ENN Ensemble based Neural Network method for Diabetes Classification

Abstract

Diabetes is considered as one of the most chronic disease which has serious impact on human health and leading cause of mortality worldwide. The early prediction of diabetes can help clinicians to provide a better diagnosis to the patients. Recently, computed aided diagnosis systems have gained attention due to significant growth in data mining, and machine learning. Several approaches are present based on the machine learning techniques but due to poor classification performance and computational complexity, it becomes difficult to utilize for real-time applications. Ensemble classification approaches have reported a noteworthy improvement in diabetes classification but desired accuracy is still a challenging task. Hence, in this work we introduce a combined hybrid approach called as ENN-Ensemble based neural network approach for diabetes classification. In this approach, a feature selection process is presented using neighboring search technique; the selected features are processed through the feature ranking model to generate the efficient feature subset for better classification accuracy. Finally, these features are learned and classified using neural network classifier. The experimental study shows that the proposed approach achieves better accuracy when compared with the existing techniques.

The Prediction of Diabetes

“…Using ECG data and cardiac rate information based on deep learning methods is described in (Ignatius et al, 2019), while Greenwood et al (2015) address the benefits of health monitoring systems (Greenwood et al, 2015). Classification techniques based on machine learning algorithms for diabetes prediction are employed in Kumari et al (2020). A method for classification of the disease is given in the paper, while a comparative analysis of the accuracy of these methods is provided.…”