基于KPCA的高校学业预警模型及其应用

针对高校招生规模扩大,学生整体素质下滑,学业完成情况恶化的教育问题,本文从辅导员的工作角度利用核主成分分析(KPCA)建立大学生学业预警创新管理模型,实现动态定性预警与定量预警相结合,对高校科学、及时、有效的开展学业预警工作具有一定的实践指导意义.     

珠算能力考核方法改革之探索

考核是学校教学工作的重要一环,是教师对学生学习效果的检查和监督。考核的结果能否反映学生的学习效果及应用能力,与考核的方法密切相关,“一卷定乾坤”或“一锤定音” 的考试,是当前教育的一大弊端。它不能全面评价一个学生的     

最优绩效分配的多目标优化方法

如何体现某种程度的激励并兼顾公平性是绩效分配问题研究的关键之一. 基于考核对象的个体差异性, 对考核对象进行分类处理, 通过引入以体现激励程度的控制参数和所有考核对象的基础工作量为变量的分值转化函数与满意度函数, 建立以所有考核对象的总体满意度的最大化和考核对象的满意度尽可能均衡为目标的多目标优化模型. 进而利用多目标优化模型的epsilon-约束标量化方法证明了弱有效解的存在性. 作为其应用, 研究了某高校教师的最优绩效分配问题.     

语言判断矩阵偏好决策中群体对某方案满意度识别算法

群体对某方案的满意度识别算法是群决策研究的热点问题.文中考虑了决策者对方案评价意见难以量化的实际情况,在语言判断矩阵研究的基础上,提出了该偏好的偏离度方差指标,建立了群体对某方案的满意度识别算法,通过实际算例证实了该算法是有效的.     

临界点的局部结构与一类负曲率算法

一、引言对于收敛于函数临界点的算法，如果目标函数为一致凸，则算法终止时已得到了最小值点，但如果目标函数为非一致凸的函数，情况可能并非如此．为此Mccormick，Moré＆Soreuiseu，Goldfarb等构造了一类以负曲率为搜索方向的算法，其特点是算法终止于函数的Hessian矩阵为半径正定的临界点．本文的工作是对Goldfarb等人的算法在退化情况下作进一步讨论，通过引进l×m×n矩阵及其运算，改进了Morsé命题，给出了函数在临界点局部结构，并以此构造了一类新的以负曲率为搜索方向的算法．定义1设定义2设（i）加法：（ii）数乘：显然R上…     

具有机器适用限制的分布式置换流水车间问题的模型与算法

考虑具有机器适用限制的多个不同置换流水车间的调度问题. 机器适用限制指的是每个工件只能分配到其可加工工厂集合. 所有置换流水车间拥有的机器数相同但是具有不同的加工能力. 首先, 针对该问题建立了基于位置的混合整数线性规划模型; 进而, 对一般情况和三种特殊情况给出了具有较小近似比的多项式时间算法. 其次, 基于NEH方法提出了启发式算法NEHg, 并给出了以NEHg为上界的分支定界算法. 最后, 通过例子说明了NEHg启发式算法和分支定界算法的计算过程, 并进行大量的实验将NEHg与NEH算法结果进行比较, 从而验证了NEHg算法的有效性.     

永德露露EVM落地实践

EVM引入EV（挣值）这一指标,同时从项目预算费用执行和完工进度两个层面考核研发绩效,能有效避免传统考核方法下,费用执行不能反映进度完成情况的问题,其效果在承德露露的实操中得到了印证。     

一类网络上的干线选址

考虑一类在网络上点到路的距离意义下的最优干线选址问题,这是一类新型的选址问题.首先证明所讨论的两个问题是NP-hard,然后讨论树的情况,给出了当G是树时求解问题的算法,该算法的复杂性是O(n2).并对一些特殊网络的情况进行了讨论.     

步进的特征列算法及其在流密码分析中的应用

"吴特征列"算法是多元方程组求解的一种主要代数方法.讨论求解布尔多项式方程组特征列算法的改进算法.具体完成以下几方面工作:1)根据二阶有限域的特点,在已有工作的基础上提出布尔方程组求解的特征列算法的步进算法——SSTDCS,并且证明了该算法的正确性;2)用C语言在SzDD软件包上编程实现了该算法;3)把算法应用在流密码的代数分析中,对算法有效性进行检验,实验结果表明所给算法对大部分实例是有效与稳定的.     

带机器准备时间的机器覆盖问题的在线、半在线算法

研究以极大化最小机器负载为目标的机器带准备时间的同型机排序问题.证明了LS算法是求解该问题的最好的在线算法,它的最坏情况界为1/m.同时给出了求解两台机的预先知道工件最大加工时间,预先知道工件集的总加工时间以及预先知道工件从大到小到达这三种情形下最好的半在线算法,这三个算法的最坏情况界分别为2/3,2/3以及3/4.     

有相似产品信息情形下的可靠性评定方法

两个具有局部相同组成部分的相似设备为模型,建立有相关信息情形下进行可靠性评估的指数模型,并给出了指数模型中的参数估计方法,在此基础上建立了相似设备到目标设备信息的融合算法,进而提出了一种具有相似产品信息情形下的可靠性评定方法.     

