基于支持向量机回归的应急物资需求预测  

Emergency Materials Demand Prediction Based on Support Vector Machine Regression

作　　者：赵一兵[1] 高虹霓[1] 冯少博[1] 

机构地区：[1]空军工程大学防空反导学院,陕西西安710043

出　　处：《计算机仿真》2013年第8期408-412,共5页Computer Simulation

摘　　要：目前对应急物资需求预测仍以专家经验判断为主,尚未形成成熟的办法。针对应急物资预测方法缺乏科学依据难题,提出了一种新的科学预测方法 -两步法,即支持向量机回归算法和库存管理模型,建立了人员伤亡预测模型,对地震人员伤亡进行了预测,然后再结合库存管理模型对应急物资进行了估算。最后,运用提出的方法对"青海玉树地震"的人员伤亡进行了预测,证明了方法的有效性,并估算出了应急物资需求量,为灾区的应急物资供应提供科学依据。A new scientific method was established based on two-steps method-the Support Machine Vector Regression and the Inventory Management Model,which can predict the earthquake casualties.Next,the emergency materials were estimated by the Inventory Management Model.At last,the casualties of ＂Qinghai Yushu earthquake＂ were predicted by this method.The method was proved effective.Next,the emergency materials of it were estimated,and this provided the scientific basis for the supply of emergencies.

关 键 词：应急物资 支持向量机回归 库存管理模型 需求预测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]