Outliers Detection Based on Partitioning Around Medoids

Abstract

Clustering is the process of grouping a set of objects into classes or clusters so that objects within a cluster have similarity in comparison to one another, but are dissimilar to objects in other clusters. Clustering analysis is a descriptive task that seeks to identify homogeneous groups of objects based on the values of their attributes. This system is intended to cluster Iris Plants (Setosa, Versicolor and Virginica) by using Partitioning Around Medoids (PAM) clustering algorithm. Partitioning Around Medoids (PAM) algorithm processes step of methods for selecting initial medoids. It also calculates the distance matrix once and uses it for finding new medoids at every iterative step. On further analysis of Iris data, the researchers found that Setosa is a clearly separable cluster while the other two clusters, Versicolor and Virginica, have significant overlap with each other. All clustering methods were able to identify Setosa more or less correctly, but made mistakes on Versicolor and Virginica. So, there are to detect inconsistent data which are outliers in the clusters. By using this system, the user can know about Iris plants, at the same time, they can learn outlier detection by PAM clustering algorithm.