Special Investigation of Variable Star Delta Cephei via Neural Network

Abstract

We investigated that the brightness magnitude of the Del Cephei had been adapted to three different training values and each training had four different hidden layers in the back-propagation neural network (BPNN) models. The best forecasting mean through different approaches in the BPNN model was obtained at 15% training with four hidden layers. However, the difference in forecasting accuracies of the different levels was not statistically significant.