The Analysis of Hybrid Brain Storm Optimisation Approaches in Feature Selection.

The volume of data available has risen significantly in recent years due to advancements in data gathering techniques in different fields. The collected data in many domains are typically of high dimensionality, making it impossible to select an optimum range of features. There are many existing research papers that discuss feature selection process used by metaheuristic algorithm. One of them is brain storm optimisation (BSO) algorithm, which is relatively new swarm intelligence algorithm that mimics the brainstorming process in which a group of people solve a problem together. The aim of this paper is to present and analyse hybrid BSO algorithm solutions combined with other metaheuristic algorithms in feature selection process. The hybrid BSO algorithm overcomes the lack of exploitation in the original BSO algorithm; and simultaneously, the obtained statistical results prove the efficiency and robustness over other state-of-the-art approaches.