ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Visualization of genetic algorithms in three-dimensional space

Sandi Gec (2011) Visualization of genetic algorithms in three-dimensional space. EngD thesis.

[img] PDF
Download (1528Kb)


    The goal of this work is an application for visualization of genetic algorithms on a simple problem in two-dimensional and three-dimensional space. The purpose is to improve comprehension of genetic algorithms. We present the history of genetic algorithms, the methodology with detailed description of all phases of the algorithm and its applications. We describe a problem that we are solving with genetic algorithm. We visualize the solving process, describe the work of graphical user interface and parameters of the algorithm. We describe the role of the genetic algorithm in the application and the role of Bezier curves. We also represent the most important technologies and tools that were used in the developement of the application: Java programming language, Java 3D API library, IntelliJ Idea integrated development envioronment, JFormDesigner tools for making of the graphical user interface, the tools for making and managing the software project Apache Maven and the tools for controlling source code TortoiseSVN. We describe the whole implementation of the problem step by step by making a graphic user interface, Step by step we describe the implementation. We describe the implementation of java library Timing Framework, an architecture of java 3D animation in application and implementation of Maven tool, used for creating the application. In the last chapter we present some interesting solutions and the behavior of the algorithm when solving the problem in two dimensional and three-dimensional space. In conclusion we suggest some ideas for further improvements.

    Item Type: Thesis (EngD thesis)
    Keywords: genetic algorithm, visualization, learning tool, Bezier curves
    Number of Pages: 48
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Marko Robnik Šikonja276Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=00008359508)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 1339
    Date Deposited: 19 Apr 2011 10:07
    Last Modified: 13 Aug 2011 00:39
    URI: http://eprints.fri.uni-lj.si/id/eprint/1339

    Actions (login required)

    View Item