Klasifikacija tumora mozga pomoću metoda dubokog učenja

undergraduate thesis

• Title (english): Classification of Brain Tumors Using Deep Learning Methods
• Author: Elena Vukelić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Petar Afrić (član povjerenstva)
• Committee member: Lucija Šikić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-09-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu objašnjen je pojam dubokog učenja i osnovne značajke bioloških i umjetnih neuronskih mreža. Objašnjene su dvije vrste neuronskih mreža, duboke i konvolucijske te je dan primjer jedne konvolucijske neuronske mreže. Nadalje je iskazan postupak učenja mreža te je ukazano na neke probleme koji se mogu pojaviti prilikom učenja. U okviru tog poglavlja također je prikazan i Backpropagation algoritam. Nakon toga objašnjen je stroj s potpornim vektorima i njegova namjena. Na kraju je proveden eksperiment na skupu slika triju tipova tumora mozga i izneseni su rezultati klasifikacije.

Abstract (english)

This work describes deep learning and basic features of biological and artificial neural networks. It describes two types of neural networks, deep and convolutional, and one example of convolutional neural network is given. Furthermore, it explains process of training neural networks along with potetntial problems that can occur. In that chapter is also explained Backpropagation algorithm. After that is described support vector machine along with its usage. The final part of work shows experiment for which was used data set which has three types of brain tumors and result of classification is shown.

• Keywords: duboko učenje; neuronske mreže; konvolucijske neuronske mreže; Backpropagation algoritam; stroj s potpornim vektorima; klasifikacija
• Keywords (english): deep learning; neural networks; convolutional neural networks; Backpropagation algorithm; support vector machine; classification
• Language: croatian
• URN:NBN: urn:nbn:hr:168:833103
• 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: 2020-01-07 23:02:09