Enhancing Big Data Feature Selection Using a Hybrid Correlation-Based Feature Selection

This study proposes an alternate data extraction method that combines three well-known feature selection methods for handling large and problematic datasets: the correlation-based (CFS), best first search (BFS), dominance-based rough set approach (DRSA) methods. aims to enhance classifier’s performance in decision analysis by eliminating uncorrelated inconsistent values. The proposed method, named CFS-DRSA, comprises several phases executed sequence, with main incorporating two crucial tasks. Data reduction is first, which implements a CFS BFS algorithm. Secondly, process applies DRSA generate optimized dataset. Therefore, this solve computational time complexity increase classification accuracy. Several datasets various characteristics volumes were used experimental evaluate method’s credibility. was validated using standard evaluation measures benchmarked other established such as deep learning (DL). Overall, work proved it could assist classifier returning significant result, accuracy rate of 82.1% neural network (NN) classifier, compared support vector machine (SVM), returned 66.5% 49.96% DL. one-way variance (ANOVA) statistical result indicates alternative tool those difficulties acquiring expensive big tools who are new field.