prikaz prve stranice dokumenta Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom
No public access
undergraduate thesis
Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. urn:nbn:hr:168:058218
Ratkovčić, Mihael
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ratkovčić, M. (2024). Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:058218

Ratkovčić, Mihael. "Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:058218

Ratkovčić, Mihael. "Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2024. https://urn.nsk.hr/urn:nbn:hr:168:058218

Ratkovčić, M. (2024). 'Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 29 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:058218

Ratkovčić M. Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2024 [cited 2024 November 29] Available at: https://urn.nsk.hr/urn:nbn:hr:168:058218

M. Ratkovčić, "Predikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:168:058218

Metadata
TitlePredikcija otvorenosti prozora u naprednoj zgradi umjetnom inteligencijom
Title (english)Prediction of windows openness in smart building by artificial intelligence
AuthorMihael Ratkovčić
MentorVinko Lešić (mentor)
Committee memberVinko Lešić (član povjerenstva)
Committee memberFilip Vrbanc (član povjerenstva)
Committee memberMihael Jakšić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2024-07-04, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj projekt istražuje primjenu naprednih tehnologija i strojnog učenja za razvoj inteligentnog sustava koji predviđa status prozora na temelju podataka prikupljenih sa senzora i vanjskih meteoroloških podataka. Korištenjem dvaju modela strojnog učenja, Random Forest i Gradient Boosting, analizirane su njihove performanse u zadatku predviđanja statusa otvorenosti prozora. Projekt uključuje implementaciju API-ja za dohvaćanje vanjskih meteoroloških podataka i uspostavu računalnog oblaka za efikasnu obradu i skladištenje tih podataka. Nakon prikupljanja podataka, razvijeni su i optimizirani modeli strojnog učenja te je provedena temeljita analiza uspješnosti i prilagodba pojedinačnih modela. Testni primjer demonstrira krajnji sustav i njegovu praktičnu primjenu. Rezultati pokazuju da strojno učenje može učinkovito koristiti stvarne podatke za precizna predviđanja. Projekt također naglašava važnost pažljivog odabira i prilagodbe modela prema dostupnim podacima. U budućem radu, sustav se može dodatno unaprijediti proširenjem funkcionalnosti i poboljšanjem točnosti modela, prilagođavajući se različitim scenarijima i potrebama korisnika. Ovaj rad potvrđuje potencijal integracije podataka iz različitih izvora i korištenja naprednih algoritama za strojno učenje, doprinoseći poboljšanju kvalitete života kroz automatizirane i inteligentne odluke.
Abstract (english)
This project explores the usage of advanced technologies and machine learning for the development of intelligent systems that predict window status based on data collected from sensors and external meteorological data. By using two different machine learning methods, Random Forest and Gradient Boosting, their performances for the task of predicting window status were analyzed. This project includes the implementation of an API for retrieving external meteorological data and establishing a cloud computing infrastructure for efficient data processing and storage. After data collection, machine learning models were developed and optimized, followed by thorough performance analysis and adjustment of individual models. In the end, a test example demonstrates the final system and its practical application. The results of this project show that machine learning can effectively use real data for accurate predictions. The project also highlights the importance of careful model selection and adjustments according to the available data. In future work, the system could be further improved by expanding functionalities and enhancing model accuracy, adapting to different scenarios and specific user needs. This project confirms the potential of integrating data from various sources and using advanced machine learning algorithms, contributing to the improvement of the quality of life through automated and intelligent decision-making.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:058218
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2024-10-12 21:59:32