An intelligent based-model role to simulate the factor of safe slope by support vector regression
An infrastructure development in landscape and clearing of more vegetated areas have provided huge changes in Malaysia gradually leading to slope instabilities accompanied by enormous environmental effects such as properties and destructions. Thus, prudent practices through vegetation incorporating...
Saved in:
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Published: |
Springer Verlag
2019
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/23523/ https://doi.org/10.1007/s00366-018-0677-4 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | An infrastructure development in landscape and clearing of more vegetated areas have provided huge changes in Malaysia gradually leading to slope instabilities accompanied by enormous environmental effects such as properties and destructions. Thus, prudent practices through vegetation incorporating to use slope stability is an option to the general stabilized technique. Few researches have investigated the effectiveness of vegetative coverings related to slope and soil parameters. The main goal of this study is to provide an intelligent soft computing model to predict the safety factor (FOS) of a slope using support vector regression (SVR). In the other words, SVR has investigated the surface eco-protection techniques for cohesive soil slopes in Guthrie Corridor Expressway stretch through the probabilistic models analysis to highlight the main parameters. The aforementioned analysis has been performed to predict the FOS of a slope, also the estimator’s function has been confirmed by the simulative outcome compared to artificial neural network and genetic programing resulting in a drastic accurate estimation by SVR. Using new analyzing methods like SVR are more purposeful than achieving a starting point by trial and error embedding multiple factors into one in ordinary low-technique software. © 2018, Springer-Verlag London Ltd., part of Springer Nature. |
---|