Application of Genetic Algorithm in Developing of Traffic Noise Prediction Model

Abstract

In order to control noise levels it is necessary to have a suitable calculation method for traffic noise prediction. Since 1950s many mathematical models for estimation of traffic noise pollution have been developed, and most of avaliable models found in literature are based on regression analysis. This paper presents the application of genetic algorithm in development of simple mathematical model for prediction of equivalent A-weighted level of road traffic noise in urban areas of the city of Kraljevo. Predictions of developed mathematical model are compared to experimental data colected by traffic noise measuring, as well as to predictions of commonly used traffic noise models, and obtained results of statistical analysis of differences between measured and calculated noise levels are shown in this paper.