Fuzzy Information Decomposition Incorporated and Weighted Relief-F Feature Selection: When Imbalanced Data Meet Incompletion

Abstract Data classification is an important computer task in data analysis, which suffers seriouslyunknown features, imbalanced class, and incomplete data. However, despite their vital yet practical significance, few results have been made on such three distinct issues. To address this problem, we propose a novel feature selection method for the data subject to incomplete data and imbalanced class, namely, improved fuzzy information decomposition (IFID) incorporated and weighted Relief-F (WRelief-F) feature selection. The main idea of the proposed feature selection method is three-fold. 1) The proposed IFID algorithm can deal with the imbalanced class and incomplete data at the same time. 2) In IFID, a new membership function is provided to reflect the influence of the observed data on the missing values appropriately. Based on this establishment, a more delicate information decomposition is adopted to make a better recovery than the traditional FID. 3) After using IFID, WRelief-F is put forward to take the relationship of the target instance to inter-class instances and the intra-class instances into consideration in a proper manner. Finally, experiments on the seven public data sets are utilized to show the effectiveness and universal applicability of the proposed feature selection algorithm.