Pouzdana klasifikacija tumorskih markera

master's thesis

• Title (english): Reliable classification of tumor markers
• Author: Nikolina Očić
• Mentor: Damir Seršić (mentor)
• Committee member: Damir Seršić (predsjednik povjerenstva)
• Committee member: Marko Subašić (član povjerenstva)
• Committee member: Ana Sović Kržić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Predstavljena je i opisana problematika ranog otkrivanja tumora te je opisana problematika tumora jajnika i prostate kao središta razvijenog sustava. Opisana je važnost razvijenog sustava kao pomoći za rano otkrivanje tumora. Prikazan je format ulaznih podataka te objašnjena metoda za dobivanje istih. Razvijen je sustav koji uz pomoć metoda za obradu signala te strojnog učenja klasificira ulazne podatke u kategorije zdravlja. Objašnjena je metoda korištena za obradu podataka te metode korištene za evaluaciju istih. Također je temeljito objašnjena metoda korištena za izgradnju modela klasifikacije. Prikazani su i objašnjeni dobiveni rezultati u obje grupe tumora.

Abstract (english)

The problem of early cancer detection is presented and described. The problems of ovary and prostate cancer, as they are the center of developed system, are also described. Importance of developed system as a helping tool for early cancer detection is presented. Format of input data and corresponding method of data acquiring are presented. Developed system, which is based upon methods of signal processing and machine learning, classifies input data into health categories. Method for signal processing and multiple methods for evaluating data are explained. Also, model for classification is thoroughly explained. Obtained results are shown and explained for both cancer groups.

• Keywords: tumori; SELDI-TOF; strojno učenje; Haarov valićni paket; entropija; Gini DIversity Index; Fisher Score; stroj potpornih vektora
• Keywords (english): tumors; SELDI-TOF; machine learning; Haar's wavelet packet; GIni Diversity Index; Fisher Score; support vector machine
• Language: croatian
• URN:NBN: urn:nbn:hr:168:599739
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 10:58:29