Share Email Print
cover

Proceedings Paper

Structural optimization of least-squares support vector classifier based on virtual leave-one-out residuals.
Author(s): Stanislaw Jankowski; Zbigniew Szymański
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The paper includes description of a novel method of the structural optimization of least squares support vector classifier. The virtual leave-one-out residuals are applied as the criterion for selection of the most influential data. The analytic form of the solution enables to obtain a high gain of the computational cost. The presented method eliminates the drawback of the LS-SVM classifiers - lack of sparseness in the solution. The quality of the method was tested on the artificial data sets - two moons problem and Ripley data set.

Paper Details

Date Published: 5 August 2009
PDF: 6 pages
Proc. SPIE 7502, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2009, 75021O (5 August 2009); doi: 10.1117/12.839616
Show Author Affiliations
Stanislaw Jankowski, Warsaw Univ. of Technology (Poland)
Zbigniew Szymański, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 7502:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2009
Ryszard S. Romaniuk; Krzysztof S. Kulpa, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray