Prediction of Logistics Demand via Least Square Method and Multi-Layer Perceptron

作     者：魏乐琴 张安国 WEI Leqin;ZHANG Anguo

作者机构：School of Humanities and TeachersEducationWuyi UniversityWuyishan 354300China College of Physics and Information EngineeringFuzhou UniversityFuzhou 350108China 

出 版 物：《Journal of Donghua University(English Edition)》 (东华大学学报（英文版）)

年 卷 期：2020年第37卷第6期

页      面：526-533页

学科分类：0817[工学-化学工程与技术] 08[工学] 0807[工学-动力工程及工程热物理] 082303[工学-交通运输规划与管理] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0811[工学-控制科学与工程] 082302[工学-交通信息工程及控制] 0823[工学-交通运输工程] 

基　　金：Educational Research Project of Social Science for Young and Middle Aged Teachers in Fujian Province,China(No.JAS19371) Social Science Research Project of Education Department of Fujian Province,China(No.JAS160571) Key Project of Education and Teaching Reform of Undergraduate Universities in Fujian Province,China(No.FBJG20190130) 

主　　题：logistics demand least square method(LSM) multi-layer perceptron(MLP) prediction strategic planning 

摘      要：To implement the prediction of the logistics demand capacity of a certain region,a comprehensive index system is constructed,which is composed of freight volume and other eight relevant economic indices,such as gross domestic product(GDP),consumer price index(CPI),total import and export volume,port s cargo throughput,total retail sales of consumer goods,total fixed asset investment,highway mileage,and resident population,to form the foundation for the model *** on the least square method(LSM)to fit the parameters,the study obtains an accurate mathematical model and predicts the changes of each index in the next five *** artificial intelligence software,the research establishes the logistics demand model of multi-layer perceptron(MLP)neural network,makes an empirical analysis on the logistics demand of Quanzhou City,and predicts its logistics demand in the next five years,which provides some references for formulating logistics planning and development strategy.