Binarization and Validation in Formal Concept Analysis

Abstract

Representation and visualization of continuous data using the Formal Concept Analysis (FCA) became an important requirement in real-life fields. Application of formal concept analysis (FCA) model on numerical data, a scaling or Discretization / binarization procedures should be applied as preprocessing stage. The Scaling procedure increases the complexity of computation of the FCA, while the binarization process leads to a distortion in the internal structure of the input data set. The proposed approach uses a binarization procedure prior to applying FCA model, and then applies a validation process to the generated lattice to measure or ensure its degree of accuracy. The introduced approach is based on the evaluation of each attribute according to the objects of its extent set. To prove the validity of the introduced approach, the technique is applied on two data sets in the medical field which are the Indian Diabetes and the Breast Cancer data sets. Both data sets show the generation of a valid lattice.