Evaluating Cluster Quality Using Modified Density Subspace Clustering Approach

Abstract

Clustering of the time series data faced with curse of dimensionality, where real world data consist of many dimensions. Finding the clusters in feature space, subspace clustering is a growing task. Density based approach to identify clusters in dimensional point sets. Density subspace clustering is a method to detect the density-connected clusters in all subspaces of high dimensional data for clustering time series data streams Multidimensional data clustering evaluation can be done through a density-based approach. In this approach proposed, Density subspace clustering algorithm is used to find best cluster result from the dataset. Density subspace clustering algorithm selects the P set of attributes from the dataset. Then apply the density clustering for selected attributes from the dataset .From the resultant cluster calculate the intra and inter cluster distance. Measuring the similarity between data objects in sparse and high-dimensional data in the dataset, Plays a very important role in the success or failure of a clustering method. Evaluate the similarity between data points and consequently formulate new criterion functions for clustering .Improve the accuracy and evaluate the similarity between the data points in the clustering,. The proposed algorithm also concentrates the Density Divergence Problem (Outlier). Proposed system clustering results compared them with existing clustering algorithms in terms of the Execution time, Cluster Quality analysis. Experimental results show that proposed system improves clustering quality result, and less time than the existing clustering methods.