Fuzzy C mean technique on high-dimensional data for fast and scalable clustering
C. Shanthi, S.J. Saritha · 2017
Day to day increase Express growth of data sets had created an arriving need to extract the knowledge hiding them. Clustering is group of data points which have same properties in a dataset. Finding cluster in the high dimensional dataset is significant data mining problem. Data group together under different subsets of dimensions is called Subspaces. But the epidemic growth in the number of subspaces with data makes the complete process of subspace clustering calculatingly very charge However, the enforcement of the existing algorithms based on this approach degrade acutely with the increase in the number of dimensions. In a proposed System an innovative Subscale clustering algorithm is used to find important clusters with less cost and requires K-database scans for K-dimensional data set. This algorithm closely deals with high dimensionality of the dataset and is mostly correlate. In this paper represent detailed information of the Subscale algorithm and its working progress. We use fuzzy logic technique on various data sets.