Data mining is a process by which valuable information can be obtained from a large volume of data. Clustering is considered as one of the most important data mining methods. Despite the progress of single clustering methods, in the last few years, the concept of ensemble clustering has received more attention due to its efficiency. This type of clustering is actually a combination of several basic clustering algorithms to achieve high-quality final clustering. Of course, this method; It poses challenges due to complexities in primary clusters such as overlap, ambiguity, instability, and uncertainty. To solve these challenges, in this research, a new ensemble hierarchical clustering algorithm based on improved distance criteria and based on merits at cluster and partition levels; provided. The main idea of the proposed method is based on using a subset of the best primary clusters instead of all of them in the consensus function. In this method, clusters are selected to participate in the final consensus that have more merit than a predefined threshold. The simulation results on the standard data set show that the proposed method is a reliable method with an average NMI of 0.58.
