Inteligentni uređaj za neinvazivnu detekciju otvorenosti prozora i savjetovanje korisnika

undergraduate thesis

• Title (english): Intelligent device for a non-invasive detection of window opening and end-user advising
• Author: Ante Perković
• Mentor: Mario Vašak (mentor)
• Committee member: Mario Vašak (član povjerenstva)
• Committee member: Danko Marušić (član povjerenstva)
• Committee member: Hrvoje Novak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-08-29, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U svijetu koji se sve više bavi zelenom tranzicijom u svrhu sprječavanja klimatskih promjena, veliki fokus se stavlja na štednju energije. Znamo da se značajan postotak energije troši na hlađenje i grijanje prostorija u kojima boravimo i nužno je minimizirati nepotrebne troškove gdje je to moguće kako bismo smanjili opterećenje na infrastrukturu, a i okoliš. U ovom radu proučavamo pristupačan način uštede energije za postojeće građevine, pomoću pametnog termostata. Koristeći se strojnim učenjem i raznim senzorima pokušavamo neinvazivno predvidjeti stanje otvorenosti prozora kako bismo mogli upozoriti korisnika ukoliko je klima upaljena da zatvori prozor ili ugasi klimu. Model se naposlijetku pokazao neuspješnim ali daje puno korisnih informacija za daljnji razvitak.

Abstract (english)

In a world that is increasingly concerned with the green transition to prevent climate change, great emphasis is being placed on saving energy. We know that a significant percentage of energy is spent on cooling and heating the rooms in which we reside and it is necessary to minimize unnecessary costs where possible to reduce the burden on infrastructure and the environment. In this paper, we study an affordable way to save energy for existing buildings, using a smart thermostat. Using machine learning and various sensors, we try to non-invasively predict the state of window openness so that we can warn the user if the air conditioning is on to close the window or turn off the air conditioning. The model eventually proved unsuccessful but provides a lot of useful information for further development.

• Keywords: Pametni termostat; Klimatizacija; Raspberry Pi; Senzori; Strojno učenje; Energija; Klimatske promjene
• Keywords (english): Smart thermostat; A/C; Raspberry Pi; Sensors; Machine learning; Energy; Climate change
• Language: croatian
• URN:NBN: urn:nbn:hr:168:422478
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-15 11:01:53