Imbalanced data set classification is a relatively new research line within the broader context of machine learning studies, which tries to learn from the skewed data distribution. A data set is imbalanced when the samples of one class consist of more instances than the rest of the classes in two-class and multi-class data sets [1]. Most of the standard machine learning algorithms show poor performance in this kind of datasets, because they tend to favor the majority class samples, resulting in poor predictive accuracy over the minority class [2]. Therefore, it becomes tough to learn the rare but

No abstract

No abstract

Abstract:The imperialist competitive algorithm (ICA) is a recent global search strategy developed based on human social evolutionary phenomena in the real world. However, the ICA has the drawback of trapping in local optimum solutions when used for high-dimensional or complex multimodal functions. In order to deal with this situation, in this paper an improved ICA, named GICA, is proposed that can enhance ICA performance by using a new assimilation method and establishing a relationship between countries inspired by the globalization concept in the real world. The proposed algorithm is evaluated using a set of well-known benchmark functions for global optimization. Obtained results show the efficiency and effectiveness of the method and show that this strategy can deal with the local optimum problem.

No abstract