Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates
This technical note applies hybrid models of neural networks (NN) and genetic algorithms (GA) to cost estimation of residential buildings to predict preliminary cost estimates. Data used in the study are for residential buildings constructed from 1997 to 2000 in Seoul, Korea. These are used in train...
Gespeichert in:
| Veröffentlicht in: | Journal of computing in civil engineering 2005-04, Vol.19 (2), p.208-211 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 211 |
|---|---|
| container_issue | 2 |
| container_start_page | 208 |
| container_title | Journal of computing in civil engineering |
| container_volume | 19 |
| creator | Kim, G. H Seo, D. S Kang, K. I |
| description | This technical note applies hybrid models of neural networks (NN) and genetic algorithms (GA) to cost estimation of residential buildings to predict preliminary cost estimates. Data used in the study are for residential buildings constructed from 1997 to 2000 in Seoul, Korea. These are used in training each model and evaluating its performance. The models applied were Model I, which determines each parameter of a back-propagation network by a trial-and-error process; Model II, which determines each parameter of a back-propagation network by GAs; and Model III, which trains weights of NNs using genetic algorithms. The research revealed that optimizing each parameter of back-propagation networks using GAs is most effective in estimating the preliminary costs of residential buildings. Therefore, GAs may help estimators overcome the problem of the lack of adequate rules for determining the parameters of NNs. |
| doi_str_mv | 10.1061/(ASCE)0887-3801(2005)19:2(208) |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_28561883</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>28561883</sourcerecordid><originalsourceid>FETCH-LOGICAL-a379t-44c6131396615c4a2ba0d0422373ba5f43ea276220d507b357f70787b859caf13</originalsourceid><addsrcrecordid>eNp9kMtOAyEUhonRxFp9BzY2djHKbYAxcdE09ZJ4S9Q1YRimotNBgcb07WVSoztX5198nJ_zATDB6BQjjs9OZk_zxRRJKQoqET4hCJVTXJ2TnOR0B4xwxWhRMil2wegX2wcHMb4hhAgXbAT09aYOroF3vrFdhL6F93YddJdH-vLhPULdN_DK9jY5A2fd0geXXlcRtj7Ax2AbZ5Lrl0Ps3Mr1Omzg3McEFzG5lU42HoK9VnfRHv3MMXi5XDzPr4vbh6ub-ey20FRUqWDMcEwxrTjHpWGa1Bo1iBFCBa112TJqNRGcENSUSNS0FK1AQopalpXRLaZjMNnu_Qj-c21jUisXje063Vu_jorIkmMpaQYvtqAJPsZgW_UR8lfDRmGkBrNKDWbVoEwNytRgVuFKkZxkfn_8U6Sj0V0bdG9c_FvCOSOYscxVWy5jVr35dejz_b8l_3Z8A_WdinM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>28561883</pqid></control><display><type>article</type><title>Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates</title><source>American Society of Civil Engineers:NESLI2:Journals:2014</source><creator>Kim, G. H ; Seo, D. S ; Kang, K. I</creator><creatorcontrib>Kim, G. H ; Seo, D. S ; Kang, K. I</creatorcontrib><description>This technical note applies hybrid models of neural networks (NN) and genetic algorithms (GA) to cost estimation of residential buildings to predict preliminary cost estimates. Data used in the study are for residential buildings constructed from 1997 to 2000 in Seoul, Korea. These are used in training each model and evaluating its performance. The models applied were Model I, which determines each parameter of a back-propagation network by a trial-and-error process; Model II, which determines each parameter of a back-propagation network by GAs; and Model III, which trains weights of NNs using genetic algorithms. The research revealed that optimizing each parameter of back-propagation networks using GAs is most effective in estimating the preliminary costs of residential buildings. Therefore, GAs may help estimators overcome the problem of the lack of adequate rules for determining the parameters of NNs.</description><identifier>ISSN: 0887-3801</identifier><identifier>EISSN: 1943-5487</identifier><identifier>DOI: 10.1061/(ASCE)0887-3801(2005)19:2(208)</identifier><identifier>CODEN: JCCEE5</identifier><language>eng</language><publisher>Reston, VA: American Society of Civil Engineers</publisher><subject>Applied sciences ; Building economics. Cost ; Buildings. Public works ; Computation methods. Tables. Charts ; Exact sciences and technology ; Structural analysis. Stresses ; TECHNICAL NOTES</subject><ispartof>Journal of computing in civil engineering, 2005-04, Vol.19 (2), p.208-211</ispartof><rights>2005 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a379t-44c6131396615c4a2ba0d0422373ba5f43ea276220d507b357f70787b859caf13</citedby><cites>FETCH-LOGICAL-a379t-44c6131396615c4a2ba0d0422373ba5f43ea276220d507b357f70787b859caf13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttp://ascelibrary.org/doi/pdf/10.1061/(ASCE)0887-3801(2005)19:2(208)$$EPDF$$P50$$Gasce$$H</linktopdf><linktohtml>$$Uhttp://ascelibrary.org/doi/abs/10.1061/(ASCE)0887-3801(2005)19:2(208)$$EHTML$$P50$$Gasce$$H</linktohtml><link.rule.ids>314,776,780,27903,27904,75939,75947</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=16642144$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Kim, G. H</creatorcontrib><creatorcontrib>Seo, D. S</creatorcontrib><creatorcontrib>Kang, K. I</creatorcontrib><title>Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates</title><title>Journal of computing in civil engineering</title><description>This technical note applies hybrid models of neural networks (NN) and genetic algorithms (GA) to cost estimation of residential buildings to predict preliminary cost estimates. Data used in the study are for residential buildings constructed from 1997 to 2000 in Seoul, Korea. These are used in training each model and evaluating its performance. The models applied were Model I, which determines each parameter of a back-propagation network by a trial-and-error process; Model II, which determines each parameter of a back-propagation network by GAs; and Model III, which trains weights of NNs using genetic algorithms. The research revealed that optimizing each parameter of back-propagation networks using GAs is most effective in estimating the preliminary costs of residential buildings. Therefore, GAs may help estimators overcome the problem of the lack of adequate rules for determining the parameters of NNs.