A Research on Different Clustering Algorithms and Techniques

Abstract

Learning is the process of generating useful information from a huge volume of data. Learning can be classified as supervised learning and unsupervised learning. Clustering is a kind of unsupervised learning. Clustering is also one of the data mining methods. In all clustering algorithms, the goal is to minimize intracluster distances, and to maximize intercluster distances. Whatever a clustering algorithm provides a better performance, it has the more successful to achieve this goal [2]. Nowadays, although many research done in the field of clustering algorithms, these algorithms have the challenges such as processing time, scalability, accuracy, etc. Comparing various methods of the clustering, the contributions of the recent researches focused on solving the clustering challenges of the partition method [3]. In this paper, the partitioning clustering method is introduced, the procedure of the clustering algorithms is described, and finally the new improved methods and the proposed solutions to solve these challenges are explained [4].The clustering algorithms are categorized based upon different research phenomenon. Varieties of algorithms have recently occurred and were effectively applied to real-life data mining problems. This survey mainly focuses on partition based clustering algorithms namely k-Means, k-Medoids and Fuzzy c-Means In particular; they applied mostly in medical data sets. The importance of the survey is to explore the various applications in different domains [5].