Detection of Outlier-Communities using Minimum Spanning Tree

Community (also known as clusters) is a group of nodes with dense connection. Detecting outlier-communities from database is a big desire. In this paper we propose a novel Minimum Spanning Tree based algorithm for detecting outlier-communities from complex networks. The algorithm uses a new community validation criterion based on the geometric property of data partition of the data set in order to find the proper number of communities. The algorithm works in two phases. The first phase of the algorithm creates optimal number of communities, whereas the second phase of the algorithm finds outlier-communities.