GPA-ES Algorithm Modification for Large Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F19%3A39915138" target="_blank" >RIV/00216275:25530/19:39915138 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-030-30329-7_9" target="_blank" >http://dx.doi.org/10.1007/978-3-030-30329-7_9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-30329-7_9" target="_blank" >10.1007/978-3-030-30329-7_9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

GPA-ES Algorithm Modification for Large Data

Popis výsledku v původním jazyce

This paper discusses improvement of Genetic Programming Algorithm to large data sets with respect to future extension to big data applications. On the beginning it summarizes requirements on evolutionary system to be applicable in the area of big data and ways of their satisfaction. Then GPAs and especially their improvements by solution constant optimization (so called hierarchical and hybrid genetic programming algorithms) are discussed in this paper. After a discussion of few experiment results of introduced novel evaluation scheme approach with floating data window is presented. Novel evaluation scheme applies floating data window to fitness function evaluation. After one evaluation step of GPA including tuning of parameters (solution constants) by embedded Evolutionary Strategy algorithm data window moves to new position. Presented results demonstrate that this strategy can be faster and more efficient than evolution of whole training data set in each evolutionary step of GPA algorithm. This modification can be starting point of future applications of GPA in the field of large and big data analytic.

Název v anglickém jazyce

GPA-ES Algorithm Modification for Large Data

Popis výsledku anglicky

This paper discusses improvement of Genetic Programming Algorithm to large data sets with respect to future extension to big data applications. On the beginning it summarizes requirements on evolutionary system to be applicable in the area of big data and ways of their satisfaction. Then GPAs and especially their improvements by solution constant optimization (so called hierarchical and hybrid genetic programming algorithms) are discussed in this paper. After a discussion of few experiment results of introduced novel evaluation scheme approach with floating data window is presented. Novel evaluation scheme applies floating data window to fitness function evaluation. After one evaluation step of GPA including tuning of parameters (solution constants) by embedded Evolutionary Strategy algorithm data window moves to new position. Presented results demonstrate that this strategy can be faster and more efficient than evolution of whole training data set in each evolutionary step of GPA algorithm. This modification can be starting point of future applications of GPA in the field of large and big data analytic.

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

<a href="/cs/project/EF17_049%2F0008394" target="_blank" >EF17_049/0008394: Spolupráce Univerzity Pardubice a aplikační sféry v aplikačně orientovaném výzkumu lokačních, detekčních a simulačních systémů pro dopravní a přepravní procesy (PosiTrans)</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Intelligent systems applications in software engineering : proceedings of 3rd computational methods in systems and software 2019, Vol. 1

ISBN

978-3-030-30328-0

ISSN

2194-5357

e-ISSN

2194-5365

Počet stran výsledku

9

Strana od-do

98-106

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Cham

Místo konání akce

Zlín

Datum konání akce

10. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—