TY  - CONF
A1  - Babangida, N.M.
A1  - Yusof, K.W.
A1  - Mustafa, M.R.
A1  - Isa, M.H.
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009801596&doi=10.1201%2fb21942-58&partnerID=40&md5=c5eca8de16bcb3975cf0687d3e618e74
EP  - 298
Y1  - 2016///
PB  - CRC Press/Balkema
SN  - 9781138029781
N1  - cited By 0; Conference of 3rd International Conference on Civil, offshore and Environmental Engineering, ICCOEE 2016 ; Conference Date: 15 August 2016 Through 17 August 2016; Conference Code:180169
N2  - Modeling pore-water pressure (PWP) responses to rainfall is an important part of monitoring hydrological behavior of hill slope. Of recent, soft computing techniques had been used to model these responses. Using support vector regression (SVR) these responses can be modeled with very good accuracy. However, selection of appropriate kernel for such modeling is a necessity. Using PWP and rainfall data from an instrumented slope, four kernel function (linear, sigmoid, polynomial and radial basis function) were used to develop four Models to predict PWP. Input features were selected using a wrapper algorithm, and the SVR meta-parameters were calibrated using k-fold cross validation and grid search. The radial basis function (RBF) was found to be the most suitable for modeling PWP responses, due to its competitive results and less complexity in implementation. © 2016 Taylor & Francis Group, London.
ID  - scholars7554
TI  - Comparison of support vector machines kernel functions for pore-water pressure modeling
SP  - 293
KW  - Functions; Offshore oil well production; Pore pressure; Pressure distribution; Rain; Soft computing; Support vector machines; Water
KW  -  K fold cross validations; Meta-parameters; Pore water pressure model; Pore-water pressures; Radial Basis Function(RBF); Radial basis functions; Softcomputing techniques; Support vector regression (SVR)
KW  -  Support vector regression
AV  - none
ER  -