Hierarchical clustering algorithm for dendrogram construction and cluster counting
Nataliya I. Boyko, Ukraine, O. A. Tkachyk · INFORMATICS AND MATHEMATICAL METHODS IN SIMULATION · 2023
The article provides a comprehensive overview of hierarchical clustering and dendrogram construction, with a focus on the methods used for determining the optimal number of clusters.The article discusses the theoretical foundations of hierarchical clustering and the process of constructing dendrograms, and goes on to describe several popular methods for determining the number of clusters.The article focused on both divisive and agglomerative clustering methods and the dendrogram, the advantages and disadvantages of each method, and how dendrograms are used to visualize the results of hierarchical clustering.It also provides comparison of hierarchical clustering with non-hierarchical clustering, particularly the K-means algorithm, and discusses their respective advantages and disadvantages.One of the key advantages of hierarchical clustering is that it does not require the user to specify the number of clusters in advance, as is the case with non-hierarchical clustering.Instead, a dendrogram can be used to determine the appropriate number of clusters.The article concludes by noting the usefulness of hierarchical clustering for a range of applications, particularly in exploratory data analysis.The article also covers the main methods to identify which objects and clusters are most similar.Additionally, the article provides an overview of the K-means clustering method and compares it to hierarchical clustering.