Traffic Flow Forecasting Method Based on Elman Neural Network

Traffic flow guidance system (TFGS) plays an important role in intelligent transportation system (ITS). The prediction of traffic flow is the core issue of TFGS. Hence, how to predict traffic flow amount online is the key to TFGS. Based on the properties of traffic flows, this paper analyzes the causes resulting in error ones during collecting transportation data, and proposes the methods of handling these errors. Furthermore, the Elman neural network is utilized to model the forecast of the traffic flow for ITS. The above system is built by using C# and Matlab, and the Elman neural network is used to forecast the traffic flow. Moreover, the predicted results are intuitively shown by using the chart. The application results show that the proposed method is effective for the prediction of traffic flow and the prediction accuracy can meet the actual requirements.