Prediction of Noise Level for Industrial Zone using Bayesian Regularization Neural Network Training Algorithm

Abstract

Hidden layers are very useful to visualize the performance of neural network design mainly to deal with the complex problems where the accuracy and the time complexity are the main constraints. The process of deciding the number of hidden layers and number of neurons in each hidden layer is one of the prominent tasks in neural network architecture. In this study, we have proposed a method to determine the number of hidden neurons in hidden layer and compare it with the existing methods. Using the proposed method of obtaining the hidden neurons in hidden layer, we then applied Bayesian Regularization neural network training algorithm and obtained the accuracy measures. The study concluded that proposed method is better than the existing conventional methods in predicting the noise levels in Industrial zone of Lucknow, India.