A fast and efficient incremental Clustering algorithm for dynamic Data clustering

Abstract

The existing clustering algorithm integrates static components Most of the applications are converted into real time application It enforced that object to be clustered during the process based on its property There are many applications based on incremental data mining in data warehousing applications and sensor network Dynamic clustering is a mechanism to adopt the clustering in real time environments such as mobile computing war end movement observation etc Most of the supervised classification algorithms perform well and will give ideal results with good accuracy measured with normal accuracy metrics which is calculated using the original class labels and the calculated class labels However if the performance of cluster algorithm is measured with cluster validation metrics without any reference to class label then it will give entirely different result So even measuring the accuracy of a dynamic clustering algorithm is also a challenging task newlineIn this research a new density based dynamic data clustering algorithm is proposed and named as normal Dynamic DBSCAN newline