Prediction of cancer using customised fuzzy rough machine learning approaches

Abstract

This Letter proposes a customised approach for attribute selection applied to the fuzzy rough quick reduct algorithm. The unbalanced data is balanced using synthetic minority oversampling technique. The huge dimensionality of the cancer data is reduced using a correlation-based filter. The dimensionality reduced balanced attribute gene subset is used to compute the final minimal reduct set using a customised fuzzy triangular norm operator on the fuzzy rough quick reduct algorithm. The customised fuzzy triangular norm operator is used with a Lukasiewicz fuzzy implicator to compute the fuzzy approximation. The customised operator selects the least number of informative feature genes from the dimensionality reduced datasets. Classification accuracy using leave-one-out cross validation of 94.85, 76.54, 98.11, and 99.13% is obtained using a customised function for Lukasiewicz triangular norm operator on leukemia, central nervous system, lung, and ovarian datasets, respectively. Performance analysis of the conventional fuzzy rough quick reduct and the proposed method are performed using parameters such as classification accuracy, precision, recall, F-measure, scatter plots, receiver operating characteristic area, McNemar test, chi-squared test, Matthew's correlation coefficient and false discovery rate that are used to prove that the proposed approach performs better than available methods in the literature.

Keywords

• lung
• fuzzy set theory
• cancer
• rough set theory
• pattern classification
• learning (artificial intelligence)
• sampling methods
• approximation theory
• medical computing
• cancer data
• fuzzy rough quick reduct algorithm
• Lukasiewicz fuzzy implicator
• fuzzy approximation
• fuzzy rough machine learning approaches
• fuzzy triangular norm operator
• correlation-based filter
• leukaemia
• central nervous system
• ovarian datasets
• lung
• McNemar test
• chi-squared test
• Matthew's correlation coefficient