摘要
An intelligent method for improving position linearity of position-sensitive detector (PSD), based on support vector machines (SVMs), is developed. The SVM is established based on the structural risk minimization principle rather than minimizing the empirical error commonly implemented in neural networks. SVM can achieve higher generalization performance. Training SVM is equivalent to solving a linearly constrained quadratic programming problem, thus the solution of SVM is always unique and globally optimal. The improving position linearity procedure has been illustrated using a two-dimensional (2D) PSD. It is pointed out that the position linearity of the measuring system with a proper SVM correction is improved by two orders of magnitude in the measurement range.
An intelligent method for improving position linearity of position-sensitive detector (PSD), based on support vector machines (SVMs), is developed. The SVM is established based on the structural risk minimization principle rather than minimizing the empirical error commonly implemented in neural networks. SVM can achieve higher generalization performance. Training SVM is equivalent to solving a linearly constrained quadratic programming problem, thus the solution of SVM is always unique and globally optimal. The improving position linearity procedure has been illustrated using a two-dimensional (2D) PSD. It is pointed out that the position linearity of the measuring system with a proper SVM correction is improved by two orders of magnitude in the measurement range.
基金
This work was supported by Zhejiang Provincial Natural Science Foundation of China under Grant No. 602145.
