A Comparison of Two-Stage Classifier Algorithm with Ensemble Techniques On Detection of Diabetic Retinopathy
Ali Tariq Nagi, Mazhar Javed Awan, Rabia Javed, Noor Ayesha
Abstract
The Diabetic retinopathy is disease of the human eye that causes retinal damage in diabetic patients. It further leads to the blindness. The machine learning techniques plays an important rule to predict the early diabetic retinopathy which avoided from the intensive labor. In this paper we used the novel technique, the Two Stage Classifier, an ensemble technique which combines various machine learning algorithms for classification. In the subject paper, the classifier is applied to predict Diabetic retinopathy (DR), a disease of the human eye that causes retinal damage in diabetic patients and ultimately lead to complete blindness. The problem lies in the fact that it is time consuming to detect this disease but an early detection of the disease is essential to avoid complete blindness. We apply machine learning algorithms to determine the existence of DR and compare the accuracies of the applied techniques. The Two Stage Classifier, turns out to be better not only in terms of parallelism but also in terms of accuracy.