What is it about?
In this study, several kernel functions (linear, Radial Basis Function, Polynomial and Multi-Layer Perceptron) were evaluated and their parameters were selected by Grey Wolf Optimizer approach, in order to improve LS-SVM for flashover voltage estimating.
Featured Image
Why is it important?
A number of optimization algorithms have been proposed to select the hyper-parameters of LS-SVM, in order to improve its performance and to provide the lowest error or the highest precision rate. In the same light, this work adopts a new meta-heuristic approach GWO to select not only the regularization parameter and the RBF kernel parameter of LS-SVM but also the kernel parameters of numerous kernels functions.
Perspectives
The hybrid model developed in this article can be spread to other engineering.
Sid Ahmed Bessedik
Department of Electrical Engineering, University Amar Telidji, Algeria
Read the Original
This page is a summary of: Performance of different kernel functions for LS-SVM-Grey Wolf Optimiser to estimate flashover voltage of polluted insulators , IET Science Measurement & Technology, April 2018, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-smt.2017.0486.
You can read the full text:
Contributors
The following have contributed to this page
