A new filter-based Gene selection method based on dragonfly optimization and correlation-based feature selection

Cancer Diagnosis is considered one of microarray data's most developing applications. But the classification of cancer using microarray data stills a hard problem, this is because of the microarray data consists of a massive number of genes and a small number of cases. In order to tackle this problem a gene selection method must be used which improves the accuracy of classification. A new filter-based gene selection method is proposed in this paper. The proposed method merges the Dragonfly algorithm and the correlation-based feature selection, this is to reduce the redundancy between the genes selected and increase the relevance between the selected genes and the decision. Our proposed method is compared with nine famous feature selection methods. The experiments in this paper are applied to five widely used public microarray datasets. The used evaluation criterion of the selected features is the average accuracy of classification using three different classifiers, which are support vector machine, naive Bayes, and decision tree. Experimental results demonstrate that our proposed method is efficient and performs better than the other nine methods used in the experiment. It also shows that the proposed method can be used with anyone of the three classifiers included in our study to obtain an efficient automatic cancer diagnostic system.