Rough Classifiers and Support Vector Machines using Boolean Kernels

Rough Sets (RS) and Support Vector Machine (SVM) are the two big and 
independent research areas in AI. Originally, rough set theory is 
dealing with the concept approximation problem under uncertainty. The 
basic idea of RS is related to lower and upper approximations, and it 
can be applied in classification problem. At the first sight RS and 
SVM offer different approaches to classification problem. Most RS 
methods are based on minimal decision rules, while SVM converts the 
linear classifiers into instance based classifiers. This paper 
presents a comparison analysis between these areas and shows that, 
despite differences, there are quite many analogies in the two 
approaches. We will show that some rough set classifiers are in fact 
the SVM with Boolean kernel and propose some hybrid methods that 
combine the advantages of those two great machine learning approaches.