Spatial selectivity estimation using cumulative density wavelet histogram

The purpose of selectivity estimation is to minimize the error of estimated value and query result using the summary data maintained on small memory space. Many works have been performed to estimate accurately selectivity. However, the existing works require a large amount of memory to retain accurate selectivity. In order to solve this problem, we propose a new technique cumulative density wavelet histogram, called CDW Histogram which is able to compress summary data and get an accurate selectivity in small memory space. The proposed method is based on the sub-histograms created by CD histogram and the wavelet transformation technique. The experimental results showed that the proposed method is superior to the existing selectivity estimation technique.