CLOPE (Clustering with sLOPE) is a simple and fast histogram-based\nclustering algorithm for categorical data. However, given the same data set with the same\ninput parameter, the clustering results by this algorithm would possibly be different if the\ntransactions are input in a different sequence. In this paper, a hierarchical clustering\nframework is proposed as an extension of CLOPE to generate stable and satisfactory\nclustering results based on an optimized agglomerative merge process. The new clustering\nprofit is defined as the merge criteria and the cluster graph structure is proposed to\noptimize the merge iteration process. The experiments conducted on two datasets both\ndemonstrate that the agglomerative approach achieves stable clustering results with a better\nprofit value, but costs much more time due to the worse complexity.
Loading....