论文部分内容阅读
基于范例推理(CBR)理论,利用最近相邻法和粗糙集理论搜索相似度最高的主震历史范例,分析各主要物资需求量的影响因素,预测当前范例主震期应急物资需求量。通过序贯决策,采用马尔科夫预测模型预测余震类型,进而搜索余震历史范例,预测余震期应急物资需求量。以“玉树”地震为例,运用该方法估算地震发生后食物类、生活用品类、药品类、工程机械类的需求量。
Based on the example reasoning (CBR) theory, the nearest neighbor method and rough set theory are used to search the history sample of the most similar mainshock, the influential factors of the demand for each major material are analyzed, and the demand of emergency materials in the current main shock period is predicted. Through sequential decision making, Markov forecasting model is used to predict the type of aftershocks, then search for historical examples of aftershocks and predict the demand for emergency supplies during aftershocks. Taking “Yushu” earthquake as an example, this method is used to estimate the demand for foodstuffs, daily necessities, pharmaceuticals and construction machinery after the earthquake.