Spatial Data Mining with Uncertainty
Binbin He, Cuihua Chen · 2006
On the basis of analyzing the deficiencies of traditional spatial data mining, a framework for spatial data mining with uncertainty has been founded. Four key problems have been analyzed, including uncertainty simulation of spatial data with Monte Carlo method, spatial autocorrelation measurement, discretization of continuous data based on neighbourhood EM algorithm and uncertainty assessment of association rules. Meanwhile, the experiments concerned have been performed using the environmental geochemistry data gotten from Dexing, Jiangxi province in China