Diabetes Data Classification Using Whale Optimization Algorithm and Backpropagation Neural Network

Abstract

Diabetes also called as diabetes mellitus is a health issue which affects more people in a world. Diagnosis of diabetic problem depends on different parameters and requires experience or good algorithm to classify it optimally. Many researchers have found different classification algorithms to diagnose this health issue with promising results. In this paper, combinations of whale optimization algorithm and backpropagation neural network methodology are integrated to diagnose diabetes mellitus. This proposed method supports high convergence speed and improved accuracy. Due to this combination, local minima trapping problem which affects the quality of the solution is totally reduced. In the proposed methodology, Whale optimization technique develops new solutions in solution space and backpropagation algorithm finds the globally optimal solution. Experimental analysis compares the proposed methodology with other algorithms and finally concludes the proposed algorithm outperforms other methodologies.