Primerjava računskih modelov za napovedovanje širjenja bolezni

diplomsko delo

Rok Bosil (Author), Jure Demšar (Mentor)

Abstract

Konec leta 2019 se je na Kitajskem pojavil nov virus. Virus so poimenovali SARS-CoV-2 (angl. severe acute respiratory syndrome coronavirus 2) in bolezen, ki jo ta povzroča COVID-19. Znaki bolezni so vročina, slabo počutje, utrujenost, bolezen se lahko razvije v pljučnico in vodi celo v smrt. Zaradi hitrega širjenja virusa, je bil COVID-19 razglašen kot pandemija. Cilj diplomske naloge je primerjava modelov, ki napovedujejo širjenje virusa. Modeli so bili zgrajeni na podatkih pridobljeni iz univerze Johns Hopkins. Za modeliranje smo uporabili linearno regresijo, nelinearno regresijo z logistično funkcijo in model SIR. Glede na dobljene rezultate smo ugotovili, da sta najboljša modela linearna regresija, kjer smo napovedovali samo s podatki prejšnjega tedna in nelinearna regresija z logistično funkcijo.

Keywords

COVID-19;napovedovanje;regresija;model SIR;računalništvo;računalništvo in informatika;računalništvo in matematika;interdisciplinarni študij;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2020
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[R. Bosil]
UDC:	004.8:578.834(043.2)
COBISS:	28534531
Views:	937
Downloads:	174
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Comparison of computational models for predicting disease spread
Secondary abstract:	At the end of 2019 a new virus appeared in China. The virus was named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the disease it causes was named COVID-19. The symptoms of SARS-Cov-2 can range from fever, nauseousness, fatigue to pneumonia and even death. Because the virus has spread extremely rapidly, COVID-19 was proclaimed as a pandemic. The goal of this bachelor's thesis is to compare models that predict the spread of the virus. Our models were built on data provided by Johns Hopkins University and our chosen models were linear regression, nonlinear regression with a logistic function and a SIR model. According to the results the best models seemed to be the linear regression, where the train set was composed from data from the previous week and the nonlinear regression with a logistic function.
Secondary keywords:	COVID-19;prediction;regression;SIR model;computer science;computer and information science;computer science and mathematics;interdisciplinary studies;diploma;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000407
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	39 str.
ID:	12027629