Research on fuzzy clustering algorithm WEKA-based

Abstract

The data in Internet has a large scale and dynamic peculiarity, the discovered knowledge or rules are likely to be imprecise or incomplete generally. Owing to the introduction of Fuzzy theory and information entropy into the clustering analysis, we ravel out the difficulties and achieve the best the results for clustering by looking for Fuzzy similarity upper approximation. Moreover, we improved on the algorithm by making use of building Fuzzy similarity relationship on the data sets. The process of embedding the Fuzzy approximation algorithm into the WEKA platform in which the classes and visualization functions of open source WEKA is fully utilized. The Fuzzy approximation algorithms extended the clustering algorithm in the WEKA system. The experiment proves that it has a higher accuracy for the nominal data. © 2011 Springer-Verlag Berlin Heidelberg.