Evolutionary Weighted Ensemble for EEG Signal Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27740%2F14%3A86089795" target="_blank" >RIV/61989100:27740/14:86089795 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-07773-4_20" target="_blank" >http://dx.doi.org/10.1007/978-3-319-07773-4_20</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-07773-4_20" target="_blank" >10.1007/978-3-319-07773-4_20</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evolutionary Weighted Ensemble for EEG Signal Recognition

Popis výsledku v původním jazyce

Recognition of EEG signal is very complex but very important problem. In this paper we focus on simplified classification problem which consists of detection finger movement based on analysis of seven EEG sensors. Signal gathered by each sensor are subsequently classified by respective classification algorithm which is based on data compression and so called LZ-Complexity. To improve the overall accuracy of the system, Evolutionary Weighted Ensemble (EWE) system is proposed. Parameters of the EWE are set in learning procedure which uses tailored for that purpose evolutionary algorithm. To take full advantage of information returned sensor classifiers, setting negative weights are permitted, which significantly elevates overall accuracy. Evaluation of EWE and its comparison against selected classical ensemble algorithm are carried on empirical data consisting of almost 5 hundred samples. The results shows that EWE algorithm exploits knowledge represented by sensor classifiers very effec

Název v anglickém jazyce

Evolutionary Weighted Ensemble for EEG Signal Recognition

Popis výsledku anglicky

Recognition of EEG signal is very complex but very important problem. In this paper we focus on simplified classification problem which consists of detection finger movement based on analysis of seven EEG sensors. Signal gathered by each sensor are subsequently classified by respective classification algorithm which is based on data compression and so called LZ-Complexity. To improve the overall accuracy of the system, Evolutionary Weighted Ensemble (EWE) system is proposed. Parameters of the EWE are set in learning procedure which uses tailored for that purpose evolutionary algorithm. To take full advantage of information returned sensor classifiers, setting negative weights are permitted, which significantly elevates overall accuracy. Evaluation of EWE and its comparison against selected classical ensemble algorithm are carried on empirical data consisting of almost 5 hundred samples. The results shows that EWE algorithm exploits knowledge represented by sensor classifiers very effec

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Advances in Intelligent Systems and Computing. Volume 298

ISBN

978-3-319-07772-7

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

10

Strana od-do

201-210

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Shenzhen

Datum konání akce

13. 6. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—