Control point selection for dimensionality reduction by radial basis function
<p>This research deals with dimensionality reduction technique which is based on radial basis function (RBF) theory. The technique uses RBF for mapping multidimensional data points into a low-dimensional space by interpolating the previously calculated position of so-called control points. Thi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Klaipėda University
2016-02-01
|
| Series: | Computational Science and Techniques |
| Online Access: | http://journals.ku.lt/index.php/CST/article/view/1095 |
| Summary: | <p>This research deals with dimensionality reduction technique which is based on radial basis function (RBF) theory. The technique uses RBF for mapping multidimensional data points into a low-dimensional space by interpolating the previously calculated position of so-called control points. This paper analyses various ways of selection of control points (<em>regularized</em> <em>orthogonal least squares</em> method, <em>random</em> and <em>stratified</em> selections). The experiments have been carried out with 8 real and artificial data sets. Positions of the control points in a low-dimensional space are found by principal component analysis. We demonstrate that <em>random</em> and <em>stratified</em> selections of control points are efficient and acceptable in terms of balance between projection error (<em>stress</em>) and time-consumption.</p><p>DOI: 10.15181/csat.v4i1.1095</p> |
|---|---|
| ISSN: | 2029-9966 |