Complex Networks

Chapter 7

Data Clustering

7.1 Introduction

A cluster is a collection of objects that are similar to each other using some attribute

and therefore can be treated as a group. Some examples of objects under consider-

ation are biological data points obtained experimentally, people in social networks

and mobile ad hoc computers. Output of a clustering method should provide clusters

where intra-cluster similarity is high and inter-cluster similarity is low. The qual-

ity of a clustering method is dependent on the similarity measure and the algorithm

employed.

Formally, given a set P = {p

1

,..., p

n

} of n data points representing n objects, the

goal of clustering ...