OBSERVATIONS OF SPATIAL DATA MINING ALGORITHMS AND CHALLENGES

摘要

In this paper, we have discussed about the spatial data mining algorithms, tools, techniques and challenges, which Have been developed and implemented. The spatial data mining algorithms are Neighbourhood, Single Scan, Decision tree, Neighbouring index, STING, Spatial Dominant CLARANS, non-spatial dominant CLARANS, Spatial association, GDBSCAN for the sequential computing or parallel computing in the high performance computing(HPC). There are also some GRID computing based spatial data mining algorithms have been developed and implemented for spatial data stored at different geographical sites such as STING, STING+, Wave-Cluster, Bang Clustering, Clustering in quest(CLIQUE), Expectation Maximization Neighbourhood, etc. These algorithms, tools and techniques have some drawback and challenges for the huge and complex spatial data, which we have also discussed.