Short-term traffic flow forecasting based on multi-dimensional parameters

The traffic condition of urban roads is affected by multi-dimensional factors, such as time and space. To accurately predict the short-term traffic condition of urban roads, this paper analyzes these multidimensional temporal and spatial parameters and develops the short-term road traffic prediction models of different dimensions based on the support vector machine (SVM). Then, the GPS data of taxis in Guiyang is used to test the prediction accuracy of these proposed models and to analyze the impact of each temporal and spatial parameter on traffic condition. The results show higher prediction accuracy of the SVM model based on previous traffic flow of target segment and the traffic condition of downstream segment. To further analyze its performance, the results are compared with those of linear regression and ARMA models. The proposed SVM model is proven to be an effective tool for forecasting short-term traffic condition of urban roads.