A classification method based on PAM algorithm and discrete preprocess
Huaizhen Yang, Lei Li · 2010
Using clustering method to generate training set, and applying rough set theory to discretization preprocess, the classification accuracy can be improve well. This paper applied PAM clustering algorithm to constitute a training set from original sample, used a discrete algorithm that integrates Boolean logic with rough set theory to discretize the training set, and trained classifier by the discrete training set. When classification was carried out in the same data set, experimental results showed that compared to the RDDTE method only based on the PAM algorithm to preprocess, the classification accuracy based on the new method increased 15.5 percentage points at most. Besides, the new method selected a smaller amount of training set.