Clustering Algorithm Based on Grid and Density for Data Stream

Data stream clustering analysis can extract useful information in real time from massive data, and have been widely applied in many fields. The traditional grid-based data stream clustering algorithm is not precise and the processing of the grid cell boundary points is crude. On the other side, the density-based clustering algorithm is inefficient and is not easy for the discovery of arbitrary shape cluster problem. Thus, this paper proposes a kind of clustering algorithm based on both grid and density for data stream. This algorithm method processes the boundary points by segmenting the data space and using data points to deal with the influence coefficient of the adjacent grid elements, in order to improve the efficiency and accuracy of the algorithm. The experimental results prove this algorithmic method to an accurate, quick, feasible way to identify clusters.