This study proposes a novel method that employs correlation based filter for dimensionality reduction followed by fuzzy rough quick reduct for feature selection on a particle swarm optimization search space. The first phase removed the redundant genes using correlation coefficient filter on a particle swarm optimization search space. The second phase produced a fuzzy rough quick reduct that would be used for classification. The genes obtained after feature selection are subjected to classification using traditional classifiers. It has been determined that the proposed method contributes to reduction in the total number of genes and improvement in the classifier accuracy compared to gene selection and classification using correlation coefficient and traditional fuzzy rough quick reduct algorithm. This approach also reduces the number of misclassifications that might occur in other approaches.
A. Chinnaswamy and Ramakrishnan, S., “Modified Fuzzy Rough Quick Reduct Algorithm for Feature Selection in Cancer Microarray Data”, Asian Journal of Information Technology, vol. 15, no. 2, pp. 199–210, 2016.