Kernel machines and classifier ensemble learning for biomedical applications
Date of Issue2006
School of Electrical and Electronic Engineering
This thesis addressed a type of imbalanced data problem encountered in many biomedical applications where one category of data is compactly clustered and the other category of data is scattered in the input space. A new Hybrid Kernel Machine Ensemble (HKME) is proposed to address this problem by integrating a two-class discriminative Support Vector Machine (SVM) and a one-class recognition-based SVM.
DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics
Nanyang Technological University