A Method Based on Iterative-Classification for Improving Clustering Results

Abstract

Clustering and classification are independent methods of data mining. This paper compares relative merits of two methods. And then try to integrate them to construct an effective way to improve clustering results. The better the results are, the better internal information of data sets will be shown. However, there isn’t any improved method which is suitable for all clustering algorithms until now. This paper proposes a modified method based on iterative-classification for better clustering results. Experiment results show that the proposed method improves the accuracy of clustering results effectively.