prikaz prve stranice dokumenta Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom
  Download
PDF 1.22 MB
master's thesis
Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom
2024. urn:nbn:hr:200:108292
Licht, Bruno
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Licht, B. (2024). Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:108292

Licht, Bruno. "Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:108292

Licht, Bruno. "Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:108292

Licht, B. (2024). 'Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 02 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:108292

Licht B. Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2024 [cited 2025 January 02] Available at: https://urn.nsk.hr/urn:nbn:hr:200:108292

B. Licht, "Prilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:200:108292

Please login to the repository to save this object to your list.
Metadata
TitlePrilagodljiva kontrola raznolikosti pomoću genetskog algoritma s dvostrukom populacijom
Title (english)Adaptive diversity control through a dual-population genetic algorithm
AuthorBruno Licht
MentorČaslav Livada (mentor)
Committee memberČaslav Livada (predsjednik povjerenstva)
Committee memberKrešimir Nenadić (član povjerenstva)
Committee memberAlfonzo Baumgartner (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2024-10-08, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Cilj ovog rada je bio analizirati različite pristupe koji se mogu primijeniti u konfiguraciji genetskih algoritama kako bi se postigla kontrola nad raznolikošću gena prilikom potrage za najboljim rješenjem. Za potrebe ovog rada, u Unityu je stvoren virtualni svijet koji podržava dvije populacije i omogućuje im natjecanje za ograničene resurse. U postavkama za simulirani svijet su ponuđene opcije kojima se lako mogu izmijeniti mnogi parametri izvođenja simulacije. Također su dane upute za izmjenu virtualnog svijeta u slučaju potrebe za testiranje različitih scenarija. Testirani su pristupi poput elitizma, uklanjanja sličnih gena, FUSS algoritma i mnogi od njih su pokazali pozitivne rezultate u smislu izbjegavanja preuranjene konvergencije zbog slabe raznolikosti gena. Neuronska mreža je također imala manji utjecaj na raznolikost, a i pokazala se prigodna za donošenje odluka na temelju cijele populacije ako jedinke imaju jasno definirana pravila ponašanja.
Abstract (english)
The aim of this work was to analyze different approaches that can be applied in the configuration of genetic algorithms in order to achieve control over the diversity of genes when searching for the best solution. For the purposes of this work, a virtual world was created in Unity that supports two populations and allows them to compete for limited resources. In the settings for the simulated world, options are provided that can easily change many parameters of the simulation run. Instructions are also given for modifying the virtual world in case of need to test different scenarios. Approaches such as elitism, removal of similar genes, FUSS algorithm have been tested and many of them have shown positive results in terms of avoiding premature convergence due to poor gene diversity. The neural network also had less impact on diversity, and proved to be suitable for making decisions based on the entire population if the individuals have clearly defined rules of behavior.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:108292
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka računarstva (sveučilišni/a magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-10-15 06:45:31