A Review of Protection against Unauthorized Access Using Sub-Space Outliers Ranking

Retrieval of information from the databases is now a days significant issues. The thrust of information for decision making is challenging one. To overcome this problem, different techniques have been developed for this purpose. One of techniques is clustering. Clustering is a significant task in data analysis and data mining applications. It is the task of arrangement a set of objects so that objects in the identical group are more related to each other than to those in other groups (clusters). The clustering is unsupervised learning. In this paper we propose a methodology for comparing clustering methods based on the quality of the result and the performance of the execution. The quality of a clustering result depends on both the similarity measure used by the method and its implementation. Clustering has been widely used as a segmentation approach therefore, choosing an appropriate clustering method is very critical to achieve better results. A good clustering method will produce high superiority clusters with high intra-class similarity and low inter-class similarity. There are different types of Clustering algorithms partition-based algorithms such as K-Means, KNN, density-based algorithms. Partitioning clustering algorithm splits the data points into k partition, where each partition represents a cluster. Density based algorithms find the cluster according to the regions which grow with high density. It is the one-scan algorithms.