Algoritmi gručenja v okolju Jamovi in programskem jeziku R

diplomsko delo

Tine Šuster (Author), Sašo Karakatič (Mentor)

Abstract

Gručenje je uporabna tehnika strojnega učenja. Velika količina podatkov, ki so na voljo odpira mnogo možnosti za iskanje skritega znanja. Ti pogoji ponujajo priložnost razvoja odprtokodnih orodij za uporabo strojnega učenja in ga tako približati več uporabnikom. Opisali smo osnove strojnega učenja in podrobneje analizirali nekaj algoritmov gručenja. V programskem jeziku R smo razvili vtičnik za odprtokodno okolje Jamovi. Končni izdelek podpira tri pogosto uporabljane algoritme gručenja in omogoča uporabniko enostavno gručenje nad podatki prav tako pa oceno pridobljenih rezultatov. Uporabniško izkušnjo smo izboljšali tudi z grafičnim prikazom podatkov.

Keywords

gručenje;analiza;strojno učenje;vtičniki;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[T. Šuster]
UDC:	004.85(043.2)
COBISS:	140571907
Views:	154
Downloads:	25
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Clustering algorithms in the Jamovi environment and the R programming language
Secondary abstract:	Clustering is a useful machine learning technique. The large amount of data available opens up many possibilities for finding hidden knowledge. These conditions offer the possibility of developing open source tools for using machine learning and thus bringing it closer to more users. We described the basics of machine learning and analyzed some clustering algorithms in more detail. In the programming language R, we developed a plug-in for the Jamovi open source environment. The final product supports three commonly used clustering algorithms and allows the user to easily analyze the data, aswell as enabling the assessment of the obtained results. We also improved the user experience with graphical display of the data.
Secondary keywords:	clustering;analysis;machine learning;plugin;
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in tehnologije komuniciranja
Pages:	1 spletni vir (1 datoteka PDF (X, 62 f.))
ID:	16450023