基于改进支持向量机的地震应急物资需求预测模型  

Demand Forecasting Model of Earthquake Emergency Supplies Based on Improved Support Vector Machine

作　　者：何珊珊[1] 朱文海[2] 

机构地区：[1]防灾科技学院,河北三河065201 [2]北京铁路局丰台货运中心,北京102300

出　　处：《物流科技》2015年第11期39-42,共4页Logistics Sci-Tech

基　　金：中国地震局教师科研基金项目;项目编号:20140107;河北省高等学校科学技术类一般项目;项目编号:Z2013111

摘　　要：目前,应急物资需求的预测是震后救援高效开展的关键环节之一,结合库存管理模型,建立了地震应急物资需求预测模型,为了改进预测效果,利用遗传算法对支持向量机进行参数优化,数值验证表明:该模型的计算结果与实测值吻合较好,能够准确地预测灾后人员伤亡人数,最后,还运用该模型对云南鲁甸地震的应急物资需求进行了估算。Currently, demand forecasting of earthquake emergency supplies is the key work to ensure the efficient earthquake rescue. Combined with inventory management model, demand forecasting model of earthquake emergency supplies is established. In order to improve efficiency and generalization ability of forecasting, genetic algorithm is applied to select parameters of support vector machine（ SVM）. The simulation results show that the calculated results of the model have good agreement with the measured ones, the model could satisfactorily predict the casualties after a disaster. Finally, earthquake emergency supplies of Yunnan earthquake are estimated by employing this model.

关 键 词：地震应急 需求预测 遗传算法 支持向量机 库存管理模型 

分 类 号：F251[经济管理—国民经济]