Абстрактный

Partitioning Clustering Algorithms for Data Stream Outlier Detection

Dr. S. Vijayarani, Ms.P.Jothi

Recently many researchers have focused on mining data streams and they proposed many techniques and algorithms for data streams. They are data stream classification, data stream clustering, and data stream frequent pattern items and so on. Data stream clustering techniques are highly helpful to cluster the similar data items in data streams and also to detect the outliers, so they are called cluster based outlier detection. The main objective of this research work is to perform the clustering process and detecting the outliers in data streams. In this research work, two partitioning clustering algorithms namely CLARANS and E-CLARANS (Enhanced Clarans) are used for clustering and detecting the outliers in data streams. Two performance factors such as clustering accuracy and outlier detection accuracy are used for observation. By examining the experimental results, it is observed that the proposed ECLARANS clustering algorithm performance is more accurate than the existing algorithm CLARANS.