| The urban transportation problem is the important and strategic problem that national economy, social development and ecological environment of China and all over the world are faced with currently. The public transportation system is one of the subsystems of the urban transportation system. It not only supports the normal operation of the city function, but also plays a overall and precursory role in the social economy development. The urban transportation planning is developing in the direction of the public transportation system, and gives priority of the development of the public traffic, which have become the consensus of the whole world.The urban public traffic demand forecast is one of the key technologies of the urban public transportation planning. Its main function is to predict traffic flow condition in future years by analyzing present social economical activity and traffic activity in traffic zones. The paper begins with the urban public traffic demand forecast. After analyzed and studied advantages, disadvantages, different application condition of regular forecast methods and disadvantages of "four-step" forecast models, gray system theory, BP artificial neural network and multiple linear regression are analyzed in detail and are applied to urban public traffic demand forecast. Research results show that application of these methods within a given period is feasible and effective, but they still have some disadvantages and it is relatively difficult to guarantee the precision. The paper comes up with combination forecasting model and elaborates basic idea of combination forecasting method and application to urban public traffic demand forecast. Because combination forecasting model can synthetically use the information that is provided by every single model, the shortage of every single model can be avoided. Generally speaking, the result of combination forecasting model is balanced, and the precision of it is better than that of every single model.
|
PDF Full Text Request