As a subsystem of society,higher education is an inevitable choice to meet the political and economic development of a country.Research of the higher education evaluation system is of great significance to the develop...As a subsystem of society,higher education is an inevitable choice to meet the political and economic development of a country.Research of the higher education evaluation system is of great significance to the development of society.In this paper,a backpropagation(BP)neural network model is established to predict the future development scale of higher education.The analytic hierarchy process(AHP)method and partial least squares regression(PLS)structural equations were used to verify the scientificity and feasibility of the model.BP neural network has strong nonlinear mapping capabilities,and it is capable of the prognostics.It performed well on issues with more complicated internal mechanisms.Through experimental simulations,it is found that the BP neural network model has a good fit when making predictions and the relative error is less than 3%,which shows that the prediction results obtained with this model have high reliability.展开更多
文摘As a subsystem of society,higher education is an inevitable choice to meet the political and economic development of a country.Research of the higher education evaluation system is of great significance to the development of society.In this paper,a backpropagation(BP)neural network model is established to predict the future development scale of higher education.The analytic hierarchy process(AHP)method and partial least squares regression(PLS)structural equations were used to verify the scientificity and feasibility of the model.BP neural network has strong nonlinear mapping capabilities,and it is capable of the prognostics.It performed well on issues with more complicated internal mechanisms.Through experimental simulations,it is found that the BP neural network model has a good fit when making predictions and the relative error is less than 3%,which shows that the prediction results obtained with this model have high reliability.
