A Critical Review of Density-based Data Stream Clustering Techniques

Data stream is relatively new and emerging domain in the current era of Internet advancement. Clustering data streams is equally important and difficult because of the numerous hurdles attached to it. A number of algorithms have been proposed to offer solutions for efficient clustering. Grid based clustering approach was adopted few years ago to overcome the limitations of conventional partition-based algorithms for data stream clustering. Data points are mapped to the grid-cells to form micro-clusters which later are used for clustering. Using density in the clustering process is proved to be a remarkable success and in recent years many researchers have used density to find arbitrary shaped & density clusters and identify outliers. Concept of density-based clustering is to use grid-based clustering at core and create a distinction between dense and sparse grids using density threshold values and use dense grids to yield clustering results; which provide more cluster purity and accuracy. In this paper, we reviewed grid based data stream clustering algorithms which utilize density. We evaluated their functionalities and identified their limitations. In the end, we critically evaluated different aspects of algorithms and suggested one of these algorithms which is better in terms of performance and accuracy.