20.500.12556/DKUM-62086 ANALIZA IN PRIMERJAVA PLATFORM ZA PODATKOVNO RUDARJENJE RAPIDMINER IN WEKA ANALYSIS AND COMPARISON OF DATA MINING PLATFORMS RAPIDMINER AND WEKA V pričujočem diplomskem delu sta analizirani in primerjani splošnonamenski platformi za podatkovno rudarjenje RapidMiner in Weka. V uvodnem delu diplomskega dela so razložene osnove strojnega učenja in podatkovnega rudarjenja ter podrobneje definirane metode dela, ki so uporabljene v praktičnem delu. Primerjava je razdeljena na teoretični in eksperimentalni del. V teoretičnem delu so na podlagi definirane metodologije identificirane pomembne lastnosti orodij in primerjane med seboj, v eksperimentalnem delu pa sta primerjani točnost in F-Mera implementacij algoritmov k-najbližjih sosedov, Naključni gozdovi in Naivni Bayes. S pomočjo statističnih testov je bilo ugotovljeno, da se nobena izvedenka algoritma od drugega statistično pomembno ne razlikuje. The following thesis analyses and compares two general-purpose platforms for data mining, RapidMiner and Weka. The introductory part of this diploma thesis describes the basics of machine learning and data mining as well as the specifically defined work methods, which are used in the experimental part. The comparison is divided into the theoretical and the empirical part. In the theoretical part the important characteristics of the tools are identified and compared on the basis of the defined methodology, whereas in the empirical part the accuracy and the F-measure of implementations of the algorithms K Nearest Neighbor, Random Forest and Naive Bayes are compared. Using appropriate statistical tests, it was found that no version of the algorithm significantly differs from another. strojno učenje klasifikacija primerjava RapidMiner Weka machine learning classification comparison RapidMiner Weka true true false A. Miloševič Slovenski jezik Angleški jezik Diplomsko delo/naloga 2016-08-22 17:44:35 2016-09-16 14:13:44 2022-06-28 03:07:47 2019-07-11 12:43:11 2016 0 [Maribor 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.65(043.2) 19991062 URN:SI:UM:DK:JGSVWTSO UN_Milosevic_Aleksej_2016.pdf UN_Milosevic_Aleksej_2016.pdf 1 0744BCFA7DA7EDAE61F60817F550DC51 d0b4e434e78a96747104d993718c6c79e3720d5cbfee767a6500f13e433ebdcb 46c4f435-7c0d-11eb-bb7a-00155d0001ca https://dk.um.si/Dokument.php?lang=slv&id=102109 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0