CAJ | 학술논문

根据某地区1996年-2007年连续12年私家车的保有量,提出了一种改进的BP神经网络的私家车保有量的预测模型,以人均国内生产总值、公交车营运总里程、居民人均可支配收入等10个指标作为网络的输入因子,以私家车保有量作为输出因子,利用1996年至2007年的数据进行训练和检验,得到了预测仿真的结果,预测值与实际值的误差比传统的神经网络预测的误差更小,达到了预期的目的.
근거모지구1996년-2007년련속12년사가차적보유량,제출료일충개진적BP신경망락적사가차보유량적예측모형,이인균국내생산총치、공교차영운총리정、거민인균가지배수입등10개지표작위망락적수입인자,이사가차보유량작위수출인자,이용1996년지2007년적수거진행훈련화검험,득도료예측방진적결과,예측치여실제치적오차비전통적신경망락예측적오차경소,체도료예기적목적.
Based on total number of private cars in some areas for each year in 1996-2007,a method of predictive model for the forecast of total number of private cars based on the improvement BP neural network is given,which take GDP,total public transportation mileage,residents' per capita disposable income as the input variables of the network,take the total number of private cars as the output factor,using the data of 1996-2007 for training and testing,which has forecast the results of the simulation,the error between the predictive value and the actual value is less than the tradition BP neural network,reaching the purpose which is expected and show the effectiveness of the method.