Prediction of diabetes and reduction of type ii error using ensemble learning

Abstract

Machine learning techniques are used in applications as a routine strategy for analysing the vast amount of available data and extracting relevant knowledge and information to support the main decision-making processes. Diabetes is a common, and fatal syndrome, that affects people all over the world. It is characterised by hyperglycemia brought on by irregularities in insulin secretion, which in turn would cause the glucose level to rise irregularly. Diabetes has significantly worsened in recent years, particularly in emerging nations like India. Machine Learning Analytics plays an significant role in healthcare industries. Healthcare industries have large volume databases. Using machine learning analytics one can study huge datasets and find hidden information, hidden patterns to discover knowledge from the data and predict outcomes accordingly. In existing method, the classification and prediction accuracy is not so high.This is primarily caused by the inconsistencies in people’s eating and living routines. As a result, research into the early detection and classification of this fatal disease has increased during the past ten years.There are many clustering and classification approaches that can be used to visualise temporal data in order to spot trends and manage diabetes. This proposed model is based on classifier comparison of various machine learning approaches and reducing the Type II error.