Modeling and Simulation of Road Traffic Noise Using Artificial Neural Network and Regression

The effect of traffic composition on the noise pollution has been investigated in a large city, where the population is over 2 millions. Noise measurements and vehicle counts were performed at three points of the city for a period of 12 hours. Two models of artificial neural network and regression were applied to predict in-city road traffic noise pollution. The MATLAB and DATAFIT softwares were used for simulation. The predicted results of noise level were compared with the measured noise levels in three stations. The values of normalized bias, standard squared error, mean-squared error, root-mean-squared error, and squared correlation coefficient calculated for each model showed that the results of two models are suitable, and the predictions of artificial neural network are closer to experimental data.