</description><subject>Applied sciences</subject><subject>Building economics. Cost</subject><subject>Buildings. Public works</subject><subject>Computation methods. Tables. Charts</subject><subject>Exact sciences and technology</subject><subject>Structural analysis. Stresses</subject><subject>TECHNICAL NOTES</subject><issn>0887-3801</issn><issn>1943-5487</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2005</creationdate><recordtype>article</recordtype><recordid>eNp9kMtOAyEUhonRxFp9BzY2djHKbYAxcdE09ZJ4S9Q1YRimotNBgcb07WVSoztX5198nJ_zATDB6BQjjs9OZk_zxRRJKQoqET4hCJVTXJ2TnOR0B4xwxWhRMil2wegX2wcHMb4hhAgXbAT09aYOroF3vrFdhL6F93YddJdH-vLhPULdN_DK9jY5A2fd0geXXlcRtj7Ax2AbZ5Lrl0Ps3Mr1Omzg3McEFzG5lU42HoK9VnfRHv3MMXi5XDzPr4vbh6ub-ey20FRUqWDMcEwxrTjHpWGa1Bo1iBFCBa112TJqNRGcENSUSNS0FK1AQopalpXRLaZjMNnu_Qj-c21jUisXje063Vu_jorIkmMpaQYvtqAJPsZgW_UR8lfDRmGkBrNKDWbVoEwNytRgVuFKkZxkfn_8U6Sj0V0bdG9c_FvCOSOYscxVWy5jVr35dejz_b8l_3Z8A_WdinM</recordid><startdate>20050401</startdate><enddate>20050401</enddate><creator>Kim, G. H</creator><creator>Seo, D. S</creator><creator>Kang, K. I</creator><general>American Society of Civil Engineers</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7TA</scope><scope>8FD</scope><scope>FR3</scope><scope>JG9</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20050401</creationdate><title>Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates</title><author>Kim, G. H ; Seo, D. S ; Kang, K. I</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a379t-44c6131396615c4a2ba0d0422373ba5f43ea276220d507b357f70787b859caf13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Applied sciences</topic><topic>Building economics. Cost</topic><topic>Buildings. Public works</topic><topic>Computation methods. Tables. Charts</topic><topic>Exact sciences and technology</topic><topic>Structural analysis. Stresses</topic><topic>TECHNICAL NOTES</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kim, G. H</creatorcontrib><creatorcontrib>Seo, D. S</creatorcontrib><creatorcontrib>Kang, K. I</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Materials Business File</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Journal of computing in civil engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kim, G. H</au><au>Seo, D. S</au><au>Kang, K. I</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates</atitle><jtitle>Journal of computing in civil engineering</jtitle><date>2005-04-01</date><risdate>2005</risdate><volume>19</volume><issue>2</issue><spage>208</spage><epage>211</epage><pages>208-211</pages><issn>0887-3801</issn><eissn>1943-5487</eissn><coden>JCCEE5</coden><abstract>This technical note applies hybrid models of neural networks (NN) and genetic algorithms (GA) to cost estimation of residential buildings to predict preliminary cost estimates. Data used in the study are for residential buildings constructed from 1997 to 2000 in Seoul, Korea. These are used in training each model and evaluating its performance. The models applied were Model I, which determines each parameter of a back-propagation network by a trial-and-error process; Model II, which determines each parameter of a back-propagation network by GAs; and Model III, which trains weights of NNs using genetic algorithms. The research revealed that optimizing each parameter of back-propagation networks using GAs is most effective in estimating the preliminary costs of residential buildings. Therefore, GAs may help estimators overcome the problem of the lack of adequate rules for determining the parameters of NNs.</abstract><cop>Reston, VA</cop><pub>American Society of Civil Engineers</pub><doi>10.1061/(ASCE)0887-3801(2005)19:2(208)</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0887-3801 |
| ispartof | Journal of computing in civil engineering, 2005-04, Vol.19 (2), p.208-211 |
| issn | 0887-3801 1943-5487 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_28561883 |
| source | American Society of Civil Engineers:NESLI2:Journals:2014 |
| subjects | Applied sciences Building economics. Cost Buildings. Public works Computation methods. Tables. Charts Exact sciences and technology Structural analysis. Stresses TECHNICAL NOTES |
| title | Hybrid Models of Neural Networks and Genetic Algorithms for Predicting Preliminary Cost Estimates |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T06%3A10%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Hybrid%20Models%20of%20Neural%20Networks%20and%20Genetic%20Algorithms%20for%20Predicting%20Preliminary%20Cost%20Estimates&rft.jtitle=Journal%20of%20computing%20in%20civil%20engineering&rft.au=Kim,%20G.%20H&rft.date=2005-04-01&rft.volume=19&rft.issue=2&rft.spage=208&rft.epage=211&rft.pages=208-211&rft.issn=0887-3801&rft.eissn=1943-5487&rft.coden=JCCEE5&rft_id=info:doi/10.1061/(ASCE)0887-3801(2005)19:2(208)&rft_dat=%3Cproquest_cross%3E28561883%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=28561883&rft_id=info:pmid/&rfr_iscdi=true |