Show simple item record

dc.contributor.advisorStanković, Milena
dc.contributor.otherStoimenov, Leonid
dc.contributor.otherStojković, Suzana
dc.contributor.otherStanković, Miomir
dc.contributor.otherMilovanović, Slavoljub
dc.creatorMarković, Ivana P.
dc.date.accessioned2018-07-05T09:38:18Z
dc.date.available2018-07-05T09:38:18Z
dc.date.available2020-07-03T16:02:53Z
dc.date.issued2018-05-03
dc.identifier.urihttp://nardus.mpn.gov.rs/handle/123456789/9591
dc.identifier.urihttp://eteze.ni.ac.rs/application/showtheses?thesesId=5861
dc.identifier.urihttps://fedorani.ni.ac.rs/fedora/get/o:1491/bdef:Content/download
dc.identifier.urihttp://vbs.rs/scripts/cobiss?command=DISPLAY&base=70052&RID=533967510
dc.description.abstractThe aim of the research presented within this doctoral dissertation is to develop a feature selection methodology through integrating domain-specific knowledge by applying mathematical methods of decision-making, to improve the feature selection process and the precision of supervised machine learning methods for predictive modeling of time series. To integrate domain-specific knowledge, a multi-criteria decision making method is used, i.e. an analytical hierarchical process proven to be successful in numerous studies carried out to date. This approach was selected because it allows the selection of a set of factors based on their relevance, even in the case of mutually opposite criteria. In predicting the movement of time series, the possibility of integrating feature relevance into support vector machines to improve their prediction accuracy was studied. The proposed methodology was applied as a feature-selection method for the predictive modelling of movement of financial time series. Unlike existing approaches, where the feature selection method is based on a quantitative analysis of the input values, the proposed methodology carries out a qualitative evaluation of the attributes in relation to the prediction domain and represents a means of integrating a priori knowledge of the prediction domain.en
dc.formatapplication/pdf
dc.languagesr
dc.publisherУниверзитет у Нишу, Електронски факултетsr
dc.rightsopenAccessen
dc.sourceУниверзитет у Нишуsr
dc.subjectizbor atributasr
dc.subjectFeature selectionen
dc.subjectWeighted kernel functionen
dc.subjectPredictive modelingen
dc.subjectTime seriesen
dc.subjecttežinska kernel funkcijasr
dc.subjectprediktivno modelovanjesr
dc.subjectvremenske serijesr
dc.titleIzbor atributa integracijom znanja o domenu primenom metoda odlučivanja kod prediktivnog modelovanja vremenskih serija nadgledanim mašinskim učenjemsr
dc.typedoctoralThesis
dc.rights.licenseBY-NC-ND
dcterms.abstractСтанковић, Милена; Стоименов, Леонид; Стојковић, Сузана; Станковић, Миомир; Миловановић, Славољуб; Марковић, Ивана П.; Избор атрибута интеграцијом знања о домену применом метода одлучивања код предиктивног моделовања временских серија надгледаним машинским учењем; Избор атрибута интеграцијом знања о домену применом метода одлучивања код предиктивног моделовања временских серија надгледаним машинским учењем;
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/52369/Disertacija.pdf
dc.identifier.fulltexthttp://nardus.mpn.gov.rs/bitstream/id/52370/Markovic_Ivana_P.pdf


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record