一种新的基于网格压缩的聚类算法SGRIDS研究

Research of new clustering algorithm SGRIDS based on grid data compression

引入了一种新的基于网格的数据压缩方法,并应用该方法对处理大型空间数据集的聚类算法SGR IDS进行研究。该方法考虑输入参数对聚类算法质量有较大影响,对密度阈值的确定进行了改进,从而减小输入参数的影响。实验证明,该方法能够获得较好的聚类效果。

By introducing a new grid-based data compression framework, conducted the study on the clustering algorithm SGRIDS which dealed with a large spatial databases. Considering that the input parameter has a great impact on the quality of clustering algorithms, improved the settlement of the value for density threshold, decreased the impact of input parameter, thus attaining a better clustering effect.