检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:谢力[1] 魏汝祥[1,2] 孙胜祥 林名驰[1] 肖金石[2]
机构地区:[1]海军工程大学装备经济管理系,湖北武汉430033 [2]海军工程大学训练部,湖北武汉430033
出 处:《系统工程与电子技术》2017年第10期2264-2269,共6页Systems Engineering and Electronics
基 金:国家社会科学基金军事学项目(13GJ003-258;14GJ003-149);国家社会科学基金(14CGL061);海军工程大学基金(2015JB-28)资助课题
摘 要:根据集对分析的基本原理,结合基于误差大小的集对分析组合预测,给出了基于误差方向的集对分析组合预测和基于模型性能的集对分析组合预测;针对基于误差大小的集对分析组合预测建模过程中,从关联度的确定到组合权重的计算过程相对复杂、难以理解,推导简化了组合预测权重计算过程;针对集对分析中同一度为0时导致组合预测模型信息丢失的问题,提出了一种基于折扣的同一度、差异度、对立度转换处理方法。最后算例说明了该方法的有效性。According to the set pair analysis theory and the combination model based on set pair analysis of the size of forecast error, two kinds of combination model are provided. One is the combination model based on set pair analysis of forecast error direction, the other is the combination model based on set pair analysis of forecast performance. The process from determining the correlation degree to calculating the combined weights is relatively complex and difficult to understand, in the forecast combination modeling based on set pair analysis of the size of forecast error. The simplified combination forecasting weight calculation process is derived. Aiming at the problem that identical degree equal to 0 may lead to combination forecasting model information loss in set pair analysis, the conversion processing method based on discount is proposed between identical degree, differential degree and opposite degree. Finally an example is given to show the effectiveness of this method.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.14.144.240