prikaz prve stranice dokumenta Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari
No public access
master's thesis
Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:659355
Relja, Zvonimir
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Relja, Z. (2018). Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:659355

Relja, Zvonimir. "Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:659355

Relja, Zvonimir. "Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:659355

Relja, Z. (2018). 'Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:659355

Relja Z. Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 December 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:659355

Z. Relja, "Primjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:659355

Metadata
TitlePrimjena tehnika dubokog učenja u okruženju automatizacije doma u sustavima interneta stvari
Title (english)Deep Learning Applications in IoT Environments for Home Automation
AuthorZvonimir Relja
MentorJosip Knezović (mentor)
Committee memberJosip Knezović (predsjednik povjerenstva)
Committee memberIvana Bosnić (član povjerenstva)
Committee memberIgor Čavrak (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom projektu, tehnologija dubokog učenja koristi se za stvaranje specifičnog okruženja za inteligentni kućni sustav koji otkriva i prepoznava kretanje na ulaznim vratima i vanjskoj balkonskoj ogradi. Kako bi se uspješno ispunili svi zahtjevi projekta, koriste se dva ESP32 mikrokontrolera, dva detektora pokreta, dvije kamere, jedan Bluetooth zvučnik i stroj s najmanje 1000 megabajta radne memorije. Uspostavljeni sustav treba pozdraviti poznatu osobu na ulaznim vratima, upozoriti vlasnika kuće na moguću prijetnju ili samo otjerati pticu s vanjske ograde na balkonu. Korištena su razna softverska rješenja i metode dubokog učenja; protokoli HTTP i MQTT, prepoznavanje lica i metode otkrivanja objekata, openHAB sustav, Telegram aplikacija, Django softver i razne Python knjižnice.
Abstract (english)
In this project, deep learning technology is used to create a specific home IoT environment that would detect and identify the movement at the front door and at the outdoor balcony fence. To successfully meet all the claims of the project, two ESP32 microcontrollers, two motion detectors, two cameras, one Bluetooth speaker, and a machine with at least 1000 megabytes of RAM are used. Established IoT system needs to greet a familiar person at the front door, warn a homeowner of a possible threat, or just repeal a bird from the outdoor balcony fence. Various software solutions and deep learning methods were used; protocols HTTP and MQTT, face recognition and object detection methods, openHAB architecture, Telegram application, Django software, and various Python libraries.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:659355
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-14 00:25:24