Web-aplikacija za studentske domove temeljena na naprednim dvodimenzionalnim kartama

master's thesis

• Title (english): Web application for student housing based on advanced two-dimensional maps
• Author: Bruno Šegvić
• Mentor: Ivica Botički (mentor)
• Committee member: Ivica Botički (predsjednik povjerenstva)
• Committee member: Mario Brčić (član povjerenstva)
• Committee member: Tomislav Jagušt (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-02-20, Croatia

Abstract

Specifičnosti i različitosti studentskih domova u Republici Hrvatskoj čine pronalazak sveobuhvatnih informacija o studentskim domovima u različitim gradovima kompliciranim, a s obzirom na sve veću popularnost i potrebu za smještajem u studentskim domovima, napravljena je web aplikacija koja pruža sve potrebne informacije o domovima unutar Republike Hrvatske.

Razvijena aplikacija sadrži vizualni prikaz svakog studentskog doma unutar Republike Hrvatske s opisom, adresom, kapacitetom i detaljnim informacijama o svakom paviljonu, uključujući kategoriju, broj i opis te koristi prepoznavanje objekta (engl. Object detection) pri unosu slika. Sama aplikacija se sastoji od baze podataka, poslužitelja i korisničke aplikacije. Pri izradi aplikacije korištene su sljedeće tehnike: TensorFlow, Vue3, Django, PostgreSQL i Konva.js. Aplikaciji se može pristupiti s dva gledišta - kao administrator koji ima mogućnost izmjene podataka ili kao korisnik koji se u sustav može prijaviti s jedinstvenim korisničkim podacima i lozinkom, ali može i ostati anoniman.

S obzirom na to da je cilj aplikacije ubrzati i pojednostaviti proces pretraživanja i odabira studentskih domova u Republici Hrvatskoj, a imajući na umu da je korišteno strojno učenje s gotovo neograničenim mogućnostima ako sadrži dovoljno veliki skup podataka za treniranje, ova aplikacija ima potencijal primjene širi od područja Republike Hrvatske.

Abstract (english)

The specificities and differences of student dormitories in Croatia make finding comprehensive information about dormitories in different cities complicated. Considering the increasing popularity and need for accommodation in student dormitories, a web application has been developed to provide all necessary information about dormitories within Croatia.
The developed application includes a visual representation of each student dormitory within Croatia with descriptions, addresses, capacities, and detailed information about each pavilion, including category, number, and description, utilizing object detection when uploading images. The application itself consists of a database, server, and user application. The following techniques were used in the development of the application: TensorFlow, Vue3, Django, PostgreSQL, and Konva.js. The application can be accessed from three different user roles - as an administrator with the ability to modify data, as a user who can log into the system with unique user data and password or as an anonymous user.
Given that the goal of the application is to expedite and simplify the process of searching and selecting student dormitories in Croatia, and considering that machine learning used in the development process has almost unlimited possibilities if it contains a sufficiently large training dataset, this application has the potential for broader application beyond the territory of Croatia.

• Keywords: Web aplikacija; strojno učenje; studentski domovi; detekcija objekata
• Keywords (english): Web application; machine learning; student dorms; object detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:996208
• 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: 2024-03-28 07:54:36