A filter-wrapper model for high-dimensional feature selection based on evolutionary computation

Abstract

In machine learning, feature selection plays an important role in improving prediction accuracy and reducing time complexity. This paper proposes a filter-wrapper model to obtain a feature subset from high-dimensional data in a short time. Firstly, features are ranked by information gain and Fisher Score. Secondly, the feature search is realized by binary evolutionary computation based on wrapper. To avoid wasting a lot of searches on low-ranked features, an adaptive feature selection strategy is adopted to guide population search and position update. Finally, a learning strategy is proposed, in which learners study from exemplars and complete position update, and the exemplars are constituted by optimal solutions to balance exploration and exploitation. To demonstrate the effectiveness and efficiency of the proposed model, three binary evolutionary computations, including particle swarm optimization, grey wolf optimizer, and fish migration optimization, are applied to the model, and they present excellent performance in high-dimensional data sets.