Cover Image

Linear kernel support vector machines for modeling pore-water pressure responses

Pore-water pressure responses are vital in many aspects of slope management, design and monitoring. Its measurement however, is difficult, expensive and time consuming. Studies on its predictions are lacking. Support vector machines with linear kernel was used here to predict the responses of pore-w...

Full description

Saved in:
Bibliographic Details
Main Authors: Yusof, K.W., Babangida, N.M., Mustafa, M.R., Isa, M.H.
Format: Article
Published: Taylor's University 2017
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026916080&partnerID=40&md5=292625363e1b6d38bea120e0107fbbba
http://eprints.utp.edu.my/19783/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.19783
record_format eprints
spelling my.utp.eprints.197832018-04-20T07:47:30Z Linear kernel support vector machines for modeling pore-water pressure responses Yusof, K.W. Babangida, N.M. Mustafa, M.R. Isa, M.H. Pore-water pressure responses are vital in many aspects of slope management, design and monitoring. Its measurement however, is difficult, expensive and time consuming. Studies on its predictions are lacking. Support vector machines with linear kernel was used here to predict the responses of pore-water pressure to rainfall. Pore-water pressure response data was collected from slope instrumentation program. Support vector machine meta-parameter calibration and model development was carried out using grid search and k-fold cross validation. The mean square error for the model on scaled test data is 0.0015 and the coefficient of determination is 0.9321. Although pore-water pressure response to rainfall is a complex nonlinear process, the use of linear kernel support vector machine can be employed where high accuracy can be sacrificed for computational ease and time. © School of Engineering, Taylor’s University. Taylor's University 2017 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026916080&partnerID=40&md5=292625363e1b6d38bea120e0107fbbba Yusof, K.W. and Babangida, N.M. and Mustafa, M.R. and Isa, M.H. (2017) Linear kernel support vector machines for modeling pore-water pressure responses. Journal of Engineering Science and Technology, 12 (8). pp. 2202-2212. http://eprints.utp.edu.my/19783/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Pore-water pressure responses are vital in many aspects of slope management, design and monitoring. Its measurement however, is difficult, expensive and time consuming. Studies on its predictions are lacking. Support vector machines with linear kernel was used here to predict the responses of pore-water pressure to rainfall. Pore-water pressure response data was collected from slope instrumentation program. Support vector machine meta-parameter calibration and model development was carried out using grid search and k-fold cross validation. The mean square error for the model on scaled test data is 0.0015 and the coefficient of determination is 0.9321. Although pore-water pressure response to rainfall is a complex nonlinear process, the use of linear kernel support vector machine can be employed where high accuracy can be sacrificed for computational ease and time. © School of Engineering, Taylor’s University.
format Article
author Yusof, K.W.
Babangida, N.M.
Mustafa, M.R.
Isa, M.H.
spellingShingle Yusof, K.W.
Babangida, N.M.
Mustafa, M.R.
Isa, M.H.
Linear kernel support vector machines for modeling pore-water pressure responses
author_facet Yusof, K.W.
Babangida, N.M.
Mustafa, M.R.
Isa, M.H.
author_sort Yusof, K.W.
title Linear kernel support vector machines for modeling pore-water pressure responses
title_short Linear kernel support vector machines for modeling pore-water pressure responses
title_full Linear kernel support vector machines for modeling pore-water pressure responses
title_fullStr Linear kernel support vector machines for modeling pore-water pressure responses
title_full_unstemmed Linear kernel support vector machines for modeling pore-water pressure responses
title_sort linear kernel support vector machines for modeling pore-water pressure responses
publisher Taylor's University
publishDate 2017
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026916080&partnerID=40&md5=292625363e1b6d38bea120e0107fbbba
http://eprints.utp.edu.my/19783/
_version_ 1738656118825025536
score 13.211869

Similar Items