prikaz prve stranice dokumenta Sustav za oblikovanje i validaciju modela prediktivne analitike
No public access
master's thesis
Sustav za oblikovanje i validaciju modela prediktivne analitike
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. urn:nbn:hr:168:477498
Poslon, Mato
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Poslon, M. (2016). Sustav za oblikovanje i validaciju modela prediktivne analitike (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:477498

Poslon, Mato. "Sustav za oblikovanje i validaciju modela prediktivne analitike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:477498

Poslon, Mato. "Sustav za oblikovanje i validaciju modela prediktivne analitike." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:477498

Poslon, M. (2016). 'Sustav za oblikovanje i validaciju modela prediktivne analitike', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:477498

Poslon M. Sustav za oblikovanje i validaciju modela prediktivne analitike [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2016 [cited 2024 November 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:477498

M. Poslon, "Sustav za oblikovanje i validaciju modela prediktivne analitike", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2016. Available at: https://urn.nsk.hr/urn:nbn:hr:168:477498

Metadata
TitleSustav za oblikovanje i validaciju modela prediktivne analitike
Title (english)System for Design and Validation of a Predictive Analytics Model
AuthorMato Poslon
MentorVlado Sruk (mentor)
Committee memberVlado Sruk (predsjednik povjerenstva)
Committee memberLeonardo Jelenković (član povjerenstva)
Committee memberAnte Đerek (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2016-07-04, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu su opisani modeli prediktivne analitike na primjeru medicinske dijagnostike. Dan je opis najpoznatijih modela za rak dojke i kao referentni korišten je Gailov model. Rezultati PrOnDi modela uspoređeni su sa rezultatima Gailovog modela. Poboljšani model NNPrOnDi razvijen je koristeći Java programski jezik koji kao model koristi neuronske mreže i genetski algoritam. Analizirana je učinkovitost poboljšanog sustava u ovisnosti o parametrima modela i analiza je pokazala da NNPrOnDi daje bolje rezultate. Na kraju su predložene smjernice daljnjeg razvoja modela.
Abstract (english)
Predicitve analytics models are described that are used in medical diagnostics. Most known models for breast cancer are described and Gail model is used as a reference. Results of the PrOnDi model are compared with those of the Gail model. An improved NNPrOnDi model is proposed that is implemented using Java programming language and neural network and genetic algorithms are used as a model. Results of this system are analyzed depending on the parameters of the model and analysis showed that NNPrOnDi gives better results. In the end, sugestions are made for further development of the model.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:477498
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 11:24:03