prikaz prve stranice dokumenta Dijagnostika kožnih bolesti primjenom strojnog učenja
Access restricted to students and staff of home institution
undergraduate thesis
Dijagnostika kožnih bolesti primjenom strojnog učenja
2019. urn:nbn:hr:155:277464
Mojaš, Elena
University of Dubrovnik
Department of Engineering and Technology

Cite this document

Mojaš, E. (2019). Dijagnostika kožnih bolesti primjenom strojnog učenja (Undergraduate thesis). Dubrovnik: University of Dubrovnik. Retrieved from https://urn.nsk.hr/urn:nbn:hr:155:277464

Mojaš, Elena. "Dijagnostika kožnih bolesti primjenom strojnog učenja." Undergraduate thesis, University of Dubrovnik, 2019. https://urn.nsk.hr/urn:nbn:hr:155:277464

Mojaš, Elena. "Dijagnostika kožnih bolesti primjenom strojnog učenja." Undergraduate thesis, University of Dubrovnik, 2019. https://urn.nsk.hr/urn:nbn:hr:155:277464

Mojaš, E. (2019). 'Dijagnostika kožnih bolesti primjenom strojnog učenja', Undergraduate thesis, University of Dubrovnik, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:155:277464

Mojaš E. Dijagnostika kožnih bolesti primjenom strojnog učenja [Undergraduate thesis]. Dubrovnik: University of Dubrovnik; 2019 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:155:277464

E. Mojaš, "Dijagnostika kožnih bolesti primjenom strojnog učenja", Undergraduate thesis, University of Dubrovnik, Dubrovnik, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:155:277464

Please login to the repository to save this object to your list.
Metadata
TitleDijagnostika kožnih bolesti primjenom strojnog učenja
AuthorElena Mojaš
MentorMario Miličević (mentor)
Committee memberMario Miličević (predsjednik povjerenstva)
GranterUniversity of Dubrovnik
(Department of Engineering and Technology)
Dubrovnik
Defense date and country2019-09-17, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Information Systems
Abstract
U radu je opisan problem klasificiranja kožnih bolesti te atributi koji pomaţu u tome. Također su objašnjeni mogući rezultati izlaznog atributa od kojih svaki predstavlja jedan tip bolesti. Cilj je olakšati dijagnostiku kožnih bolesti koristeći programski alat Weka tako da se pronađu algoritmi koji će davati najbolje rezultate. Pronalaze se algoritmi koji dobivaju najveći postotak točnosti dijagnosticiranja na temelju testnih podataka. Detaljno su opisani algoritmi LMT i SMO koji daju najbolje rezultate za navedenu problematiku. Također su opisane i njihove značajke i principi na kojima rade. Zatim su obrađeni rezultati u Weki te pojedinačni rezultati za svaki od navedenih algoritama. Na kraju slijedi zaključak rada o korištenim algoritmima i o samoj problematici dijagnosticiranja kožnih bolesti.
Abstract (english)
The paper describes the problem of classification of skin diseases and the attributes that help in this. The possible results of the output attribute, each representing one type of disease, are also explained. The goal is to facilitate the diagnosis of skin diseases by using the Weka software tool to find the algorithms that will produce the best results. Algorithms are found that get the highest percentage of diagnostic accuracy based on test data. The LMT and SMO algorithms that give the best results for these problems are described in detail. Their features and the principles on which they work are also described. The results were then processed in Weka and the individual results for each of the mentioned algorithms. Finally, there is the conclusion about used algorithms and the problem of diagnosing skin diseases.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:155:277464
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 on2019-10-11 07:15:15