PROMETHEE filter-based method for microarray gene expression data

Gene expression datasets have been successfully applied for a variety of purposes, including cancer classification. The challenges faced in developing effective classifiers for expression datasets are high dimensionality and over-fitting. Gene selection is an effective and efficient method to overcome these challenges and improve the predictive accuracy of a classifier. Based on PROMETHEE, this paper introduces a multi-filter ensemble approach by integrating the results of two potential filters namely MaCΨ-filter and PCRWG-filter to pre-select the most informative genes. Experiments were conducted on nine microarray datasets to demonstrate the performance of the proposed method.