Enhanced K-Means Clustering Algorithms in Pattern Detection of Human Freedom Index Dataset

Abstract

The human freedom index (HFI) evaluates the universal state of social liberty using a wide metric that includes individual, public, and financial liberty. Human freedom is a public notion that affirms a person's self-respect and is described here as undesirable freedom or the nonappearance of coercion. Since liberty is fundamentally valued and contributes to social development, it is worth measuring cautiously. This study emphasizes using the k-means clustering technique to locate clusters in data, with the inconstant k representing the number of clusters. After the groups have been gathered, this method will be tested with several k-clusters defining metrics in order to find the best k value for the model and group the data into the correct cluster counts. This study aims to examine existing data mining approaches for k-means clustering and mini batch k-means clustering and develop ways to improve accuracy by looking at a large number of statistics and choosing those with a specific shape using the human freedom index (HFI).