Paper Title
A Case Study on Class Imbalance Diabetes Data using the Proposed Classification Algorithms

Abstract
Diabetes is one of the diseases which are leading to high percentage of death rate. The knowledge discovery of diabetes data set comes under a challenging problem of class imbalance learning. In class imbalance learning the high ratio of instances in one class predominantly outnumber the instances in the other class. The prediction model build using the class imbalance data set is not sufficient for efficient knowledge discovery. In this paper, we conducted a case study on the recently proposed algorithm for efficient knowledge discovery from the class imbalance diabetes dataset. The experimental results suggest that the proposed approach is better than the compared approach in terms of accuracy, AUC and RMS Error. Keywords - Data mining, classification, Imbalanced data, diabetes dataset, OSID3, USRF, IELT.