7-Dimensional Optimization Task: PBO-Nature-Inspired Optimizer Versus 10-Years-Old Differential Evolution Based Optimizer 3rd Generation EPSDE

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F20%3A39916052" target="_blank" >RIV/00216275:25530/20:39916052 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-51971-1_2" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-51971-1_2</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-51971-1_2" target="_blank" >10.1007/978-3-030-51971-1_2</a>

Jazyk výsledku

angličtina

Název v původním jazyce

7-Dimensional Optimization Task: PBO-Nature-Inspired Optimizer Versus 10-Years-Old Differential Evolution Based Optimizer 3rd Generation EPSDE

Popis výsledku v původním jazyce

Origins of the branch of numerical optimizations with use of evolutionary opti-mizers date almost 60 years back. It is the area which does not evolve by big jumps and the advancement sometimes hits stagnation periods. At such stagna-tion times there is a big hungry for the new optimization methods which would fill up the empty space. Many optimizers have appeared in the last decade. These optimizers are more specialized in comparison to optimizers which were pro-posed dozens of years back. The new optimizers are very often derived from old-er optimizers. In this presented paper, a 7-dimensional optimization task is solved which is called persons identification using contour of a human hand. The paper is considered as research and comparative study at the same time. An optimizer called EPSDE is compared to the Polar Bear Optimizer. The EPSDE is a deputy of 3rd generation optimizers derived from algorithm differential evolution. The PBO falls into a group of young optimizers marked as „nature inspired“. The PBO is three times more time-demanding and primarily significantly worse in solving of given task which is very difficult. A comparison of both optimizers was conducted with use of large comparative database.

Název v anglickém jazyce

7-Dimensional Optimization Task: PBO-Nature-Inspired Optimizer Versus 10-Years-Old Differential Evolution Based Optimizer 3rd Generation EPSDE

Popis výsledku anglicky

Origins of the branch of numerical optimizations with use of evolutionary opti-mizers date almost 60 years back. It is the area which does not evolve by big jumps and the advancement sometimes hits stagnation periods. At such stagna-tion times there is a big hungry for the new optimization methods which would fill up the empty space. Many optimizers have appeared in the last decade. These optimizers are more specialized in comparison to optimizers which were pro-posed dozens of years back. The new optimizers are very often derived from old-er optimizers. In this presented paper, a 7-dimensional optimization task is solved which is called persons identification using contour of a human hand. The paper is considered as research and comparative study at the same time. An optimizer called EPSDE is compared to the Polar Bear Optimizer. The EPSDE is a deputy of 3rd generation optimizers derived from algorithm differential evolution. The PBO falls into a group of young optimizers marked as „nature inspired“. The PBO is three times more time-demanding and primarily significantly worse in solving of given task which is very difficult. A comparison of both optimizers was conducted with use of large comparative database.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Intelligence and Bioinspired Computational Methods : Proceedings of the 9th Computer Science On-line Conference 2020, Vol. 2

ISBN

978-3-030-51970-4

ISSN

—

e-ISSN

—

Počet stran výsledku

14

Strana od-do

11-25

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

online

Datum konání akce

23. 4. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—