Tehnike dubokog učenja primjenjene kod analize prijetnji od korona virusa

undergraduate thesis

• Title (english): Deep learning techniques applied in coronavirus threat analysis
• Author: Martin Vugić
• Mentor: Tomislav Stipančić (mentor)
• Committee member: Zoran Kunica (predsjednik povjerenstva)
• Committee member: Danko Brezak (član povjerenstva)
• Committee member: Tomislav Stipančić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2020-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering; Precision Mechanical Engineering

Abstract

Kako tehnologija napreduje, a globalna populacija raste, raste i količina podataka i informacija koje svakodnevno stvaramo. Njihovo sortiranje, skupljanje i analiziranje može biti poprilično težak i mukotrpan zadatak. Jedna od najzastupljenijih i najnovijih grana strojnog učenja, duboko učenje (deep learning) upravo se bavi tom problematikom. Duboko učenje se temelji na predstavljanju podataka složenim algoritmima na visokom stupnju apstrakcije do kojih se dolazi slijedom stečenih nelinearnih transformacija. Metode dubokog učenja svoju primjenu pronalaze u važnim područjima kao što su: umjetna inteligencija, obrade prirodnog jezika, u bioinformatici i sl., no u okviru ovog rada, koristit ćemo je u analiziranju i predviđanju trendova bolesti zastupljenom korona virusom ili skraćeno COVID-19, uz stečene podatke i statistike u programskom jeziku Python.

Abstract (english)

As technology advances and the world’s population grows, so does the amount of data we create every day. Collecting, sorting and analyzing them can be quite a difficult and demanding task. One of the most common and newest branches of machine learning, deep learning, deals with this kind of issues. Deep learning is based on the presentation of complex data algorithms at a high degree of abstraction which are given by learned nonlinear transformations. Deep learning methods find their application in important areas such as artificial intelligence, natural language processing, bioinformatics, etc., but in this paper, we will use it to analyze and predict trends with acquired data and statistics for disease aquired by corona virus, or shortened COVID-19 in the Python programming language.

• Keywords: Python; duboko učenje: COVID-19; predviđanje; vremenske serije
• Keywords (english): Python; deep learning; COVID-19; forecasting; time series
• Language: croatian
• URN:NBN: urn:nbn:hr:235:072803
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-09-24 11:44:23