Share Email Print
cover

Proceedings Paper

Position error correction of position sensitive detector by least squares support vector machine
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A new method for position error correction of position-sensitive detector (PSD) using least squares support vector machine (LS-SVM) is presented. The LS-SVM is established based on the structural risk minimization principle rather than minimize the empirical error commonly implemented in the neural networks, LS-SVM achieves higher generalization performance than the MLP and RBF neural networks in solving these machine learning problems. Another key property is that unlike MLP’ training that requires non-linear optimization with the danger of getting stuck into local minima, training LS-SVM is equivalent to solving a set of linear equations. Consequently, the solution of LS-SVM is always unique and globally optimal. A difference with the RBF neural networks is that no center parameter vectors of the Gaussians have to be specified and no number of hidden units has to be defined because of Mercer's condition. The position error correction procedure has been illustrated using 2D PSD as example. The results indicate that this approach is effective, and the position detection errors can be reduced from ±300μm to ±10μm.

Paper Details

Date Published: 20 January 2005
PDF: 7 pages
Proc. SPIE 5633, Advanced Materials and Devices for Sensing and Imaging II, (20 January 2005); doi: 10.1117/12.570262
Show Author Affiliations
Xiaodong Wang, Zhejiang Normal Univ. (China)
Meiying Ye, Zhejiang Normal Univ. (China)


Published in SPIE Proceedings Vol. 5633:
Advanced Materials and Devices for Sensing and Imaging II
Anbo Wang; Yimo Zhang; Yukihiro Ishii, Editor(s)

© SPIE. Terms of Use
Back to Top