Handling Missing Values Based on Similarity Classifiers and Fuzzy Entropy Measures

Handling missing values (MVs) and feature selection (FS) are vital preprocessing tasks for many pattern recognition, data mining, machine learning (ML) applications, involving classification regression problems. The existence of MVs in badly affects making decisions. Hence, have to be taken into consideration during as a critical problem. To this end, the authors proposed new algorithm manipulating using FS. Bayesian ridge (BRR) is most beneficial type regression. BRR estimates probabilistic model dubbed cumulative with similarity Luca’s fuzzy entropy measure (CBRSL). CBRSL reveals how FS used selecting candidate holding aids prediction within selected Ridge technique. can utilized manipulate other features order; filled incorporated equation order predict next incomplete feature. An experimental analysis was conducted on four datasets generated from three missingness mechanisms compare state-of-the-art practical imputation methods. performance measured terms R2 score (determination coefficient), RMSE (root mean square error), MAE (mean absolute error). Experimental results indicate that accuracy execution times differ depending amount MVs, dataset’s size, mechanism missingness. In addition, show any competitive against compared