文献类型：会议论文

英文题名：Modeling and Forecasting of Urban Logistics Demand Based on Support Vector Machine

作者：Gao, Meijuan[1];Feng, Qian[2]

第一作者：高美娟

通讯作者：Gao, MJ[1]

机构：[1]Beijing Union Univ, Dept Automat Control, Beijing, Peoples R China;[2]Beijing Jiaotong Univ, Sch Econ & Management, Beijing, Peoples R China

第一机构：北京联合大学城市轨道交通与物流学院

通讯机构：[1]corresponding author), Beijing Union Univ, Dept Automat Control, Beijing, Peoples R China.|[1141751]北京联合大学城市轨道交通与物流学院;[11417]北京联合大学;

会议论文集：2nd International Workshop on Knowledge Discovery Data Mining

会议日期：JAN 23-25, 2009

会议地点：Moscow, RUSSIA

语种：英文

外文关键词：urban logistics; demand; modeling and forecasting; support vector machine

摘要：Because logistics system was an uncertain, nonlinear, dynamic and complicated system, it was difficult to describe it by traditional methods. The support vector machine (SVM) has the ability of strong nonlinear function approach, it has the ability of strong generalization and it also has the feature of global optimization. In this paper, a modeling and forecasting method of urban logistics demand based on regression SVM is presented. The SVM network structure for forecasting of urban logistics is established. Moreover, we propose a self-adaptive parameter adjust iterative algorithm to confirm SVM parameters, thereby enhancing the convergence rate and the forecasting accuracy. With the ability of strong self-learning and well generalization of SVM, the modeling and forecasting method can truly forecast the logistics demand by learning the index information of affect logistics demand. The actual forecasting results show that this method is feasible and effective.