DC-Tree: Density-Based Clustering Index for Objects in Skewed Distribution

Efficient spatial index is essential for querying data objects in spatial databases. Data objects may be unevenly distributed in real situations. In this setting, R-tree and its variants may cause large overlap and coverage among branch nodes, which impact the query efficiency to some extent. To address this challenge, this paper proposes a novel Density-based Clustering tree (DC-tree) by clustering data objects. Data objects in a dense region will be put into the same node. Thus, overlap and coverage among node regions are less than that of R-tree and its variants. Since dense regions contain more data objects, we assign a higher priority to these region nodes for facilitating the query operation. Experimental results show that in the context of skewed distribution, DC-tree can have a better performance for the insertion, deletion and query operations than that of traditional R-tree.