Enhanced Binary Small World Optimization Algorithm for High Dimensional Datasets

Large scale databases with high dimensional datasets can be mined and used for making decisions which may be unknown information but effective and will be used in the related fields like bio-informatics, medical, business, etc. Clustering is an unsupervised method that creates group of objects or clusters such that objects in the same group are very similar and objects in different group are very distinct. It allows users to analyze data from many different dimensions and categorize it, and summarize the relationships. Technically, binary small world optimization algorithm (BSWOA) is newly implied technique. In this paper, we review and compare these clustering algorithms to identify their efficiency and differences among them. Keywords-Clustering, Knowledge discovery, Clustering methods, Dynamic clustering problems.