两阶段半监督加权朴素信念分类模型

针对目前半监督分类算法中未考虑缺失属性隐含信息和算法复杂度高的情况,改进了朴素信念分类,提出了两阶段半监督加权朴素信念分类模型。与直推支持向量机对比实验结果表明两阶段半监督加权朴素信念分类模型减少了分类时间,并且在其能够明确分类的样本上的正确率与直推支持向量机相当,是一种有效的不完整数据分类算法。     

ABC库存分类的多指标体系及其信息熵方法

库存合理分类对企业的库存管理非常重要.在现有ABC库存分类指标体系的基础之上,指出需求波动对库存分类的重要性,设计了考虑需求波动系数的.ABC库存分类多指标体系;进一步,分析了指标的差异性对库存分类的影响,提出了基于信息熵的多指标ABC库存分类方法.与已有文献对比分析表明,所设计的多指标分类体系综合考虑了库存物资的不同属性;对某家电企业的案例分析可以看出,所提出的.ABC库存分类的多指标体系及其信息熵方法有助于企业制定合理的库存决策,可有效提高企业的管理绩效.     

分类讨论的数学思想及其应用（5）

在第四讲中,我们围绕概念型与原理型分类进行了分类讨论运用的探讨．这两类问题分类的原因与教材中的相关内容紧密衔接,只要我们注意相关内容中的分类因素,又学会了如何进行分类讨论,解决这两类问题的规律并不难掌握．     

基于SVM的高分辨率遥感图像的分类方法研究

SVM(Support Vector Machine,支持向量机)分类算法是一种在高分辨率遥感图像分类中逐步得到重视的算法.首先详细介绍了SVM算法的数学原理,其次给出了基于SVM的高分辨率遥感图像分类方法的模型建立、光谱特征提取以及分类器设计,然后在AVIRIS标准多波段遥感数据集Indian Pines上进行了仿真,通过混淆矩阵和kappa系数评价了分类性能,最后以作者所在高校地区高分图像分类为例,验证了方法在高分辨率遥感图像地物分类上的有效性.     

一种新的中文文本分类特征提取的研究

特征提取是中文文本分类中的关键,传统的互信息算法没有考虑特征存在负值时,互信息量对分类的影响,因此削弱了这些特征在分类中的作用.首先提出一种改进的互信息算法,对特征和类的互信息量取绝对值的方法来克服这个缺点.然后实现了基于传统互信息KNN算法和改进互信息FV-KNN算法的两种中文文本自动分类系统.最后实验结果表明改进互信息FV-KNN算法在分类准确率、分类招回率和分类速度上都有较大的提高.     

基于GBMTS算法的不平衡数据分类研究

解决不平衡数据分类问题,在现实中有着深远的意义。马田系统利用单一的正常类别构建基准空间和测量基准尺度,并由此建立数据分类模型,十分适合不平衡数据分类问题的处理。本文以传统马田系统方法为基础,结合信噪比及F-value、G-mean等分类精度,建立了基于遗传算法的基准空间优化模型,同时运用Bagging集成化算法,构造了改进马田系统模型算法GBMTS。通过对不同分类方法及相关数据集的实验分析,表明:GBMTS算法较其他分类算法,更能够有效的处理不平衡数据的分类问题。     

关于多变量P—adic数的Mahler分类

1.引言 Mahler分类是超越数论的重要组成部分。自从1932年,K,Mahler引入这个分类以来,国内外专家在单变量实数的Mahler分类方面已作出了大量结果。1987年,于坤瑞推广了实数的Mahler分类,引入了多变量实数Mahler分类。他将R~n中的全部     

煤炭资源资产分类方法比较研究

煤炭资源资产评估是实行煤炭资源资产化管理的重要基础工作 ,而煤炭资源资产分类的可靠性是有效完成这一工作的前提条件 .针对煤炭资源资产的特点 ,建立了多个分类模型——基于模糊聚类的分类模型、基于 BP网络的分类模型及基于自适应共振理论网络的分类模型 ,编制了相应的分类程序软件包 ,实例运行效果证明了模型的有效性 .文中还对所建模型进行了比较和分析 ,提出了具体应用的建议 .     

