Dinamičko predviđanje trase kretanja pokretljivog objekta u geoprostoru

master's thesis

• Title (english): Dynamic Prediction of Mobile Object Moving Path in Geographic Space
• Author: Bruno Blažeka
• Mentor: Dejan Škvorc (mentor)
• Committee member: Dejan Škvorc (predsjednik povjerenstva)
• Committee member: Željka Mihajlović (član povjerenstva)
• Committee member: Leonardo Jelenković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-18, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj diplomski rad proučava mogućnosti predviđanja gibanja pokretljivog objekta u geoprostoru korištenjem odabranih algoritama strojnog učenja. Na početku se objašnjava arhitektura implementiranog rješenja, objašnjavaju ostvarene funkcionalnosti. Nakon toga se razrađuje teoretsku pozadinu metoda primijenjenih u ovom diplomskom radu. Dotiče se neuronskih mreža, a detaljnije objašnjava što su to učenje na temelju primjera, polinomijalna regresija i Markovljev model. Kasnije se objašnjava kako su implementirani algoritmi temeljeni na prethodno obrađenim algoritmima. Na kraju se prikazuju i komentiraju rezultati evaluacije uspješnosti algoritama koristeći ručno izgenerirane ulazne skupove.

Abstract (english)

Subject of this master thesis is dynamic movement prediction using various machine learning algorithms. At the beginning, implemented software is examined and functionalities are mentioned. Afterwards, theoretical background of implemented algorithms is explained. Neural networks are mentioned and instance based learning, polynomial regression and Markov models are defined and explained in more detail. It is followed by technical explanation of implemented algorithms. At the end, results of evaluation of manually generated data sets are presented and analysed.

• Keywords: Predviđanje gibanja; polinomijalna regresija; učenje na temelju primjera; Markovljevi modeli
• Keywords (english): Movement prediction; polynomial regression; instance based learning; Markov model
• Language: croatian
• URN:NBN: urn:nbn:hr:168:018278
• 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: 2020-01-07 16:49:50