Feature selection using modified imperialist competitive algorithm

Feature selection process is one of the main steps in data mining and knowledge discovery. Feature selection is a process to remove redundant and irreverent features without reducing the classification accuracy. This paper tries to select the best features set using imperialist competitive algorithm. Imperialist competitive algorithm is a novel population based algorithm which is inspired sociopolitical process of imperialist competition. In this paper, a modified imperialist competitive algorithm is presented and then this proposed algorithm is applied to feature selection process. To verify the effectiveness of the proposed approach, experiments carried out on some datasets. Results showed the features set selected by the imperialist competitive algorithm provide the better classification performance compared to the other methods.