An evolutionary filter approach to feature selection in classification for both single- and multi-objective scenarios
Emrah Hançer, Bing Xue, Mengjie Zhang
Abstract
The high-dimensional datasets in various domains, such as text categorization, information retrieval and bioinformatics, have highlighted the importance of feature selection in data mining. Despite the numerous existing approaches to feature selection, there is still a need for further research in this field. In this paper, we propose an evolutionary filter feature selection approach that can be used for both single- and multi-objective scenarios by introducing an objective function inspired by Neighborhood Component Analysis (NCA)-based method and then integrating it into the differential evolution framework. The proposed approach applicable to two scenarios aims to identify an optimal feature subset through an evolutionary search process that maximizes class separation while minimizing the dimensionality. Through comprehensive experimental studies conducted on diverse datasets, the results show that the proposed approach outperforms recently proposed evolutionary information-theoretic, rough set-based and state-of-the-art feature selection approaches in both scenarios. Notably, this study is the first to integrate an NCA-based strategy into an evolutionary feature selection approach.