj pozadinskih objekata uvelike, približno 14 puta, manji od signalnih. Obrađena su dva pristupa problemu neuravnoteženosti podataka. Prvi pristup je težinsko treniranje koje mijenja težine funkciji pogreške. Drugi pristup je balansiranje klasa dodavanjem ili izbacivanjem objekata skupa podataka za treniranje.
Abstract (english)
In this thesis, the identification of objects obtained by simulation of the Drell-Yan process is made. The reconstructed objects were divided into two classes: the signal object class and the background object class, which were then stored in a data set. Signal objects are muons most likely formed in the primary vertex, while background objects are inaccurately reconstructed as muons. Data analysis at CERN often use so-called cut-based ID methods to identify objects, therefore this paper considers the possibility of replacing this approach with a machine learning strategy. Machine learning teaches the model to distinguish objects by training on already classified data to be able to identify the signal in the experimental data collected by the operation of the CMS detector. Wanting to mimic this process, the created data set is divided into a training data set and a test data set. In achieving the goal, the main impediment were the imbalance of classes which means the number of background objects is much, approximately 14 times, less than the signal. Two approaches to the problem of data imbalance are discussed. The first approach is weight balancing which changes the weights of the error function. The second approach is to balance classes by adding or removing objects from a training data set.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:806797
Study programmeTitle: Physics; specializations in: major in teaching, major in Astrophysics, major in Biophysics, major in Enviromental physics, major in Computational physics, major in Astrophysics and physics of elemental particles
Course: major in Computational physics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra fizike (magistar/magistra fizike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-02-01 11:13:35