prikaz prve stranice dokumenta Primjena strojnog učenja u dijagnostici dijabetesa
Access restricted to students and staff of home institution
undergraduate thesis
Primjena strojnog učenja u dijagnostici dijabetesa
Dubrovnik: University of Dubrovnik, 2022. urn:nbn:hr:155:652012
Lazo, Mia
University of Dubrovnik
Faculty of Electrical Engineering and Applied Computing

Institutional repository: Repository of the University of Dubrovnik

Cite this document

Lazo, M. (2022). Primjena strojnog učenja u dijagnostici dijabetesa (Undergraduate thesis). Dubrovnik: University of Dubrovnik. Retrieved from https://urn.nsk.hr/urn:nbn:hr:155:652012

Lazo, Mia. "Primjena strojnog učenja u dijagnostici dijabetesa." Undergraduate thesis, University of Dubrovnik, 2022. https://urn.nsk.hr/urn:nbn:hr:155:652012

Lazo, Mia. "Primjena strojnog učenja u dijagnostici dijabetesa." Undergraduate thesis, University of Dubrovnik, 2022. https://urn.nsk.hr/urn:nbn:hr:155:652012

Lazo, M. (2022). 'Primjena strojnog učenja u dijagnostici dijabetesa', Undergraduate thesis, University of Dubrovnik, accessed 18 November 2024, https://urn.nsk.hr/urn:nbn:hr:155:652012

Lazo M. Primjena strojnog učenja u dijagnostici dijabetesa [Undergraduate thesis]. Dubrovnik: University of Dubrovnik; 2022 [cited 2024 November 18] Available at: https://urn.nsk.hr/urn:nbn:hr:155:652012

M. Lazo, "Primjena strojnog učenja u dijagnostici dijabetesa", Undergraduate thesis, University of Dubrovnik, Dubrovnik, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:155:652012

Metadata
TitlePrimjena strojnog učenja u dijagnostici dijabetesa
AuthorMia Lazo
MentorMario Miličević (mentor)
Committee memberMario Miličević (predsjednik povjerenstva)
Committee memberAna Kešelj (član povjerenstva)
Committee memberKrunoslav Žubrinić (član povjerenstva)
GranterUniversity of Dubrovnik
(Faculty of Electrical Engineering and Applied Computing)
Dubrovnik
Defense date and country2022-07-08, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
U radu je opisan problem dijagnostike dijabetesa pomoću demografskih i kliničkih podataka. Cilj istraživanja je pokazati kako se korištenjem strojnog učenja odnosno algoritama iz programskog alata Weka može pomoći liječniku kod postavljanja dijagnoze. U uvodnom dijelu prikazana su druga istraživanja i radovi u kojima su primijenjeni različiti pristupi i algoritmi strojnog učenja u cilju dijagnostike dijabetesa. Detaljno je opisan i odabrani skup podataka. Na temelju rezultata prethodnih radova i dodatnih istraživanja odabrane su dvije metode koje su ostvarile najbolje rezultate klasifikacije - Multilayer Perceptron i LMT (Logistic Model Tree). Detaljno su opisana oba algoritma, kao i metrike pomoću kojih se mjere performanse modela. Rezultati su pokazali da odabrani algoritmi imaju visoku točnost dijagnostike dijabetesa te da bi u praksi mogli predstavljati značajnu pomoć liječniku.
Abstract (english)
The paper describes the problem of classification of diabetes using demographic and clinical data. The goal of the research is to show how to use machine learning, i.e. algorithms from the Weka software tool, can help the doctor in making a diagnosis. In the introductory part, other research and papers are presented in which different approaches and algorithms of machine learning are applied to diagnose diabetes. The selected data set is described in detail. Based on the results of previous works and additional research, two methods were chosen that realized the best classification results - Multilayer Perceptron and LMT (Logistic Model Tree). Both algorithms are described in detail as well, as the metrics used to measure the performance of the model. The results showed that the selected algorithms have a high accuracy in the diagnosis of diabetes and that in practice they could represent a significant help to the doctor.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:155:652012
Study programmeTitle: Applied Computer Science / Information Management
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2022-07-15 11:15:52