Data smoothing numerical methods and their applications in unsupervised learning for prediction of diabetes in patients

Abstract

Machine Learning in its fullest can provide much more accurate and enhanced analysis for medical diagnosis. In this paper we are trying to portray how the data related to diabetes can be used to predict if a person has diabetes or not. In more specific way this paper will explore the utilization of numerical methods smoothing with unsupervised learning to predict the early signs of disease like diabetes and rest.