Makara Journal of Technology
Vol 15, No 1 (2011)

Two-Class Classification with Various Characteristics Based on Kernel Principal Component Analysis and Support Vector Machines

Timotius, Ivanna ( Department of Electronic Engineering, Satya Wacana Christian University, Salatiga 50711, Indonesia)
Setyawan, Iwan ( Department of Electronic Engineering, Satya Wacana Christian University, Salatiga 50711, Indonesia)
Febrianto, Andreas ( Department of Electronic Engineering, Satya Wacana Christian University, Salatiga 50711, Indonesia)



Article Info

Publish Date
22 Sep 2011

Abstract

Two class pattern classification problems appeared in many applications. In some applications, the characteristic of the members in a class is dissimilar. This paper proposed a classification system for this problem. The proposed system was developed based on the combination of kernel principal component analysis (KPCA) and support vector machines (SVMs). This system has been implemented in a two class face recognition problem. The average of the classification rate in this face image classification is 82.5%.

Copyrights © 2011