A Predictive Analysis of Heart Diseases and Diabetes Using Adaptive Modified Backpropagation

Abstract

An Artificial Neural Network (ANN) is a data preparing method that is motivated by the way organic sensory systems, for example, the mind, process data. ANN learns (i.e. logically enhance execution on) errands by thinking about illustrations, for the most part without assignment particular programming. Backpropagation is a method utilized as a part of neural networks to figure a value that is required in the computation of the weights to be utilized as a part of the system. In this project, neural network Backpropagation with adaptive learning rate is used to predict heart and diabetes diseases to the patients by the given parameters. The algorithm modifies the learning rate at each step based on the data and gives faster results when compared to the traditional algorithm. This is chosen to implement on Hear Diseases and Diabetic Disease dataset and results are compared. The model is trained with a set of training data and then that trained model is used to predict the testing data of patient disease. These predictions will give an idea of the type of disease and can be used to diagnose the patient.