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:王小林[1] 成金华[1] 尹正杰[2] 胡铁松[3]
机构地区:[1]中国地质大学(武汉)经济管理学院,武汉430074 [2]长江科学院水资源研究所,武汉430010 [3]武汉大学水资源与水电工程科学国家重点实验室,武汉430072
出 处:《系统工程理论与实践》2009年第10期129-137,共9页Systems Engineering-Theory & Practice
基 金:国家自然科学基金(50479039);中国地质大学(武汉)校青年基金(CUGQNW0908)
摘 要:以北方某供水水库为例,将人工免疫识别系统(Artificial immune recognition system,AIRS)作为一种新兴数据挖掘方法用于水库调度规则提取研究,所获调度规则对检验样本的分类精度为86.1%,缺水指数为2.14(10^(14)m^6),优于RBF提取调度规则的结果.进一步从调度规则与训练、检验样本之间的距离分布间接分析了在水库调度特征属性构成的高维非线性决策空间中亲和力测度方法、学习样本空间分布以及追加样本对AIRS提取供水调度规则的行为与性能的影响.结果表明,①HVDM(Heterogeneous value difference metric)距离测度方法能融入调度决策先验知识,使AIRS提取的规则在空间分布上更接近训练、检验样本;②所获规则分类性能不仅取决于训练样本空间分布,也取决于检验样本的空间分布;③追加近期调度资料可以不断更新或补充规则,使其空间分布更适应未来水文环境变化.This paper artificial immune recognition system (AIRS) was employed as an emerging technique of data mining to extract operating rules with a case of water supply reservoir, eventually obtaining the classification rate 86.1% for testing samples and the shortage index 2.14(10^14m^6) which outperformed the results of RBF. Further statistics about distance distributions between the acquired operating rules and training or testing samples were made to indirectly illuminate the impacts on the performances or behaviors of AIRS from three aspects of different affinity functions, training and testing sample spatial distribution and supplemental samples in high nonlinear space of operating decision. The results indicate that ① heterogeneous value difference metric for affinity function in AIRS can make use of prior knowledge and experiences of decision-makers so that extracted operating rules in spatial distribution are closer to training and testing samples; ②classification abilities of obtained rules depend on not only training sample spatial distribution, but also testing sample distribution; ③latest operating decision data can be used for updating existing rules or increasing new ones, which can improves operating rule spatial distribution to make the rules more fit for changes of hydrological environment in the future.
分 类 号:TV697.1[水利工程—水利水电工程] TP181[自动化与计算机技术—控制理论与控制工程]
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:18.117.82.179