Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/4099
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Mučenski, Vladimir | en |
dc.contributor.author | Trivunić, Milan | en |
dc.contributor.author | Ćirović, Goran | en |
dc.contributor.author | Peško, Igor | en |
dc.contributor.author | Dražić, Jasmina | en |
dc.date.accessioned | 2019-09-23T10:32:01Z | - |
dc.date.available | 2019-09-23T10:32:01Z | - |
dc.date.issued | 2013-01-01 | en |
dc.identifier.issn | 17858860 | en |
dc.identifier.uri | https://open.uns.ac.rs/handle/123456789/4099 | - |
dc.description.abstract | © 2013, Budapest Tech Polytechnical Institution. All rights reserved. In recent years, we are witnessing a greater tendency towards the use of existing construction waste, in order to reduce the amount of material being disposed of on the one hand, and to limit the exploitation of natural resources necessary for the production of construction materials on the other hand. This paper provides an outline of a process for predicting the recyclable amount of concrete and reinforcement built in structures of residential buildings based on artificial neural networks (ANN). The following analyses are included in the process: an analysis of the optimal network structure, analysis of the effect of training algorithms and a network sensitivity analysis. While analyzing these, networks with one and two hidden layers trained with 5 algorithms (Gradient descent with adaptive lr backpropagation, Levenberg-Marquardt backpropagation, quasi-Newton backpropagation, Bayesian regularization and Powell-Beale conjugate gradient backpropagation) for neural network training were observed. The research was carried out with the purpose of observing ANN that will quickly and with adequate precision provide information regarding the amounts of concrete and reinforcement that can be recycled. | en |
dc.relation.ispartof | Acta Polytechnica Hungarica | en |
dc.title | Estimation of recycling capacity of multi-storey building structures using artificial neural networks | en |
dc.type | Journal/Magazine Article | en |
dc.identifier.doi | 10.12700/APH.10.04.2013.4.11 | en |
dc.identifier.scopus | 2-s2.0-85020991797 | en |
dc.identifier.url | https://api.elsevier.com/content/abstract/scopus_id/85020991797 | en |
dc.relation.lastpage | 192 | en |
dc.relation.firstpage | 175 | en |
dc.relation.issue | 4 | en |
dc.relation.volume | 10 | en |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
crisitem.author.dept | Fakultet tehničkih nauka, Departman za građevinarstvo i geodeziju | - |
crisitem.author.dept | Fakultet tehničkih nauka, Departman za građevinarstvo i geodeziju | - |
crisitem.author.dept | Fakultet tehničkih nauka, Departman za građevinarstvo i geodeziju | - |
crisitem.author.dept | Fakultet tehničkih nauka, Departman za građevinarstvo i geodeziju | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
Appears in Collections: | FTN Publikacije/Publications |
SCOPUSTM
Citations
5
checked on May 3, 2024
Page view(s)
30
Last Week
12
12
Last month
0
0
checked on May 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.