Show simple item record

dc.contributor.authorSamui, P.
dc.contributor.authorShahin, Mohamed
dc.date.accessioned2017-01-30T14:56:54Z
dc.date.available2017-01-30T14:56:54Z
dc.date.created2015-06-23T20:00:40Z
dc.date.issued2014
dc.identifier.citationSamui, P. and Shahin, M. 2014. Relevance vector machine and multivariate adaptive regression spline for modelling ultimate capacity of pile foundation. Journal of Numerical Methods in Civil Engineering. 1 (1): pp. 37-45.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/42029
dc.description.abstract

This study examines the capability of the Relevance Vector Machine (RVM) and Multivariate Adaptive Regression Spline (MARS) for prediction of ultimate capacity of driven piles and drilled shafts. RVM is a sparse method for training generalized linear models, while MARS technique is basically an adaptive piece-wise regression approach. In this paper, pile capacity prediction models are developed based on data obtained from the literature and comprise in-situ pile loading tests and Cone Penetration Test (CPT) results. Equations are derived from the developed RVM and MARS models, and the prediction results are compared with those obtained from available CPT-based methods. Sensitivity has been carried out to determine the effect of each input parameter. This study confirms that the developed RVM and MARS models predict ultimate capacity of driven piles and drilled shafts reasonably well, and outperform the available methods.

dc.publisherKhaje Nasirodin Toosi University of Technology
dc.subjectPrediction
dc.subjectmultivariate adaptive regression spline
dc.subjectaxial capacity
dc.subjectpile foundations
dc.subjectrelevance vector machine
dc.titleRelevance vector machine and multivariate adaptive regression spline for modelling ultimate capacity of pile foundation
dc.typeJournal Article
dcterms.source.volume1
dcterms.source.number1
dcterms.source.startPage37
dcterms.source.endPage45
dcterms.source.titleJournal of Numerical Methods in Civil Engineering
curtin.departmentDepartment of Civil Engineering
curtin.accessStatusFulltext not available


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record