Hybrid Multiple-Filter-Multiple-Wrapper Method Used for Gene Selection from Biomedical Database.

In this paper, it is proposed a hybrid multiple-filter/multiple-wrapper method for selection and classification of DNA-microarray data. The wrapper algorithm GA/TS/SVM, combines relevant genes obtained of five data filtering methods, to perform an efficiently guided search of a subset gene of the bases obtained from the DNA-microarray technology. In the experimental results, it is observed that the method GA/TS/SVM works accurately, and achieves a lower classification error rate using a smaller number of selected genes than other methods reported in literature.