A Grid-based Spatial Association Mining Method

Abstract

The grid is a distributed computing infrastructure that supports the sharing and coordinated use of various resources in virtual organizations. The grid can be used for compute intensive tasks and data intensive applications. Data mining algorithms are intensive compute and data, and spatial data are heterogeneous, multidimensional and stored at various places. Therefore, the grid can provide a computing and data management platform for spatial data. In this paper, a grid-based spatial association mining method, grid-based spatial apriori algorithm (GSAA), is presented to find hidden relations and regularities in the grid framework. The main thoughts of GSAA are described. We adopt GSAA in a traffic information system. It discovers the inherent connections and relative factors, and finds the causes of traffic accidents and the places where the traffic accidents often take place. It proves to improve the traffic conditions of cities in the grid framework effectively.