A kind of hybrid classification algorithm based on rough set and support vector machine

Support vector machine (SVM) is a new machine learning method and it has greater generalization performance. Rough set theory is a new effective tool in dealing with vagueness and uncertainty information. Integrating the advantages of two approaches, a kind of hybrid classification algorithm to efficiently extract classification rules is proposed in the paper. Moreover, a new kind of attribute reduction algorithm by constructing generalized decision information table is presented in the paper. Finally they are applied into handwritten Chinese recognition, and result shows the validity and feasibility of the algorithm suggested in the paper.