Abstract:
Urban living in large modern cities exerts considerable adverse effects on health and thus increases the risk of contracting several chronic kidney diseases (CKD). The prediction of CKDs has become a major task in urbanized countries. The primary objective of this work is to introduce and develop predictive analytics for predicting CKDs. However, prediction of huge samples is becoming increasingly difficult. Meanwhile, MapReduce provides a feasible framework for programming predictive algorithms with map and reduce functions. The relatively simple programming interface helps solve problems in the scalability and efficiency of predictive learning algorithms. In the proposed work, the iterative weighted map reduce framework is introduced for the effective management of large dataset samples. A binary classification problem is formulated using ensemble nonlinear support vector machines and random forests. Thus, instead of using the normal linear combination of kernel activations, the proposed work creates nonlinear combinations of kernel activations in prototype examples. Furthermore, different descriptors are combined in an ensemble of deep support vector machines, where the product rule is used to combine probability estimates of different classifiers. Performance is evaluated in terms of the prediction accuracy and interpretability of the model and the results.
