prikaz prve stranice dokumenta Kompleksnost skrivenih Markovljevih modela
  Download
PDF 1.86 MB
master's thesis
Kompleksnost skrivenih Markovljevih modela
Zagreb: University of Zagreb, Faculty of Science, 2016. urn:nbn:hr:217:151332
Mišura, Ankica
University of Zagreb
Faculty of Science
Department of Mathematics

Institutional repository: Repository of the Faculty of Science

Cite this document

Mišura, A. (2016). Kompleksnost skrivenih Markovljevih modela (Master's thesis). Zagreb: University of Zagreb, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:217:151332

Mišura, Ankica. "Kompleksnost skrivenih Markovljevih modela." Master's thesis, University of Zagreb, Faculty of Science, 2016. https://urn.nsk.hr/urn:nbn:hr:217:151332

Mišura, Ankica. "Kompleksnost skrivenih Markovljevih modela." Master's thesis, University of Zagreb, Faculty of Science, 2016. https://urn.nsk.hr/urn:nbn:hr:217:151332

Mišura, A. (2016). 'Kompleksnost skrivenih Markovljevih modela', Master's thesis, University of Zagreb, Faculty of Science, accessed 03 July 2024, https://urn.nsk.hr/urn:nbn:hr:217:151332

Mišura A. Kompleksnost skrivenih Markovljevih modela [Master's thesis]. Zagreb: University of Zagreb, Faculty of Science; 2016 [cited 2024 July 03] Available at: https://urn.nsk.hr/urn:nbn:hr:217:151332

A. Mišura, "Kompleksnost skrivenih Markovljevih modela", Master's thesis, University of Zagreb, Faculty of Science, Zagreb, 2016. Available at: https://urn.nsk.hr/urn:nbn:hr:217:151332

Metadata
TitleKompleksnost skrivenih Markovljevih modela
AuthorAnkica Mišura
MentorPavle Goldstein (mentor)
Committee memberPavle Goldstein (predsjednik povjerenstva)
Committee memberMiljenko Huzak (član povjerenstva)
Committee memberMatija Kazalicki (član povjerenstva)
Committee memberMiljenko Marušić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Science
(Department of Mathematics)
Zagreb
Defense date and country2016-09-27, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Abstract
U ovom diplomskom radu smo se bavili skrivenim Markovljevim modelima, statističkim alatom koji je namijenjen modeliranju nizova koje generira neki skriveni proces. Dali smo formalnu definiciju skrivenog Markovljevog modela, opisali neke algoritme za rad sa skrivenim Markovljevim modelima i implementirali ih u programskom jeziku Python. Konstruirali smo primjer skrivenog Markovljeva modela. Proveli smo nekoliko simulacija i pokušali smo naći najbolji model koji bi opisao te podatke. Koristili smo nekoliko statističkih metoda za odabir najboljeg modela: maksimizacija vjerodostojnosti, log-omjer vjerodostojnosti i informacijske kriterije.
Abstract (english)
This thesis is concerned with a statistical model called hidden Markov model (HMM), statistical tool designed for modelling sequences generated by hidden processes. We give a formal definition of the hidden Markov model, describe several algorithms used in their analysis and present their in Python. We also construct example of hidden Markov model. We simulate data and attempt to find the best model for it. We use several statistical methods: likelihood maximization, log-likelihood ratio and information criteria.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:217:151332
Study programmeTitle: Mathematical Statistics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-01-25 11:44:12