欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
铁路货运量与其影响因素之间关系复杂,单一核函数支持向量机（SVM）难以进行准确描述,而且各因素对铁路货运量的影响程度具有差异性,若忽略这种差异性,将难以获得理想的铁路货运量预测结果.为此,本文提出一种基于灰色关联分析（GRA）与混合核函数支持向量机（SVM-mixed）的铁路货运量预测方法.该方法采用灰色关联分析确定各影响因素的权重,再将赋予权重的影响因素作为输入变量,构建多项式核函数与径向基核函数线性组合的SVM-mixed预测模型.针对SVM-mixed参数难以确定问题,采用果蝇优化算法（FOA）选择SVM-mixed最优参数.基于中国铁路货运量的实例分析表明,该方法可有效提高铁路货运量的预测精度,为准确预测铁路货运量提供了一种新途径.
英文摘要：
The relationship between railway freight volumes and its influence factors is complex. It is difficult for support vector machines with single kernel function（SVM） to describe the complex relationship.At the same time, the impact of the factors on railway freight volumes is different. If we ignored this difference, it would be difficult to obtain the desired predicting results of railway freight volumes. To solve these problems, this paper proposes a novel method for predicting railway freight volumes based on grey relational analysis（GRA） and SVM with mixed kernel function（SVM- mixed）. The weights of influence factors of railway freight volume are determined by GRA. Being as the input variables, the influence factors with weights are used to construct SVM- mixed whose kernel function combined polynomial kernel with radial basis kernel. Fruit fly optimization algorithm（FOA） is adopted to adjust the parameters in SVM-mixed to solve the problem of parameters selection of SVM-mixed. The example analysis of China railway freight volumes shows that the proposed method can effectively enhance accuracy in forecasting railway freight volumes, which provides a new approach for the accurate forecasting of railway freight volumes.
同期刊论文项目
同项目期刊论文
期刊信息
位置：