Data mining algorithms to compute mixed concepts with negative attributes: an application to breast cancer data analysis

Abstract

In the design of mathematical methods for a medical problem, one of the kernel issues is the identification of symptoms and measures that could help in the diagnosis. Discovering connections among them constitute a big challenge because it allows to reduce the number of parameters to be considered in the mathematical model. In this work, we focus on formal concept analysis as a very promising technique to address this problem. In previous works, we have studied the use of formal concept analysis to manage attribute implications. In this work, we propose to extend the knowledge that we can extract from every context using positive and negative information, which constitutes an open problem. Based on the main classical algorithms, we propose new methods to generate the lattice concept with positive and negative information to be used as a kind of map of attribute connections. We also compare them in an experiment built with datasets from the UCI repository for machine learning. We finally apply the mining techniques to extract the knowledge contained in a real data set containing information about patients suffering breast cancer. The result obtained have been contrasted with medical scientists to illustrate the benefits of our proposal.

Concept lattices with negative information: A characterization theorem

“…They will be A C C E P T E D M A N U S C R I P T inspired by the classical ones but take into account the advantages provided by the algebraic results presented here, allowing an increase in performance. As a first step in this direction, in [20], we make a review of the most relevant traditional algorithm for mining concept lattices and propose a preliminary extended versions of all of them to compute mixed concept lattices. Our intention is to study the applicability of the results given in [1] to the problem of mining mixed concept lattices.…”

A Comparative Analysis of Data Mining Techniques on Breast Cancer Diagnosis Data using WEKA Toolbox

“…By analyzing the literature, it is noticeable that different techniques got the highest accuracy in each study as follows: in the study conducted by [11], the highest accuracy was achieved by Bayes Network (BN), and SVM and DT (C5.0) got the best accuracy in [12]. Similarly, by looking at [13], it is noticeable that the highest accuracy was yielded by LR and in [15] the highest accuracy was achieved by the J48 classifier.…”

“…To analyze breast cancer data, [15] utilized four different DT classification algorithms, namely, Classification and Regression Trees (CART), J48, Best First Tree (BF Tree) and DT (AD Tree). The experiment employed the WEKA tool, and the results demonstrated that the J48 classifier reached the highest accuracy of 99% whereas the CART algorithms resulted in 96% accuracy; AD Tree algorithm resulted in 97%, and BF Tree algorithm resulted in 98%.…”

Inference of Mixed Information in Formal Concept Analysis

“…[3] have approached the generation of mixed implications from two given sets of implications only with positive and negative attributes respectively. We have followed this line: in [7], we extended the classical FCA framework with new derivation operators constituting a Galois connection for the treatment of negative and positive information in FCA and in [5,6] we proposed some mining algorithms to derive directly mixed implications.…”