Detekcija oboljenja na temelju genetskih značajki

master's thesis

• Title (english): Detecting Complex Diseases Using Genetic Features
• Author: Sofia Čolaković
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: Marko Čupić (član povjerenstva)
• Committee member: Leonardo Jelenković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu istažen je problem detekcije složenih bolesti na temelju genetskih
značajki. Predloženo rješnje uključuje odabir značajki uz pomoć genetskog algoritma
te detekciju bolesti algoritmima strojnog učenja. Predložen je postupak pronalaženja
funkcije cilja za odabir značajki korištenjem genetskog programiranja. Rješenje je
ispitano na skupu podataka prikupljenom od pacijenata s reumatoidnim artritisom.
Rezultati ispitivanja i zaključi priloženi su radu.

Abstract (english)

This thesis explores the problem of complex disease detection using genetic data.
The proposed solution is based on feature selection using genetic algorithm and disease
detection using machine learning algorithms. A method for deriving an optimal goal
function based on genetic programming is introduced and examined. The proposed
solution is tested on a dataset containing data collected from rheumatoid arthritis patients. The results are presented and discussed.

• Keywords: detekcija bolesti; genetski algoritam; strojno učenje; SVM; genetsko programiranje
• Keywords (english): disease detection; genetic algorithm; machine learning; SVM; genetic programming
• Language: english
• URN:NBN: urn:nbn:hr:168:702097
• 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 08:17:44