prikaz prve stranice dokumenta Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu
  Download
PDF 2.08 MB
undergraduate thesis
Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu
2024. urn:nbn:hr:190:426888
Došen, Leonarda
University of Rijeka
Faculty of Engineering
Department of Mathematics, Physics, and Foreign Languages
Section of Applied Mathematics

Cite this document

Došen, L. (2024). Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu (Undergraduate thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:426888

Došen, Leonarda. "Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2024. https://urn.nsk.hr/urn:nbn:hr:190:426888

Došen, Leonarda. "Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2024. https://urn.nsk.hr/urn:nbn:hr:190:426888

Došen, L. (2024). 'Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu', Undergraduate thesis, University of Rijeka, Faculty of Engineering, accessed 05 September 2024, https://urn.nsk.hr/urn:nbn:hr:190:426888

Došen L. Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu [Undergraduate thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2024 [cited 2024 September 05] Available at: https://urn.nsk.hr/urn:nbn:hr:190:426888

L. Došen, "Upotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu", Undergraduate thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:190:426888

Please login to the repository to save this object to your list.
Metadata
TitleUpotreba ROC krivulja u evaluaciji performansi sustava u inženjerstvu
Title (english)Using the ROC curve to evaluate the performance of technical systems
AuthorLeonarda Došen
MentorLoredana Simčić (mentor)
MentorNelida Črnjarić (komentor)
Committee memberSamir Žic (predsjednik povjerenstva)
Committee memberLoredana Simčić (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Mathematics, Physics, and Foreign Languages)
(Section of Applied Mathematics)
Rijeka
Defense date and country2024-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Ovaj završni rad predstavlja istraživanje primjene modela strojnog učenja u predviđanju performansi timova i vozača u Formuli 1 pomoću ROC (eng. Receiver Operating Characteristic) krivulja. Cilj je pokazati kako se podaci iz prošlih utrka mogu iskoristiti za stvaranje modela koji predviđa vjerojatnost postizanja odabranih rezultata, poput osvajanja pobjedničkog postolja i pobjede u utrkama. Kroz ovaj rad opisuje se proces strojnog učenja, objašnjavaju se algoritmi strojnog učenja, način prikupljanja i obrade podataka, te evaluacija performansi modela pomoću različitih metrika. Model logističke regresije pokazuje se najboljim za predviđanje osvajanja podija, dok su slučajne šume najuspješnije u predviđanju pobjednika. Unatoč ograničenjima, istraživanje pokazuje potencijal korištenja strojnog učenja u predviđanju performansi inženjerskih sustava, pružajući temelj i potrebna znanja za buduća istraživanja.
Abstract (english)
This thesis presents a study on the application of machine learning models in predicting the performance of teams and drivers in Formula 1 using ROC (Receiver Operating Characteristic) curves. The aim is to show how data from past races can be used to create a model that predicts the likelihood of achieving selected results, such as winning a podium or a race. This thesis describes the process of machine learning, explains the machine learning algorithms, the methods of data collection and processing, and the evaluation of model performance using various metrics. The logistic regression model is shown to be the best for predicting podium finishes, while random forests are the most successful in predicting winners. Despite the limitations, the research demonstrates the potential of using machine learning in predicting the performance of engineering systems, providing a foundation and necessary knowledge for future research.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:426888
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2024-07-13 08:25:16