分类讨论的数学思想及其应用（3）

第三讲：分类的方法 前面我们已经研究了分类讨论的过程．分类讨论首先就是要对分类的条件进行逻辑划分．     

城市居民生活垃圾源头分类行为的影响因素研究

识别影响我国城市居民生活垃圾源头分类行为的影响因素是确保生活垃圾源头分类有效实施的基础和前提。本文以计划行为理论为基础,运用实证研究方法,分析了影响我国城市居民生活垃圾源头分类行为的影响因素,研究结果表明源头分类行为意向包含2个维度,影响因素包含7个维度,且借鉴层次分析方法解释说明了影响因素对源头分类行为的影响力。研究结论可以为城市市政相关部门制定政策和促进居民实施源头分类提供指导和借鉴。     

北京市居民垃圾分类情况调查浅析

采用调查问卷的形式,对北京市泰和小区、贵园南、北小区的居民和亦庄中心小学的家长进行垃圾分类知识的掌握情况,垃圾分类的态度意识,以及其对垃圾分类的处理方式等相关方面的了解.本文通过Pearson卡方检验来分析三个小区垃圾分类问题上的差异性;通过logistic回归,建立垃圾分类问题中居民的垃圾分类行为、居民的垃圾分类态度与垃圾分类知识的掌握情况之间的关系;同时,通过调查问卷来分析民众是否正确进行垃圾分类,并且分析民众将垃圾错误分类的原因何在,并提出合理有效措施以确保民众能够更好地进行垃圾分类.     

Lie symmetries and form-preserving transformations of reaction-diffusion-convection equations

New Lie symmetry classification of the known class of reaction-diffusion-convection equations is presented. The classification method is based on combining the standard group classification method and the form-preserving transformation approach.     

考虑消费者选择行为的农产品质量分级博弈分析

质量分级是农产品实现优质优价的重要手段,但目前只有少数农产品实现了分级销售。基于消费者的质量优选行为,构建了生产商和零售商实施质量分级的博弈模型,分析了不同主体实施质量分级对产品最优定价及利润的影响。结论表明,农产品质量分级优于不分级;当高质量产品消费者的流失率低于临界值时,零售商质量分级能够实现供应链系统利润最大。据此,建议政府出台相关支持政策,鼓励零售商对农产品进行质量分级。     

A complete classification of ternary self-dual codes of length 24

Ternary self-dual codes have been classified for lengths up to 20. At length 24, a classification of only extremal self-dual codes is known. In this paper, we give a complete classification of ternary self-dual codes of length 24 using the classification of 24-dimensional odd unimodular lattices.     

On the classification of weighing matrices and self‐orthogonal codes

We provide a classification method of weighing matrices based on a classification of self‐orthogonal codes. Using this method, we classify weighing matrices of orders up to 15 and order 17, by revising some known classification. In addition, we give a revised classification of weighing matrices of weight 5. A revised classification of ternary maximal self‐orthogonal codes of lengths 18 and 19 is also presented. © 2011 Wiley Periodicals, Inc. J Combin Designs 20:40–57, 2012     

Analysis of the consistency of a mixed integer programming-based multi-category constrained discriminant model

Classification is concerned with the development of rules for the allocation of observations to groups, and is a fundamental problem in machine learning. Much of previous work on classification models investigates two-group discrimination. Multi-category classification is less-often considered due to the tendency of generalizations of two-group models to produce misclassification rates that are higher than desirable. Indeed, producing “good” two-group classification rules is a challenging task for some applications, and producing good multi-category rules is generally more difficult. Additionally, even when the “optimal” classification rule is known, inter-group misclassification rates may be higher than tolerable for a given classification model. We investigate properties of a mixed-integer programming based multi-category classification model that allows for the pre-specification of limits on inter-group misclassification rates. The mechanism by which the limits are satisfied is the use of a reserved judgment region, an artificial category into which observations are placed whose attributes do not sufficiently indicate membership to any particular group. The method is shown to be a consistent estimator of a classification rule with misclassification limits, and performance on simulated and real-world data is demonstrated.     

A classification of one-dimensional affine rank three graphs

The rank three subgroups of a one-dimensional affine group over a finite field were classified in 1978 by Foulser and Kallaher. Although one can use their results for a classification of corresponding rank three graphs, the author did not find such a classification in a literature. The goal of this note is to present such a classification. It turned out that graph classification is much simpler than the group one. More precisely, it is shown that the graphs in the title are either the Paley graphs or one of the graphs constructed by Van Lint and Schrijver or by Peisert. Our approach is based on elementary group theory and does not use the classification of rank three affine groups.     

Classification of extensions of the modal logic S4

We introduce a natural classification of normal extensions of the modal logic S4 in accordance to the volumes of clusters in the Kripke frames and prove the decidability of the classification. We distinguish the main logics in this classification and establish their important properties: finite axiomatizability, finite approximability, and recognizability.