Primjena metode prepoznavanja stršećih vrijednosti pomoću diskretne totalne varijacije

undergraduate thesis

• Title (english): Application of the discrete total variation outlier recognizer method
• Author: Josip Došen
• Mentor: Lenka Mihoković (mentor)
• Committee member: Lenka Mihoković (predsjednik povjerenstva)
• Committee member: Tomislav Burić (član povjerenstva)
• Committee member: Mario Krnić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Primijenjena je metoda TVOR na skup podataka zaraženih virusom COVID-19, metoda je provedena na skupu histograma tako da se svakom histogramu izračunala predviđena i prava vrijednost diskretne totalne varijacije te je uzeta razlika između dvije, što je razlika bila veća to je veća vjerojatnost da je navedeni histogram devijantan u odnosu na ostale. Metoda je primijenjena na ulazni skup i izlaz je rezultat metode za svaku državu za koju su postojale dostupne informacije. Rezultati mogu ukazivati na mnoge stvari zbog brojnih poznatih i nepoznatih faktora koji su bili prisutni u svakoj analiziranoj zemlji. Pronađene su i zemlje koje su vrlo devijantne u odnosu na ostale, što može značiti da su u istima brojevi zaraženih bili ili falsificirani ili država nije dobro provodila testiranja ili se virus COVID-19 na specifičan način širio kroz državu. Iako višeznačni, rezultati istraživanja mogu poslužiti u analizi vremena pandemije.

Abstract (english)

Method TVOR was applied on dataset which contains number of people who were infected with virus COVID-19, method was carried out on set of histograms in a way that for every histogram its predicted and real discrete total variations were calculated and
difference between the two was taken as a result, bigger difference meant greater probability that that histogram was deviant compared to others. Method was applied on input dataset and the output was result of the method for each country for which available data existed. Results can indicate a lot of different conclusions because
of many known and unknown factors which were present in each country whose data were analyzed. Some countries had very deviant results in comparison to others, what could mean that in those countries numbers of infected people were either corrupted or state did not conclude testing’s in a good way or that virus COVID-19 was spread through the population on a specific way. Although ambiguous, the results of the research can be useful in the analysis of the time of the pandemic.

• Keywords: TVOR; varijacija; COVID-19; analiza
• Keywords (english): TVOR; variation; COVID-19; analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:785146
• 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: 2023-10-11 08:44:16