Importante

Artif Intell Rev (2011) 36:179–204
DOI 10.1007/s10462-011-9210-5

A survey: hybrid evolutionary algorithms
for cluster analysis
Mohamed Jafar Abul Hasan ·
Sivakumar Ramakrishnan

Published online: 11 March 2011
© Springer Science+Business Media B.V. 2011

Abstract Clustering is a popular data analysis and data mining technique. It is the unsupervised classification of patterns intogroups. Many algorithms for large data sets have been
proposed in the literature using different techniques. However, conventional algorithms have
some shortcomings such as slowness of the convergence, sensitive to initial value and preset classed in large scale data set etc. and they still require much investigation to improve
performance and efficiency. Over the last decade, clustering withant-based and swarm-based
algorithms are emerging as an alternative to more traditional clustering techniques. Many
complex optimization problems still exist, and it is often very difficult to obtain the desired
result with one of these algorithms alone. Thus, robust and flexible techniques of optimization are needed to generate good results for clustering data. Some algorithms that imitate
certainnatural principles, known as evolutionary algorithms have been used in a wide variety
of real-world applications. Recently, much research has been proposed using hybrid evolutionary algorithms to solve the clustering problem. This paper provides a survey of hybrid
evolutionary algorithms for cluster analysis.
Keywords Data mining · Cluster analysis · Swarm intelligence ·
Hybrid evolutionaryalgorithms

1 Introduction
In recent years there has been an explosive growth in the generation and storage of electronic
information. In fact, data doubles about every year but useful information seems to be decreasing. This large amount of stored data contains valuable hidden knowledge, which could be
M. J. Abul Hasan (B · S. Ramakrishnan
)
Department of Computer Science, A.V.V.M. Sri PushpamCollege (Autonomous),
Poondi, Tamil Nadu, India
e-mail: mohamedjafaroa@yahoo.in
S. Ramakrishnan
e-mail: rskumar.avvmspc@gmail.com

123

180

M. J. Abul Hasan, S. Ramakrishnan

used to improve the decision-making process of an organization. Extracting information and
knowledge from the continuously increasing amount of enterprise data available, has become
a complex task. Therefore,a process for converting large amounts of data to knowledge will
become invaluable. The area of knowledge discovery in databases (KDD) has arisen over
the last decade to address this challenge. Data mining is a part of the KDD process. It refers
to extracting or mining knowledge from large amounts of data. It involves the use of data
analysis techniques to discover previously unknown, validpatterns and relationships in large
data sets (Han and Kamber 2001).
Clustering is one of the important data mining tasks. Clustering means the act of partitioning an unlabeled dataset into groups of similar objects. Each group, called a ‘cluster’, consists
of objects that are similar between themselves and dissimilar to objects of other groups. The
goal of clustering is to group sets ofobjects into classes such that similar objects are placed
in the same cluster while dissimilar objects are in separate clusters. Clustering is used as a
data processing technique in many different areas, including artificial intelligence, bioinformatics, biology, computer vision, city planning, data mining, data compression, earth quake
studies, image analysis, image segmentation, informationretrieval, machine learning, marketing, medicine, object recognition, pattern recognition, spatial database analysis, statistics
and web mining (Jain et al. 1999).
The process of knowledge discovery from databases necessitates fast and automatic clustering of very large datasets. Researchers have developed many clustering algorithms. Some
of the clustering algorithms in the literature are BRICH...