决策表的建立和转换算法

本文将多值逻辑理论中的展开定理推广到混合多值逻辑上,从而得出了2-n-3和3-n-3两种模型的原始决策表的一种新的建立方法,并提出了原始决策表转换为标准决策表的完整算法。     

拓扑公式中树及各类K_树的一种系统算法

本文对拓扑公式中树及各类k_树提出了一种系统算法。由本算法求得的树及各类k_树的树支导纳乘积之和.都是以乘积表达式由图成批生成,且无重复项和对消项出现,使运算速度得到了大幅度提高。     

有向图的满装

本文应用 Edmonds 定理得到了某些有向图中以固定顶点为根的弧互不交的支撑树形图的极大个数.     

Ballot序列和一类二元树的表示

本文从Ballot序列出发推广定义了广义Ballot序列,利用它来表示一类具有n内节点的二元树,并且给出了自动生成广义Ballot序列和n内节点二元树的有效算法。文中还解决了对n内节点二元树的计数问题。     

带钢表面检验中的缺陷分类

文章论述了一种使用质量检测软件决策树对带钢表面缺陷进行分类的方法。     

Research on decision tree induction from self-map space based on web

This paper proposes an improved decision tree method for web information retrieval with self-map attributes. Our self-map tree has a value of self-map attribute in its internal node, and information based on dissimilarity between a pair of map sequences. Our method selects self-map which exists between data by exhaustive search based on relation and attribute information. Experimental results confirm that our improved method constructs comprehensive and accurate decision tree. Moreover, an example shows that our self-map decision tree is promising for data mining and knowledge discovery.     

基于改进的点击流树的自适应站点导航

由于Web信息的日益增长,人们不得不花费大量的时间去搜索,浏览自己需要的信息。自适应站点导航能够预测用户下一步的请求,帮助用户找到自己所需的信息。文中提出了一种改进的点击流树模型,其主要特点是融入了站点的概念层次。实验表明改进后的算法提高了导航路径的预测精度。     

A modernized and versatile startup reactivity measuring system installed at NPP Paks and its application for subcritical systems

In 2004 the Hungarian Paks NPP completed a project for upgrading the reactivity measuring system applied during reactor startup experiments. Almost all components of the previous system were replaced, only ex-core ionisation chambers remained unaltered. New hardware and software components were introduced for neutron flux signal handling, for data acquisition, as well as for measurement evaluation and data presentation. High-precision picoamper meters were installed at each reactor unit, current signals are handled by a portable signal processing unit. The system applies an accurate on-line reactivity calculation algorithm based on the point-kinetic model with six delayed neutron groups. Detailed off-line evaluation and analysis of startup measurements can be performed on the portable unit, as well.The paper describes the architecture, data acquisition modules, services and man–machine interface of the new system. Functions and results are illustrated with measured data recorded during a startup of Unit 3. In 2003 and 2004 the RMR was installed and tested at all Paks NPP units successfully and now it is in regular use during unit startups.The second part of the paper illustrates an extension of the new system to perform reactivity measurements using the well-known Rossi-α and Feynman-α statistical methods. The modified system was needed to estimate the reactivity of a subcritical system formed by damaged fuel assemblies stored at the fuel service pit of Paks Unit 2. Theoretical background of the applied algorithms is outlined, then results of validation tests and on site measurements are treated. The measurements have shown that the subcriticality of the damaged fuel was sufficiently deep if the high boron concentration in the fuel service pit was maintained.     

决策树中数值型属性分裂的研究

在介绍了现有数值型属性分裂方法的基础上，引出了纯区间的概念，提出了一种基于纯区间归约的数值型属性分裂方法。该方法将属性值域用等宽直方图的方法划分为多个区间，对纯区间和非纯区间分别处理。理论分析和实验结果表明该方法在保证了分裂精度的同时，减小了搜索空间。     

多代表点特征树与空间聚类算法

空间数据具有海量、复杂、连续、空间自相关、存在缺损与误差等的特点，要求空间聚类算法具有高效率，能处理各种复杂形状的簇，聚类结果与数据空间分布顺序无关，并且对离群点是健壮的等性能，已有的算法难以同时满足要求。本文提出了一个适合处理海量复杂空间数据的数据结构一多代表点特征树。基于多代表点特征树提出了适合挖掘海量复杂空间数据聚类算法CAMFT，该算法利用多代表点特征树对海量的数据进行压缩，结合随机采样的方法进一步增强算法处理海量数据的能力；同时，多代表点特征树能够保存复杂形状的聚类特征，适合处理复杂空间数据。实验表明了算法CAMFT能够快速处理带有离群点的复杂形状聚类的空间数据，结果与对象空间分布顺序无关，并且效率优于已有的同类聚类算法BLRCH与CURE。