Feature Selection Method Based on Honeybee-SMOTE for Medical Data Classification

Bio-Medical data analysis has an important role in clinical practices. Usually, bio-medical have complex issues like skeweedness, redundant and irrelevant attributes etc.. Several unrelated features frequently degrade the accuracy of classifier while using with imbalanced datasets. The selection becomes critical this situation. key goal feature is to establish a subspace that maintains even as reducing excessive computational learning cost casting off noise. Appropriate approaches are highly dependent on their ability match issue context uncover fundamental patterns within data. This study’s main construct disease detection model uses hybrid feature-selection strategy based Honeybee-SMOTE classification c4.5 algorithm. empirical results suggested methodology's superiority over competing methods regarding parameter, precision-parameter, recall-parameter, f1-score parameter G-Mean parameter. statistical collected findings demonstrates method outperforms competitive existing state-of-the-art algorithms.