本文選題：最小二乘支持向量機(jī)(LSSVM) + 灰色關(guān)聯(lián)分析(GRA)��； 參考：《上海海事大學(xué)學(xué)報(bào)》2017年01期

【摘要】：為對(duì)港口吞吐量進(jìn)行科學(xué)預(yù)測(cè),在最小二乘支持向量機(jī)(Least Squares Support Vector Machine,LSSVM)基礎(chǔ)上,引入灰色關(guān)聯(lián)分析(Grey Relational Analysis,GRA)和二階振蕩粒子群優(yōu)化(Two-Order Oscillating Particle Swarm Optimization,TOOPSO),提出一種新的GRA-TOOPSO-LSSVM算法預(yù)測(cè)港口吞吐量.采用GRA法篩選出對(duì)上海港吞吐量有重大影響的因素,并將其作為L(zhǎng)SSVM的輸入變量;采用TOOPSO法對(duì)LSSVM的參數(shù)進(jìn)行尋優(yōu);運(yùn)用LSSVM非線(xiàn)性映射的優(yōu)勢(shì)對(duì)上海港吞吐量進(jìn)行預(yù)測(cè).在上海港吞吐量實(shí)證研究的過(guò)程中,GRA-TOOPSO-LSSVM算法與TOOPSOLSSVM和基于交叉驗(yàn)證的LSSVM算法進(jìn)行對(duì)比分析.研究結(jié)果表明,GRA-TOOPSO-LSSVM算法具有更好的預(yù)測(cè)精度和收斂速度,為港口吞吐量預(yù)測(cè)的研究提供了一種新的方法.
[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.
【作者單位】： 上海海事大學(xué)物流科學(xué)與工程研究院;
【基金】：交通運(yùn)輸部建設(shè)科技項(xiàng)目(2015328810160) 上海市科學(xué)技術(shù)委員會(huì)重大項(xiàng)目(15DZ1100900,14DZ2280200)
【分類(lèi)號(hào)】：U652.14

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 黃勤;趙海茹;陳玲;;基于改進(jìn)PSO的組合預(yù)測(cè)模型研究[J];計(jì)算機(jī)工程與應(yīng)用;2015年14期

2 鐘映z，

本文編號(hào)：1734839