A Classification Model for Imbalanced Medical Data based on PCA and Farther Distance based Synthetic Minority Oversampling Technique

Abstract

—Medical data are extensively used in the diagnosis of human health. So it has played a vital role for physicians as well as in medical engineering. Accordingly, many types of research are going on related to this to have a better prediction of the diseases or to improve the diagnosis quality. However, most of the researchers work on either dimensionality space or imbalanced data. Due to this, sometimes one may not have the accurate predictions or classifications of the malignant diseases as both the factors are equally important. So it still needs an improvement or more work required to address these biomedical challenges by combing both the factors. As such this paper proposes a new and efficient combined algorithm based on FD_SMOTE (Farther Distance Based on Synthetic Minority Oversampling Techniques) and Principle Component Analysis (PCA), which successfully reduces the high dimensionality and balances the minority class. Finally, the present algorithm has been investigated on biomedical data and it gives the desired results in terms of dimensionality and data balancing. Here, In this paper, the quality of dimensionality reduction and balanced data has been evaluated using assessment metrics like co-variance, Accuracy (ACC) and Area Under the Curve (AUC). It has been observed from the numerical results that the performance of the algorithm achieved the best accuracy with metrics of ACC and AUC.