Analiza tokova velikih podataka uz pomoć metoda nenadziranog učenja

master's thesis

• Title (english): Analysing Big Data Streams Using Unsupervised Learning Methods
• Author: Matija Maljić
• Mentor: Damir Pintar (mentor)
• Committee member: Damir Pintar (predsjednik povjerenstva)
• Committee member: Zoran Skočir (član povjerenstva)
• Committee member: Boris Vrdoljak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-02-22, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad obrađuje primjenu algoritama strojnog učenja nad tokovima podataka za dubinsku analizu podataka. Prvo je dana definicija strojnog učenja. Definirane su različite vrste strojnog učenja i njihove razlike. Dodatno je objašnjeno nenadzirano učenje, odnosno grupiranje podataka. Zatim su definirani tokovi podataka, objašnjena njihova ograničenja pri rađenju analize i opisana moguća rješenja za primjenu algoritma grupiranja nad njima. Opisana je važnost telekomunikacija, definirane... More telekomunikacijske prijevare i objašnjeno je kako ih se algoritmima strojnog učenje mogu otkriti. U konačnici implementiran je E-Stream algoritam grupiranja tokova podataka i evaluiran nad sintetičkim skupom podataka. Less

Abstract (english)

This thesis deals with using machine learning on data streams for data analysis. Firstly, the definition of machine learning is given. Then explained differences between different types of machine learning. Additionally unsupervised learning and clustering was explained. Then data streams are defined, explained their limitations in the data analysis and described possible solutions for applying the clustering algorithms on them. After that, importance of telecommunications is... More explained, telecommunication fraud is defined and it is explained how frauds could be detected using machine learning algorithms. Finally, E-Stream algorithm for clustering data streams is implemented and evaluated using synthetic dataset. Less

• Keywords: Strojno učenje; tok podataka; grupiranje podataka; veliki podatci
• Keywords (english): Machine learning; data stream; data clustering; big data
• Language: croatian
• URN:NBN: urn:nbn:hr:168:990317
• 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: 2019-03-13 22:32:57