关联规则在图书管理中的应用

关联规则主要用来发现数据库中存在的频繁项集.研究关联规则Apriori算法,并利用该数据挖掘技术对高校图书馆管理信息系统中的数据进行挖掘研究,并将挖掘到的规则结果应用到高校图书馆公共检索系统中,达到优化公共检索系统并且向读者提供多元化信息检索服务的目的.     

基于自学习规则和改进贝叶斯结合的问题分类*

根据对中文问题的分析可知,问题中的疑问词和中心词等关键词对问题所属类型起着决定性的作用。提出利用自学习方法建立疑问词—类别和疑问词+中心词—类别两种规则,并结合改进贝叶斯模型的问题分类方法。该方法充分利用了关键词对分类的贡献。实验结果表明,该分类方法有很大的改进,准确率达到了84%。     

基于类云模型聚类的多目标数据关联算法

针对多目标跟踪中的数据关联问题,提出一种基于类云模型c-均值聚类的数据关联算法.该算法采用类云模型c-均值聚类算法对目标有效回波进行聚类,将聚类中心作为目标最终观测值,运用最近邻法对聚类中心与航迹进行关联,用Kalman滤波器进行状态估计.实验结果表明,本算法与联合概率数据互联算法相比,跟踪精度高,计算量小,更适应于工程应用.     

混合匹配规则的否定选择算法

针对目前基于免疫的检测器生成算法中,匹配规则单一造成的检测器质量低下的问题,提出一种基于混合匹配规则的否定选择算法,采用海明距离整体匹配的各段内R连续比特匹配的否定选择算法,即混合匹配否定选择算法,对算法的性能进行了分析．实验结果表明,该算法能够高效地产生所需要的检测器,提高了检测率,且降低了误报率．     

云计算环境下多来源数据最优选取模型仿真

在云计算环境下多来源数据最优选取的研究中,由于来自不同的服务器数据具有不同特征,数据所含信息的融合度也不同,使得数据可选取特征存在较强的关联性.传统的数据最优选取模型,在进行选择时,关联性会给最优数据的选择带来干扰,选出大量的相关数据,不能很好地排除关联性数据,无法实现数据的最优高效选取,提出一种依据数据估计量变化的云计算环境下多来源数据最优选取模型,利用前几点数据拟合直线或曲线,进行云计算环境下多来源数据最优选取中干扰数据的预测,分析干扰数据点删除前后推断统计量的变化,检测该干扰数据点是不是强干扰点,过滤强干扰数据点后的模型则是云计算环境下多来源数据最优选取模型,通过分析数据排除模型引起的估计量的变化,实现云计算环境下多来源数据的最优选取.仿真结果说明,在大量云计算环境下多来源数据的处理中,采用所提模型可有效选取最优数据,并且具有较高的准确率.     

Change in the molecular weight distribution of poly(ethylene oxide) caused by the complexation with poly(acrylic acid)

The complexation between poly(ethylene oxide) (PEO) and poly(acrylic acid) (PAA) was made by using double the molar quantity of either polymer component at pH 2 where the resulting complex completely precipitates. After the removal of the precipitate, PEO or PAA remaining in the supernatant was subjected to gel permeation chromatography to investigate the change in the molecular weight distribution (MWD) caused by the complexation. No remarkable difference is observed in the MWD curves for PEO[1] (M_w=1.37 × 10⁴) before and after the complexation with PAA[1] (M_w=1.10 × 10³) and PAA[2] (M_w=4.16 × 10⁵). However, the MWD curves of PEO[2] (M_w=1.26 × 10⁵) and PAA[2] become shortened and shift to the low molecular weight side after the complexation with PAA[1] or [2] and PEO[2], respectively. This tendency is enhanced by increasing the complexation temperature. From these results, it is indicated that the complexation between PEO and PAA deals with an equilibrium reaction, and the equilibrium constant is dependent on the chain length of both polymer components and also on the complexation temperature.     

一种基于生成树的分类去除关联规则冗余方法

在信息及数据爆炸的时代,冗余问题已经成为数据挖掘者获得知识的重大障碍,而目前解决的方法会导致关联规则的不完整性。基于此,文中引入了有向超图表示关联规则,重定义了邻接矩阵,介绍了冗余规则分类处理思想,将冗余规则分为从属规则和重复路径规则,通过VB编程去除了从属规则冗余,以及利用生成树算法去除了重复路径规则冗余。实验结果证明,此方法创新性地结合了图论中有向超图、生成树与关联规则的知识,维护了关联规则的完整性和准确性,同时去除了全部冗余规则。     

面向移动机器人应用的跨平台自适应软件框架

摘要：自适应软件在移动机器人上具有广泛的应用前景,然而要在具有不同软硬件平台的移动机器人上开发自适应软件是一件非常困难的事情．．为了解决这个问题,提出并实现了一个面向移动机器人应用的跨平台自适应软件框架该框架屏蔽了运行平台的软硬件差异性,并使用规则文件将自适应逻辑分离出来,从而降低了自适应软件开发的难度。为了便于编写及检查规则文件,还实现了一个可视化的规则文件编辑器,用于自动生成模型图,并检查规则中存在的语法及逻辑错误i,最后,通过实验测试了框架的使用情况,并对框架的应用效果进行了评估、     

Rheological behavior of reactive blending of epoxidized natural rubber with cassava starch and epoxidized natural rubber with natural rubber and cassava starch

Epoxidized natural rubbers (ENR‐25 and ENR‐45) were prepared using the performic epoxidation method. Two‐component (ENR–cassava starch) and three‐component (ENR–NR–cassava starch) blends were prepared. ENR‐25 and ENR‐45 were blended with various quantities of gelatinized cassava starch in the latex state. The pure ENR exhibited lower shear stress and shear viscosity than those of the blends with cassava starch. Furthermore, the shear stress and shear viscosity were increased with an increase in the cassava starch concentration. The chemical interaction between the epoxide groups in the ENR and the hydroxyl groups in the cassava starch molecules might be the reason for the increasing trends of the shear stress and shear viscosity. The blends are classified as compatible blends because of the strong chemical bonding between different phases. SEM micrographs were used to clarify the compatibility. Power law behavior with pluglike flow profiles was observed for all sets of ENR–NR–cassava starch blends. Very low power law index values (<0.34) and highly pseudoplastic fluid behavior were also observed. The log additive rule was applied to plots of zero shear viscosity (consistency index) and the shear viscosity versus the concentration of ENR‐25. Positive deviation blending was observed, which indicates compatible blends. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 91: 1752–1762, 2004