Search

Abstract: This paper presents a supervised classification based on labeled kernel component analysis (KPCA). KPCA have recently shown to be very effective on extracting nonlinear feature. However, KPCA operates in an unsupervised setting without using the class labels of training inputs to derive informative nonlinear projections. Based on this consideration, we describe a labeled classification method based on KPCA. The experimental results demonstrate that our method is more accurate than Support Vector Machine (SVM) classification method and Linear Discriminant Analysis (LDA) classification method. [Copyright &y& Elsevier]