基于Markov-BP神经网络的武汉市物流需求预测
首发时间:2022-11-28
摘要: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神经网络模型预测, 在此基础上借助马尔科夫链(Markov)对误差值进行修正, 使平均相对误差从7.3%下降至2.1%. 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.
关键词: 物流需求预测; BP神经网络; 马尔科夫链; MATLAB
For information in English, please click here
Forecast of urban logistics demand based on Markov-BP neural network
Abstract: Logistics demand forecast is an important part of urban development planning. In order to forecast the logistics demand of Wuhan scientifically, the regional GDP, the retail value of social goods and the import and export of goods in Wuhan are selected as input indicators, and the cargo transportation volume is used as output indicators. In this foundation, the BP neural network model is used to forecast, and the error value is corrected by Markov chain, so that the average relative error is reduced from 7.3% to 2.1%. The results show that the prediction accuracy of Markov-BP neural network model is higher than that of single BP neural network model and other neural network combination methods. Using Markov-BP neural network model has certain reference value for forecasting the future logistics demand of Wuhan.
Keywords: orecast of logistics demand BP neural network Markov MATLAB
引用
No.****
动态公开评议
共计0人参与
勘误表
基于Markov-BP神经网络的武汉市物流需求预测
评论
全部评论0/1000