Predviđanje vremenske prognoze pomoću analize vremenskih serija

master's thesis

• Title (english): Weather Forecast Prediction Using Time Series Analysis
• Author: Andrea Lukić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu opisane su metode analize i predviđanja vremenskih serija, s posebnim naglaskom na predviđanje koristeći povratne neuronske mreže. Detaljno su objašnjeni modeli RNN, LSTM, GRU i BRNN mreža. Ostvaren je programski sustav za predviđanje temperature koristeći LSTM mrežu, detaljno je prikazan postupak implementacije te ispitan i vrednovan prikladnim mjerama vrednovanja. Na kraju su prikazani i opisani rezultati ispitivanja.

Abstract (english)

This thesis describes methods of analysis and prediction of time series, with special emphasis on prediction using reccurent neural networks. Models of RNN, LSTM, GRU and BRNN networks are explained in detail. A software system for temperature prediction using the LSTM network was developed, the implementation procedure was presented in detail, and it was tested and evaluated with appropriate evaluation measures. Finally, the test results are presented and described.

• Keywords: vremenska serija; vremenska prognoza; RNN; LSTM; GRU
• Keywords (english): time series; weather forecast; RNN; LSTM; GRU
• Language: croatian
• URN:NBN: urn:nbn:hr:168:449425
• 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: 2023-01-13 10:19:19