A dynamic R-tree index based on hybrid clustering algorithm
Huang Ji-xian, Bao Guang-shu · Journal of Central South University(Science and Technology) · 2006
Considering that dynamic R-tree is implemented by dynamic insertion algorithm,and its quality of splitting algorithm influences directly the performance of R-tree and querying efficiency,in order to meet the demands of multi-dimension and complex spatial data,the hybrid clustering(HCR) algorithm was proposed for the nodes splitting of R-tree which was based on the common clustering algorithms,and some extensions were built.According to the difference of spatial objects distributed evenly and unevenly,different clustering rules were adopted to improve the query efficiency.Some comparisons and experiments were conducted.The results show that the hybrid clustering algorithm has high efficiency in querying.