A Combination Predicted Model of Short Term Traffic Flow

In order to increase the precision of forecast, this paper proposes a combination forecasting model in short term traffic flow based on wavelet neural network. The model consists of the following stages: first, the relevant forecasting variable to the traffic flow is selected by use data mining technology such as the genetic algorithm; second, training pattern of wavelet neural network which is similar to the forecast term is carried out by using data mining technology; finally the wavelet neural network is used to carry on forecasting the traffic flow. Through forecasting traffic flow at Xinhua Street in Huhehot, the result shows that this model has a higher precision and surpasses gray model and the BP artificial neural network model, which provides a new reliable and effective way of forecasting short term traffic flow of nodes in urban road network