Please use this identifier to cite or link to this item: https://rfos.fon.bg.ac.rs/handle/123456789/1820
Full metadata record
DC FieldValueLanguage
dc.creatorRakić, Ivan
dc.creatorMilošević, Željana
dc.creatorAničić, Nenad
dc.creatorBabarogić, Slađan
dc.date.accessioned2023-05-12T11:15:47Z-
dc.date.available2023-05-12T11:15:47Z-
dc.date.issued2018
dc.identifier.issn1451-4397
dc.identifier.urihttps://rfos.fon.bg.ac.rs/handle/123456789/1820-
dc.description.abstractU ovom radu je opisan način na koji se velike količine podataka mogu obraditi u Oracle bazi podataka korišćenjem različitih algoritama i funkcija. Nakon što su algoritmi istrenirani, performanse njihove primene na novim setovima podataka se mogu izmeriti i analizirati. Fokus ovog rada je na poređenju specifičnih algoritama kako bi mogao da se donese zaključak o tome koji od njih daje pouzdanije rezultate prilikom obrade podataka. Kako bi se osigurali da je najefikasniji algoritam izabran, Oracle analitičke funkcije se mogu koristiti za pripremu podataka pre treniranja algoritama, kao i za obradu rezultata dobijenih nakon primene algoritama. Hadoop razvojni okvir i Hive, kao njegov sastavni deo, su jako često korišćeni za poboljšani pristup podacima koje bi trebalo analizirati i obraditi.sr
dc.description.abstractIn this paper we have described the way of processing a large amount of data in Oracle Database using different algorithms and functions. After training Data Mining algorithms, their performance on new datasets can be measured and examined. We have paid attention on the comparison of specific algorithms so that we can make a decision which of them gives more reliable data processing results. To make sure that more efficient algorithm is chosen, Oracle analytic functions can be used for data preparation before using the algorithms and for analysing the results obtained after the execution of the algorithms. Hadoop framework and Hive, as part of it, have been used to improve access to data being processed.en
dc.publisherUniverzitet u Beogradu - Fakultet organizacionih nauka, Beograd
dc.rightsopenAccess
dc.sourceInfo M
dc.subjectOraclesr
dc.subjectklasterizacijasr
dc.subjectklasifikacijasr
dc.subjectHadoopsr
dc.subjectData Miningsr
dc.subjectanalitičke funkcijesr
dc.subjectOracleen
dc.subjectHadoopen
dc.subjectData Miningen
dc.subjectclusteringen
dc.subjectclassificationen
dc.subjectanalytic functionsen
dc.titlePristup otkrivanju zakonitosti u podacima korišćenjem Oracle Data Miner-a i analitičkih funkcijasr
dc.titleData mining approach using Oracle Data Miner and analytical functionsen
dc.typearticle
dc.rights.licenseARR
dc.citation.epage43
dc.citation.issue66
dc.citation.other17(66): 37-43
dc.citation.rankM53
dc.citation.spage37
dc.citation.volume17
dc.identifier.rcubconv_760
dc.type.versionpublishedVersion
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.grantfulltextnone-
item.openairetypearticle-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
Appears in Collections:Radovi istraživača / Researchers’ publications
Show simple item record

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.