基于GRA-TOOPSO-LSSVM的港口吞吐量预测

发布时间：2018-04-11 06:37

本文选题：最小二乘支持向量机(LSSVM) + 灰色关联分析(GRA)　；参考：《上海海事大学学报》2017年01期

【摘要】：为对港口吞吐量进行科学预测,在最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)基础上,引入灰色关联分析(Grey Relational Analysis,GRA)和二阶振荡粒子群优化(Two-Order Oscillating Particle Swarm Optimization,TOOPSO),提出一种新的GRA-TOOPSO-LSSVM算法预测港口吞吐量.采用GRA法筛选出对上海港吞吐量有重大影响的因素,并将其作为LSSVM的输入变量;采用TOOPSO法对LSSVM的参数进行寻优;运用LSSVM非线性映射的优势对上海港吞吐量进行预测.在上海港吞吐量实证研究的过程中,GRA-TOOPSO-LSSVM算法与TOOPSOLSSVM和基于交叉验证的LSSVM算法进行对比分析.研究结果表明,GRA-TOOPSO-LSSVM算法具有更好的预测精度和收敛速度,为港口吞吐量预测的研究提供了一种新的方法.
[Abstract]:In order to predict port throughput scientifically, a new GRA-TOOPSO-LSSVM algorithm is proposed to predict port throughput based on least squares support vector machine (Least Squares Support Vector Machine), grey Relational analysis (GRA) and second-order oscillating particle swarm optimization (OPSO).The GRA method is used to screen out the factors that have great influence on the throughput of Shanghai Port, which is regarded as the input variable of LSSVM; the TOOPSO method is used to optimize the parameters of LSSVM; and the advantage of LSSVM nonlinear mapping is used to predict the throughput of Shanghai Port.The GRA-TOOPSO-LSSVM algorithm is compared with TOOPSOLSSVM and LSSVM algorithm based on cross-validation in the process of empirical study on throughput of Shanghai Port.The results show that the GRA-TOOPSO-LSSVM algorithm has better prediction accuracy and convergence speed, and provides a new method for port throughput prediction.
【作者单位】：上海海事大学物流科学与工程研究院;
【基金】：交通运输部建设科技项目(2015328810160) 上海市科学技术委员会重大项目(15DZ1100900,14DZ2280200)
【分类号】：U652.14

【参考文献】