An efficient cell-based clustering method for handling large, high-dimensional data
Jae‐Woo Chang · 2003
Abstract. Data mining applications have recently required a large amount of high-dimensional data. However, most clustering methods for the data miming applications do not work efficiently for dealing with large, high-dimensional data because of the so-called ‘curse of dimensionality ’ [1] and the limitation of available memory. In this paper, we propose an efficient cell-based clustering method for handling a large of amount of high-dimensional data. Our clustering method provides an efficient cell creation algorithm using a space-partitioning technique and a cell insertion algorithm to construct clusters as cells with more density than a given threshold. To achieve good retrieval performance on clusters, we also propose a new filtering-based index structure using an approximation technique. In addition, we compare the performance of our cellbased clustering method with the CLIQUE method in terms of cluster construction time, precision, and retrieval time. The experimental results show that our clustering method achieves better performance on cluster construction time and retrieval time. Finally, our clustering method shows good performance on system efficiency which is a measure to combine both precision and retrieval time. Keywords: Cell-based clustering methods, high-dimensional data, data mining 2 1.