Dijagnoza diabetesa putem strojnog učenja

undergraduate thesis

• Title (english): Machine Learning for Diagnosis of Diabetes
• Author: Bruno Horvat
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Zoran Medić (član povjerenstva)
• Committee member: Igor Stančin (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Fokus ovoga rada bio je na analizi algoritama strojnog učenja primijenjenih na problem dijagnoze dijabetesa. U uvodu je napisano o samome dijabetesu i njegovim tipovima, a nakon toga je definirano što je to strojno učenje. Zadan je problem određivanja algoritma učenja na skupu podataka te je analizirana preciznost svakog od unaprijed određenih algoritama. Kad je određen odgovarajući algoritam, bilo je potrebno izraditi grafičko sučelje prema korisniku. Grafičko sučelje prima samo realne brojeve i nije moguć unos bilo kakvog teksta ili sličnog. Za unos neke od vrijednosti koja nije realan broj, otvara se novi prozor koji izvještava korisnika o pogrešnom unosu. Za svaki dobar unos podataka, otvara se novi prozor koji sa sigurnošću od 74.8% tvrdi da osoba ima/nema dijabetes. Nakon svakog unosa podataka i detekcije dijabetesa, stari unos se briše i grafičko sučelje je spremno primiti nove parametre.

Abstract (english)

The focus of this project was to analyze machine learning algorithms applied to the problem of diabetes diagnosis. In the introduction, it was written about diabetes itself and its types, and after that it was defined what machine learning is. Then, it was defined the problem of determining the algorithm for learning the data and analyzing the accuracy of each of the predetermined algorithms. When the appropriate algorithm was selected, it was necessary to create a graphical user interface. The graphical interface only accepts real numbers and it is not possible to enter any text or similar. When a value other than a real number is entered, a new window opens informing the user of the incorrect input. For each good data input, a new window opens which claims that the person has/does not have diabetes with a certainty of 74.8%.

• Keywords: dijabetes; strojno učenje; medicina; algoritam; umjetna inteligencija
• Keywords (english): diabetes; machine learning; medicine; algorithm; artificial intelligence
• Language: croatian
• URN:NBN: urn:nbn:hr:168:412878
• Study programme: Title: Computing; 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 08:54:30