development of traffic volume forecasting using multiple regression analysis and artificial neural network

development of traffic volume forecasting using multiple regression analysis and artificial neural network

the purpose of this study is to develop a model for traffic volume forecasting of the road network in anamorava region. the description of the current traffic volumes is enabled using ptv visum software, which is used as an input data gained through manual and automatic counting of vehicles and interviewing traffic participants. in order to develop the forecasting model, there has been the necessity to establish a data set relying on time series which enables interface between demographic, socio-economic variables and traffic volumes. at the beginning models have been developed by mlr and ann methods using original data on variables. in order to eliminate high correlation between variables appeared by individual models, pca method, which transforms variables to principal components (pcs), has been employed. these pcs are used as input in order to develop combined models pca-mlr and pca-rbf in which the minimization of errors in traffic volumes forecasting is significantly confirmed. the obtained results are compared to performance indicators such r², mae, mse and mape and the outcome of this undertaking is that the model pca-rbf provides minor errors in forecasting.