Interval-valued Data Ward's Hierarchical Agglomerative Clustering Method: Comparison of Three Representative Merge Points
Sérgio Mário Lins Galdino, Jornandes Dias · 2021 International Conference on Engineering and Emerging Technologies (ICEET) · 2021
This paper presents Ward Linkage Data Clustering on interval-valued data. Nowadays, clustering methods rely dissimilarity measures for interval-valued data uses representative point distance. Our work applies Ward's Hierarchical Agglomerative Clustering Method to interval-valued data based on the Range Euclidean Metric as a reliable alternative to be used to uncertainty quantification from interval-valued data. The range metric use makes possible different merge points be explored in the Hierarchical Cluster Analysis methods. We observe the remarkable impact of using three different merge points-infimum, supremum and midpoint of used range Euclidean distance on obtained clusters.