Study of Kernel Principal Component Regression Function Estimators Properties
| Main Author: | Ismail Djakaria |
|---|---|
| Format: | Article |
| Terbitan: |
International Journal of Academic Research
, 2017
|
| Subjects: | |
| Online Access: |
http://repository.ung.ac.id/karyailmiah/show/555/study-of-kernel-principal-component-regression-function-estimators-properties.html |
Daftar Isi:
- This paper purpose to examine the kernel principal component regression (KPCR), which is the development of the principal component regression (PCR) with the radial basis fungction (RBF) kernel or Gaussian kernel. This study started to presented a standard principal component analysis (PCA) and kernel principal component analysis (KPCA), that includes PCA in feature space and KPCA in input space. The focus of this study describes the properties of model KPCR published in several theorems, includes linear estimator, unbiased estimator, and the best estimator, that known the best linear unbiased estimator (BLUE). Key words: PCR model, KPCR model, RBF kernel, the BLUE.