Curves and surfaces for computer aided geometric design (3rd ed.): a practical guide
Curves and surfaces for computer aided geometric design (3rd ed.): a practical guide
The nature of statistical learning theory
The nature of statistical learning theory
Cluster Analysis
| Hi-index | 0.00 |
In this paper we present a new algorithm for approximating data that lie on a set of curved paths by using support vector machine (SVM) regression. The algorithm is designed to exploit the structure inherent in the abscissae, which is done by fitting a tensor-product surface to the data. This allows substantial computational savings to be made. In addition, it is assumed that the measurements made along each curved path may be corrupted by different levels or types of noise. SVM regression is ideally suited to cope with this type of problem, and we show how the algorithm can be modified to overcome any difficulties caused by different types of noise in the data.