Traffic flow forecasting based on ant colony neural network

As intelligent transportation systems (ITS) are implemented widely throughout the world, managers of transportation systems have access to large amounts of real-time status data. A variety of methods and techniques have been developed to forecast traffic flow. The traffic flow forecasting model based on neural network has been applied widely in ITS because of its high forecasting accuracy and self-learning ability. But the problems of neural network such as the difficult of designing optimal structure and weak global searching ability limit seriously its applications. So the traffic flow forecasting based on ant colony neural network is proposed. The ant colony algorithm, which has a powerful global searching ability, is applied to solve the problem of tuning both network structure and parameters of a feedforward neural network. First, the ant colony neural network algorithm is introduced in detail. Then, the presented approach is effectively applied to solve traffic flow forecasting. The simulation experiments show that the presented traffic flow forecasting based on ant colony neural network can simplify the structure of neural network greatly and improve the forecasting accuracy significantly.