基于Markov-BP神经网络的武汉市物流需求预测

Forecasting of Logistics Demand in Wuhan Based on Markov-BP Neural Network

物流需求预测是城市发展规划中的重要组成部分,为了能够科学地预测出武汉市的物流需求,选择武汉市地区生产总值、社会商品零售总值及货物进出口作为输入指标,将货物运输量作为输出指标,利用BP神经网络模型进行预测。在此基础上,借助马尔可夫链(Markov)对误差值进行修正,使平均相对误差从7.3%下降至1.9%。结果表明,与单一的BP神经网络模型以及其他神经网络组合方法相比,Markov-BP神经网络模型的预测精度更高,使用Markov-BP神经网络模型,对武汉市未来物流需求预测具有一定的参考价值。

Logistics demand forecasting is an important part of urban development planning.In this paper,in order to scientifically predict the logistics demand in Wuhan City,with the regional GDP,total social commodity retail value and goods import and export of Wuhan as input indicators,and cargo transportation volume as output indicator,we used the BP neural network model to predict the logistics demand in Wuhan.On this basis,we corrected the error value with the help of the Markov chain,reducing the average relative error from 7.3%to 1.9%.The result showed that compared with the single BP neural network model and other neural network combination methods,the Markov-BP neural network model has higher prediction accuracy.