1. 武汉商学院 商贸物流学院, 武汉 430056; 2. 武汉理工大学 物流工程学院, 武汉 430063; 3. 武汉理工大学 智能交通系统研究中心， 武汉 430063
出版日期:2019-05-28发布日期:2019-05-28通讯作者:吴青，女，教授，博士生导师， E-mail: wq@whut.edu.cn.作者简介:陈琛(1984-)，女，湖北省武汉市人，博士生，主要研究方向为物流系统优化.基金资助:交通运输部建设科技项目（2015328811180）Short-Term Shipping Freight Volume Prediction Based on Temporal-Spatial Features
CHEN Chen，WU Qing，GAO Song1. School of Logistic and Trade, Wuhan Business University, Wuhan 430056, China; 2. School of Logistic Engineering, Wuhan University of Technology, Wuhan 430063, China； 3. Intelligent Transport System Research Center, Wuhan University of Technology, Wuhan 430063, China
Online:2019-05-28Published:2019-05-28摘要/Abstract
摘要： 考虑货运网络港口间空间关联能提高短期预测精度，但是不同于公路网络中通过交叉路口形成简单明确的上下游空间关系，超高维的水运货运空间关系数据难以直接利用，为此，基于频繁港口和神经网络(FR-NN)构建考虑时空因素的水路货运量预测模型.该模型基于频繁模式的思想挖掘出目标港口在货运空间网络中的频繁港口，利用频繁港口提取货运网络的主要空间关系，用低维数据保留高维网络主要空间特征，再利用神经网络拟合频繁港口与目标港口货运量间的时空关系.实例分析表明，考虑时空关系有助于提高预测精度，模型能提高不同粒度的短期货运量预测精度，尤其是能够预测采用时间序列方法不理想的周、日货运量.
关键词: 货运量, 短期预测, 时空因素, 频繁模式, 神经网络
Abstract: Considering spatial correlation in shipping network is an effective method to improve veracity of the short-term freight volume prediction. But the shipping network is much more complicated than the highway transportation. The high-dimensional data of shipping network cannot be used effectively. A short-term freight volume prediction model FR-NN which is based on frequent pattern mining and neural network is constructed. Frequent ports in cargo network are found out according to idea of frequent pattern mining, and they represent the main spatial relations in network. Neural network is used for fitting statistical relationships among ports. Example analysis shows that the model can improve veracity of the short-term freight volume prediction in different time particle sizes. Furthermore, the model can forecast to the weeks and days freight volume, that the time series method is not ideal for the prediction results.
Key words: freight volume, short-term prediction, temporal-spatial features, frequent pattern, neural network
PDF全文下载地址:
点我下载PDF
