A Symmetrically Diminished Interconnected Database Segmentation Framework Using Data Mining

Abstract

Clustering is a series of mathematical learning methods for the exploration of heterogeneous partition structures grouping homogeneous data known as clusters. Clustering has successfully been implemented in many areas, such as medicine, genetics, economics, industry, and so on. We propose the notion of clustering for problems of multifactorial data processing in this article. The aim of a case study is to examine trends in 813 individuals for an issue in occupational medicine. To minimise the dimensionality of the data set, we use the key component analysis as the most widely used statistical method in factor analysis. The natural problems, particularly in the field of medicine, are mostly focused on performance criteria of a stratified kind, while PCA processes only quantitative. In comparison, consistency data are typically binary-coded, initially unnoticeable, quantitative replies. We are therefore introducing a new approach that enables theoretical and practical data to be analysed simultaneously. The idea of this approach is to project important variables on the quantitative feature space. The corresponding Clustering algorithm subspaces are then given an ideal model.