Predviđanje budućih očitanja uređaja Interneta stvari putem dubokog učenja

master's thesis

• Title (english): Predicting IoT Readings With Deep Learning
• Author: Stjepan Kovačić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Mirko Poljak (član povjerenstva)
• Committee member: Tomislav Marković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada je primjena modela dubokog učenja na problem predviđanja budućih očitanja uređaja Interneta stvari. Objašnjeni su pojmovi Interneta stvari i dubokog učenja. Razvijen je LSTM model za predviđanje. Provedeni su postupci učenja modela i optimiranja hiperparametara. Predstavljeni su i analizirani rezultati razvijenog modela te su predložene moguće nadogradnje modela. Razvijeno je i predstavljeno programsko rješenje na odabranoj IoT platformi.

Abstract (english)

The subject of this thesis is the application of deep learning models for the problem of predicting IoT readings. The concepts of the Internet of Things and deep learning are explained. An LSTM model has been developed. Model training was performed as well as hyperparameter optimization. The results of the model are presented and analyzed. Possible model upgrades are proposed. IoT solution on the chosen IoT platform was developed and presented.

• Keywords: Internet stvari; duboko učenje; vremenski nizovi; predviđanje; RNN; LSTM
• Keywords (english): Internet of Things; deep learning; time series; prediction; RNN; LSTM
• Language: croatian
• URN:NBN: urn:nbn:hr:168:261091
• 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: 2023-01-14 09:09:57