Selection Strategies in Evolution Algorithms and Biased Selection with Incest Control
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24210%2F20%3A00007862" target="_blank" >RIV/46747885:24210/20:00007862 - isvavai.cz</a>
Result on the web
<a href="https://mme2020.mendelu.cz/wcd/w-rek-mme/mme2020_conference_proceedings_final_final.pdf" target="_blank" >https://mme2020.mendelu.cz/wcd/w-rek-mme/mme2020_conference_proceedings_final_final.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Selection Strategies in Evolution Algorithms and Biased Selection with Incest Control
Original language description
Evolution algorithms are suitable to solve the large field of NP problems. The main difficulty of applying an evolutionary algorithm is to determine an appropriate set of parameter values of evolution operators. One of the most difficult operators to set is the selection of appropriate parents to be reproduced into new solutions. This parameter influences not only the quality of future solutions directly by parent chromosome, but also indirectly by keeping suitable diversity of the whole population. The main motivation of this article is to discuss the ability to prevent premature convergence of selection procedures to make the base for further adaptive scheme to select parents. The presented research is then focused on suggesting a new mechanism of incest control in selection strategies schemes by considering the relationship between selected parents. The new incest control mechanism in biased selection is introduced and experimentally compared with well-known selections. The control mechanism showed promising results in both premature convergence and the objective function.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10101 - Pure mathematics
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
38th International Conference on Mathematical Methods in Economics 2020
ISBN
978-80-7509-734-7
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
266-271
Publisher name
—
Place of publication
Brno
Event location
Brno
Event date
Jan 1, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000668460800041