Saengsiri, PatharawutWichian, Sageemas NaMeesad, PhayungHerwig, UngerEichler, GeraldKüpper, AxelSchau, VolkmarFouchal, HacèneUnger, HerwigEichler, GeraldKüpper, AxelSchau, VolkmarFouchal, HacèneUnger, Herwig2019-01-112019-01-112011978-3-88579-280-2https://dl.gi.de/handle/20.500.12116/18978In fact, cancer is produced for genetic reasons. So, gene feature selection techniques are very important for biological processes which help to find subsets of informative genes. However, the quality of recognition is still not sufficient and leads to low accuracy rates. Hence, this research proposes integrating a feature selection method (IFS). There two phases of IFS: 1) determining feature length by Gain Ratio (GR) and 2) estimating each rank list using a wrapper approach based on K-nearest neighbor classification (KNN), Support Vector Machine (SVM), and Random Forest (RF). Experimental results based on two gene expression datasets, it is found that the proposed method not only has higher accuracy rate than tradition methods, but also reduce many irrelevant features. In addition, most models based on IFS method are more beneficial when working with two or multi-classes.enText/Conference Paper1617-5468