Predictive Analytics Using Deep Residual Neural Network Model for The Prediction of Breast Cancer Disease

Utilizing Residual Neural Networks (ResNets) that are fed data received from the Internet of Things (IoT), the objective of this study is to develop a method for detecting breast cancer that can be implemented in the future. The purpose of this research is to successfully address the problem by implementing a system that aims to combat newly emerging illnesses in their early phases. This research takes on the task of effectively addressing the problem. In addition to the fatalities and cures that have taken place, the system maintains a record of the confirmed and reported cases daily. To ensure that everyone would be able to notice the terrible signs of the fatal illness as promptly as possible, the goal was to give everyone the opportunity to do so. To estimate the root, mean square error (RMSE) values of a variety of cases, including those who were infected, those that were treated, and those that were deceased, an ensemble of recurrent neural networks (RNN) and generalized root mean square (GRU) was utilized. When it comes to forecasting the presence of breast cancer, the findings of the simulation indicate that the ResNets for classification that was suggested in the simulation performs substantially better than earlier deep learning models.