Hybrid artificial fish particle swarm optimizer and kernel extreme learning machine for type II diabetes predictive Model

Abstract

According to WHO (World Health Organization), Diabetes is the world s second populated disease resulted in the deaths of 1.5 million people in 2019. Diabetes is a metabolic disorder, which affects how our bodies use digested food for energy and growth. A healthy diet, regular exercise, routine screening, and monitoring the disorders will also cure diabetes and postpone or prevent the effects of the disease. There are three common ty0pes of diabetes such as Type-I, Type-II, and Gestational diabetes (diabetes during pregnancy). newlineType-II is the most common form of diabetes. It is also called Adult-onset diabetes. The accurate prediction of Type-II diabetes is essential for lowering the risk of complications like stroke, blindness, cardiac failure, renal failure, diabetic neuropathy, diabetic retinopathy, and cerebrovascular issues. In this context, Machine Learning techniques are considered important and reliable in the prediction of diabetes into two classes such as diabetic and non-diabetic persons. Several studies have recently been suggested to predict the presence of diabetes. As a result, the proposed KELM-HAFPSO stacking approach has been developed to predict and assess the risk factors associated with type-II diabetes. newline