Comparative Analysis of Fuzzy C Means and Fuzzy C Means++

Cluster analysis is one of the most useful means for identifying relations and patterns in the area of data mining. It can be defined as partitioning of large volumes of data into various clusters that share some property or attribute. The most common clustering algorithm is k means. The more improved version of k means that incorporates fuzzy feature is fuzzy c means. To overcome some of the limitations of fuzzy c means, fuzzy c means ++ was introduced which was based on effective seeding mechanism of k means++ algorithm. The latter algorithm showed remarkable results but with some more limitations of its own. In this paper, we discuss both the methods and their algorithms in detail. We discuss the advantages and limitations of each in various scenarios.