Sensitivity Based Feature Selection for Recurrent Neural Network Applied to Forecasting of Heating Gas Consumptin

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00218399" target="_blank" >RIV/68407700:21230/14:00218399 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/chapter/10.1007%2F978-3-319-07995-0_26#page-1" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-319-07995-0_26#page-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-07995-0_26" target="_blank" >10.1007/978-3-319-07995-0_26</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Sensitivity Based Feature Selection for Recurrent Neural Network Applied to Forecasting of Heating Gas Consumptin

Popis výsledku v původním jazyce

The paper demonstrates the importance of feature selection for recurrent neural network applied to problem of one hour ahead forecasting of gas consumption for office building heating. Although the accuracy of the forecasting is similar for both the feed-forward and the recurrent network, the removal of features leads to accuracy reduction much earlier for the feed-forward network. The recurrent network can perform well even with 50% of features. This brings significant benefits in scenarios, where theneural network is used as a blackbox model of building consumption, which is called by an optimizer that minimizes the consumption. The reduction of input dimensionality leads to reduction of costs related to measurement equipment, but also costs relatedto data transfer.

Název v anglickém jazyce

Sensitivity Based Feature Selection for Recurrent Neural Network Applied to Forecasting of Heating Gas Consumptin

Popis výsledku anglicky

The paper demonstrates the importance of feature selection for recurrent neural network applied to problem of one hour ahead forecasting of gas consumption for office building heating. Although the accuracy of the forecasting is similar for both the feed-forward and the recurrent network, the removal of features leads to accuracy reduction much earlier for the feed-forward network. The recurrent network can perform well even with 50% of features. This brings significant benefits in scenarios, where theneural network is used as a blackbox model of building consumption, which is called by an optimizer that minimizes the consumption. The reduction of input dimensionality leads to reduction of costs related to measurement equipment, but also costs relatedto data transfer.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/GP13-21696P" target="_blank" >GP13-21696P: Selekce příznaků pro modely vícedimenzionálních časových řad uvažující časový kontext</a><br>

Návaznosti

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

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Joint Conference SOCO?14-CISIS?14-ICEUTE?14

ISBN

978-3-319-07994-3

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

10

Strana od-do

259-268

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Bilbao

Datum konání akce

25. 6. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000343754200026