Experimenty s rojovou inteligencí (swarm intelligence)
Loading...
Date
Authors
ORCID
Advisor
Referee
Mark
A
Journal Title
Journal ISSN
Volume Title
Publisher
Vysoké učení technické v Brně. Fakulta informačních technologií
Abstract
Práce se zabývá rojovou inteligencí jako podoborem umělé inteligence. Stručně popisuje biologické pozadí problematiky a zabývá se také principy hledání cest v mravenčích koloniích. Představena je i oblast kombinatorické optimalizace a detailně jsou definovány úlohy Travelling Salesman Problem a Quadratic Assignment Problem. Hlavní část práce sestává z popisu metod rojové inteligence pro řešení uvedených problémů a zhodnocení experimentů, které byly na těchto metodách provedeny. Konkrétně jde o algoritmy Ant System, Ant Colony System, Hybrid Ant System a Max-Min Ant System. V rámci práce byla také navržena a otestována vlastní metoda Genetic Ant System, která obohacuje základní Ant System mimo jiné o vývoj parametrů jednotek na základě genetických principů. V rámci obou řešených úloh jsou porovnány výsledky popisovaných metod společně s výsledky metod klasické umělé inteligence.
This work deals with the issue of swarm intelligence as a subdiscipline of artificial intelligence. It describes biological background of the dilemma briefly and presents the principles of searching paths in ant colonies as well. There is also adduced combinatorial optimization and two selected tasks are defined in detail: Travelling Salesman Problem and Quadratic Assignment Problem. The main part of this work consists of description of swarm intelligence methods for solving mentioned problems and evaluation of experiments that were made on these methods. There were tested Ant System, Ant Colony System, Hybrid Ant System and Max-Min Ant System algorithm. Within the work there were also designed and tested my own method Genetic Ant System which enriches the basic Ant System i.a. with development of unit parameters based on genetical principles. The results of described methods were compared together with the ones of classical artificial intelligence within the frame of both solved problems.
This work deals with the issue of swarm intelligence as a subdiscipline of artificial intelligence. It describes biological background of the dilemma briefly and presents the principles of searching paths in ant colonies as well. There is also adduced combinatorial optimization and two selected tasks are defined in detail: Travelling Salesman Problem and Quadratic Assignment Problem. The main part of this work consists of description of swarm intelligence methods for solving mentioned problems and evaluation of experiments that were made on these methods. There were tested Ant System, Ant Colony System, Hybrid Ant System and Max-Min Ant System algorithm. Within the work there were also designed and tested my own method Genetic Ant System which enriches the basic Ant System i.a. with development of unit parameters based on genetical principles. The results of described methods were compared together with the ones of classical artificial intelligence within the frame of both solved problems.
Description
Keywords
rojová inteligence, umělá inteligence, mravenčí kolonie, kombinatorická optimalizace, Travelling Salesman Problem, Quadratic Assignment Problem, Ant Colony Optimization, Ant System, Ant Colony System, Max-Min Ant System, Hybrid Ant System, Genetic Ant System, swarm intelligence, artificial intelligence, ant colony, combinatorial optimization, Travelling Salesman Problem, Quadratic Assignment Problem, Ant Colony Optimization, Ant System, Ant Colony System, Max-Min Ant System, Hybrid Ant System, Genetic Ant System
Citation
HULA, T. Experimenty s rojovou inteligencí (swarm intelligence) [online]. Brno: Vysoké učení technické v Brně. Fakulta informačních technologií. 2008.
Document type
Document version
Date of access to the full text
Language of document
cs
Study field
Inteligentní systémy
Comittee
Date of acceptance
2008-06-16
Defence
Result of defence
práce byla úspěšně obhájena
Document licence
Standardní licenční smlouva - přístup k plnému textu bez omezení