Novel Machine Learning Techniques for Diabetes Prediction

Diabetes Mellitus is a dangerous metabolic disease nowadays, that raises levels of blood glucose which over time leads to serious damage to body organs. It doesn’t have any permanent cure so early detection is very much required. Diabetes also invites lots of other diseases like heart attack, brain stock, heart failure, etc. Machine Learning is widely used in this field for early detection. In the past, it has been successfully applied to various domains such as computer vision, computer graphics, natural language processing, speech recognition, computer networks and intelligent control, and also healthcare. Machine Learning along with the internet of things helps to improve the quality of human lives by automating some basic tasks. It can monitor individuals by using applications, and sensors attached to the body. There are various machine learning algorithms that have been implemented for diabetes prediction. In this paper, we are going to discuss the methodologies of diabetes prediction using different machine learning algorithms, and we have proposed a novel algorithm based on 2 blocks with a minimum of 13 layers with better accuracy. It will provide an effective way to predict diabetes.