Artificial RBF Neural Network for Big Data Analysis and New Cases Prediction

Abstract

AI-based treatments have shown promise in a variety of fields, particularly those directly connected to human health. Some AI processors are used to categorize and distinguish groupings and patterns, while others are used to forecast future values based on data from previous study and the environment in which that data was employed. An artificial neural network that employs radial basis functions as activation functions is known as a radial basis function network. The radial basis functions input and the neural parameters are combined linearly to produce the network output. There are several applications for radial-based functional networks, such as function approximation, classification, time series prediction, and system control. In this paper, the RBF network will be used in two phases: the data training phase, where the data is trained with the inputs and outputs to obtain new values for the outputs and compare them with the original outputs, and the testing phase, where only the inputs are entered without the outputs and the outputs are evaluated using the RMSE calculation, where it reached a performance of RMSE of 0.018. In the training phase of utilizing the system, the mistake rate was 0.04 and the success rate was 96%; in the testing phase, the error rate was 0.05 and the success rate was 95%.