Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/31041

TitleUpdate of data mining models for the prediction of laboratory soil-cement mechanical properties
Author(s)Tinoco, Joaquim Agostinho Barbosa
Correia, A. Gomes
Cortez, Paulo
KeywordsSoft-soils
Cutter soil mixing
Laboratory formulations
Data mining
Neural networks
Support vector machines
Jet grouting
Issue date20-Jul-2014
PublisherIOS Press
Abstract(s)In the past, a novel approach for mechanical properties prediction of Jet Grouting (JG) laboratory formulations was proposed. Such approach is supported in advanced statistics analysis, usually known as data mining, and is able to predict with high accuracy the Unconfined Compressive Strength (UCS) and stiffness of JG laboratory formulations. In this paper, the developed model for UCS prediction is updated using new data collected from a new project involving cutter soil mixing technology. This update increased the model applicability domain, particularly in terms of the water/cement ratio, cement content and cement type, keeping the same high performance in UCS prediction of soil-cement laboratory formulations as the old model.
TypeconferencePaper
URIhttp://hdl.handle.net/1822/31041
ISBN9781614994169
DOI10.3233/978-1-61499-417-6-206
Publisher versionhttp://ebooks.iospress.nl/volume/information-technology-in-geo-engineering-proceedings-of-the-2nd-international-conference-icitg-durham-uk
Peer-Reviewedyes
AccessrestrictedAccess
Appears in Collections:ISISE - Comunicações a Conferências Internacionais

Files in This Item:
File Description SizeFormat 
ASMGE3-0206.pdfFull paper238,87 kBAdobe PDFView/Open    Request a copy!

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis