magistrsko delo
Tadej Jerovšek (Author), Matej Črepinšek (Mentor)

Abstract

V tem magistrskem delu se ukvarjamo z vizualizacijo procesov evolucijskih algoritmov in interpretacijo le-teh. Najpogosteje uporabljene metode za primerjavo evolucijskih algoritmov imajo težave že pri oceni algoritmov, samega delovanja algoritmov pa ne upoštevajo. Najprej smo podrobneje pogledali razvoj statističnih metod, kaj nudijo in kje kažejo pomanjkljivosti. Pod drobnogled smo vzeli enokriterijsko in večkriterijsko optimizacijo in jo z uporabo metod vizualizacije informacij predstavili ter interpretirali prednosti in slabosti posameznih algoritmov in problemov, pri čemer smo za temelj uporabili sistem EARS.

Keywords

evolucijski algoritmi;večkriterijska optimizacija;vizualizacija informacij;primerjava evolucijskih algoritmov;Pareto dominiranost;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: T. Jerovšek
UDC: 004.421.2:519.863(043.2)
COBISS: 20124694 Link will open in a new window
Views: 1056
Downloads: 120
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: VISUALIZATION OF EVOLUTIONARY COMPUTATION PROCESSES
Secondary abstract: In this thesis we deal with the visualization of evolutionary processes and its interpretation. Commonly used methods for comparison of evolutionary algorithms have difficulties with rating algorithms, while how they actually work is never taken into account. First we take a closer look at the benefits and shortcomings of statistical methods. We also take a detailed look of single-criteria and multi-criteria optimization and with the use of information visualization methods present advantages and weaknesses of individual algorithms and problems, for which we used the system EARS.
Secondary keywords: evolutionary algorithms;multri-criteria optimization;information visualization;evolutionary algorithm comparison;Pareto dominance;
URN: URN:SI:UM:
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: XI, 84 str.
ID: 9166683