Boolean binary particle swarm optimization for feature selection

Abstract

Feature selection is the process of choosing a subset of features from an original set. This subset should be necessary, reasonably represent the original data, and useful for identification classification. The task of feature selection is to search for an optimal solution in a - usually large - search space. However, if the search space too large, difficulties can occur during the search process, often resulting in a considerable increase in computational time. A particle swarm optimization algorithm (PSO) is a relatively new evolutionary computation technique, which has previously been used to implement feature selection. However, particle swarm optimization, like other evolutionary algorithms, tends to converge at a local optimum early. In this paper, we introduce a Boolean function which improves on the disadvantages of standard particle swarm optimization and use it to implement a feature selection for six microarray data sets. The experimental results show that the proposed method selects a smaller number of feature subsets and obtains better classification accuracy than standard PSO.