Приказ основних података о документу

Ensemble of radial basis neural networks with k-means clustering for heating energy consumption prediction

dc.creatorJovanović, Radiša
dc.creatorSretenović, Aleksandra
dc.date.accessioned2022-09-19T18:16:30Z
dc.date.available2022-09-19T18:16:30Z
dc.date.issued2017
dc.identifier.issn1451-2092
dc.identifier.urihttps://machinery.mas.bg.ac.rs/handle/123456789/2660
dc.description.abstractU radu je predložen i prikazan ansambl neuronskih mreža za predviđanje potrošnje toplote univerzitetskog kampusa. Za obučavanje i testiranje modela korišćeni su eksperimentalni podaci. Razmatrano je poboljšanje tačnosti predviđanja primenom k-means metode klasterizacije za generisanje obučavajućih podskupova neuronskih mreža zasnovanih na radijalnim bazisnim funkcijama. Korišćen je različit broj klastera, od 2-5. Izlazi članova ansambla su kombinovani primenom aritmetičkog, težinskog i osrednjavanja metodom medijane. Pokazano je da ansambli neuronskih mreža ostvaruju bolje rezultate predviđanja nego svaka pojedinačna mreža članica ansambla. PR Data used for this paper were gathered during study visit to NTNU, as a part of the collaborative project: Sustainable energy and environment in Western Balkans.sr
dc.description.abstractFor the prediction of heating energy consumption of university campus, neural network ensemble is proposed. Actual measured data are used for training and testing the models. Improvement of the prediction accuracy using k-means clustering for creating subsets used to train individual radial basis function neural networks is examined. Number of clusters is varying from 2 to 5. The outputs of ensemble members are aggregated using simple, weighted and median based averaging. It is shown that ensembles achieve better prediction results than the individual network.en
dc.publisherUniverzitet u Beogradu - Mašinski fakultet, Beograd
dc.relationNorwegian Programme in Higher Education, Research and Development
dc.rightsopenAccess
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceFME Transactions
dc.subjectradial basis neural networksen
dc.subjectheating consumption predictionen
dc.subjectensembleen
dc.titleAnsambl neuronskih mreža sa radijalno bazisnim funkcijama i k-means klasterizacijom za predviđanje potrošnje toplotesr
dc.titleEnsemble of radial basis neural networks with k-means clustering for heating energy consumption predictionen
dc.typearticle
dc.rights.licenseBY
dc.citation.epage57
dc.citation.issue1
dc.citation.other45(1): 51-57
dc.citation.rankM24
dc.citation.spage51
dc.citation.volume45
dc.identifier.doi10.5937/fmet1701051J
dc.identifier.fulltexthttp://machinery.mas.bg.ac.rs/bitstream/id/1383/2657.pdf
dc.identifier.scopus2-s2.0-85011395662
dc.identifier.wos000408082100008
dc.type.versionpublishedVersion


Документи

Thumbnail

Овај документ се појављује у следећим колекцијама

Приказ основних података о документу