Feature subset selection using constrained binary/integer biogeography-based optimization

Feature selection plays a crucial role in applications where data consists of hundreds of features due to curse of dimensionality. This paper presents two feature selection methods by modifying the main operators of Biogeography-Based Optimization algorithm. The difference between these methods is in employing binary or integer coding. The simulations perform on datasets with different feature dimensions and classes. The results indicate the effectiveness of the proposed methods in comparison with other most frequently used meta-heuristic strategies in feature selection problems.