Urban Short-Term Traffic Forecasting Based on Grey Neural Network Combined Model: Macao Experience

The paper presents three kinds of grey neural network combined model for short-term prediction of urban traffic parameters, which are parallel grey neural network, series grey neural network, and inlaid grey neural network. They are employed to forecast a real vehicle speed in Barbosa road of Macao with satisfied precision. The experiment shows that the above three kinds of mode are feasible and effective in comparison with single model GM(1,1) and neural network. And actual traffic speed varies smoothly or not will influence significantly the accuracy for forecasting.