基于改进支持向量机(SVM)模型的荆州港吞吐量预测

在编制港口总体规划过程中,港口吞吐量的预测对于提出规划方案至关重要,支持向量机(SVM)方法是港口吞吐量预测较为常见和有效的预测方法。针对港口吞吐量预测影响因素复杂的问题,以荆州港总体规划为实例,研究分析了影响港口吞吐量的主要指标因素。在采用SVM预测方法的基础上,运用遗传算法(GA)、网格搜索算法(GS)对SVM模型主要参数进行优化改进,GA-SVM和GS-SVM模型预测结果都是在支持向量机预测方法的基础上,采用遗传算法和GS方法对支持向量机模型的主要参数进行优化和改进,并用MSE和R2检验了遗传支持向量机和GS支持向量机模型的预测结果。改进后的SVM模型是在当前研究成果基础上提出的一种新港口吞吐量预测方法,可将该模型在港口总体规划工作中进行推广应用。

Port throughput forecast of Jingzhou Port based on improved SVM model

In the process of drawing up overall port planning,the prediction of port throughput is very important to put forward the planning scheme.Support vector machine (SVM) method is a common and effective prediction method for port throughput prediction.In view of the complexity of the influencing factors of the port throughput prediction,this paper takes the overall planning of Jingzhou Port as an example to study and analyze the main index factors affecting the port throughput.Based on SVM prediction method,GA and GS method are used to optimize and improve the main parameters of SVM model,and the results of the GA-SVM and GS-SVM model predictions are tested by the MSE and R2.The improved SVM model is a new port throughput prediction method based on the current research results,which can be applied in the overall port planning .