Environmental impact assessment using the evidential reasoning approach

Environmental impact assessment (EIA) problems are often characterised by a large number of identified environmental factors that are qualitative in nature and can only be assessed on the basis of human judgments, which inevitably involve various types of uncertainties such as ignorance and fuzziness. So, EIA problems need to be modelled and analysed using methods that can handle uncertainties. The evidential reasoning (ER) approach provides such a modelling framework and analysis method. In this paper the ER approach will be applied to conduct EIA analysis for the first time. The environmental impact consequences are characterized by a set of assessment grades that are assumed to be collectively exhaustive and mutually exclusive. All assessment information, quantitative or qualitative, complete or incomplete, and precise or imprecise, is modelled using a unified framework of a belief structure. The original ER approach with a recursive ER algorithm will be introduced and a new analytical ER algorithm will be investigated which provides a means for using the ER approach in decision situations where an explicit ER aggregation function is needed such as in optimisation problems. The ER approach will be used to aggregate multiple environmental factors, resulting in an aggregated distributed assessment for each alternative policy. A numerical example and its modified version are studied to illustrate the detailed implementation process of the ER approach and demonstrate its potential applications in EIA.     

Robustness of Discrete Decisions to the Worst Case Distribution

This paper proposes a robustness measure for discrete decisions subject to uncertainty in the state probabilities. The robustness measure is the worst case difference in expected payoffs between the chosen action (the decision) and all other actions, as the state probabilities are allowed to vary simultaneously over prescribed tolerance ranges. In contrast to the more difficult to assess single distribution, the current approach requires only the assessment of an interval for each state probability; i.e. it works with a more easily assessed spectrum of distributions. It is shown that the robustness can be determined with an algorithm that is much simpler than the usual linear programming techniques. Its computational simplicity makes this algorithm amenable to manual calculation.     

基于模糊理论的软件寿命周期费用评价模型

软件寿命周期费用评价模型涉及到软件开发、使用和维护过程中各种资源最有效利用的权衡分析。由于软件开发不是一门严谨的精确科学,往往存在大量具有不确定性的需求以及许多未知和不确定因素,所有这些都给软件寿命周期费用评价带来模糊效用。本文将模糊理论应用于软件寿命周期费用的评价,给出了从评价属性模糊值的确定、模糊评价模型的建立,到模型求解和最优方案选择的模糊评价方法,并通过对一个算例的分析,证明了该模型的可行性。     

小微企业信用风险评估的IDGSO-BP集成模型构建研究

针对传统BP神经网络在小微企业信用风险评估实际应用中,随机初始权值和阈值导致网络学习速度慢、易陷入局部解以及运算结果误差较大等缺陷,借助群智能萤火虫(GSO)算法,提出一种基于改进离散型萤火虫(IDGSO)算法的BP神经网络集成学习算法的小微企业信用风险评估IDGSO-BP模型。该模型以BP神经网络为基本框架,在学习过程中引入离散型萤火虫算法,优化设计神经网络的网络结构与连接权值,得到一组相对合适的权值与阈值,再进行新一轮网络训练,以“均平方误差最小”为评价准则,产生网络的输出结果,以此建立小微企业信用风险评估模型。其仿真实验结果表明,该模型在收敛速度及运算精度方面较传统BP神经网络模型、遗传GA-BP模型及连续GSO-BP模型有较明显优势。因此,IDGSO-BP模型可以有效提高小微企业信用风险评估的准确性。     

基于多目标进化聚类的信用风险特征识别

在信用风险识别领域,聚类算法常被用于区分不同风险等级的样本并识别风险特征。然而该领域中通常面临高维数据处理问题,导致传统聚类算法存在不适应此类问题的缺陷：易陷入局部最优、受冗余特征干扰、鲁棒性不强等。采用高维信用风险数据,研究上市公司信用风险,建立信用风险特征识别的三目标优化模型,设计基于分解的多目标子空间聚类算法进行求解。通过算法的横向对比实验,展示了所提出的算法在聚类精度和鲁棒性方面的优势,并根据聚类算法的权重分配结果,归纳总结上市公司信用风险评估过程中应重点关注的指标。     

基于随机森林融合朴素贝叶斯的信用评估模型

利用随机森林特征选择算法,对信用评估的可用指标集进行特征选择,在此基础上建立基于随机森林融合朴素贝叶斯的信用评估模型.选取UCI数据库中的German数据集进行实证研究,结果表明,通过随机森林进行特征选择的随机森林融合朴素贝叶斯模型具有更高的预测准确度.     

基于语言变量模糊评价的可信软件非功能需求权衡模型

提出了一个模糊定性定量的软目标相互依存图FQQSIG模型(Fuzzy Qualitative and Quantitative Softgoal Interdependency Graphs)来分析可信软件(Trustworthy Software,TS)中的非功能需求(Non-Functional Requirements,NFRs)的相关性.首先描述了一个NFRs层次分解图,专家团队并对NFRs的重要性程度进行语言变量形式的模糊定性评价,然后再用梯形模糊数和RAGE(RAndom GEneration)随机仿真算法来完成定性到定量数据的转化,最后再提出关系矩阵算法实现NFRs节点贡献值的计算以及应用FQQSIG模型进行NFRs节点权衡.     

Evaluation of the performance of inexact GMRES

The inexact GMRES algorithm is a variant of the GMRES algorithm where matrix-vector products are performed inexactly, either out of necessity or deliberately, as part of a trading of accuracy for speed. Recent studies have shown that relaxing matrix-vector products in this way can be justified theoretically and experimentally. Research, so far, has focused on decreasing the workload per iteration without significantly affecting the accuracy. But relaxing the accuracy per iteration is liable to increase the number of iterations, thereby increasing the overall runtime, which could potentially end up being greater than that of the exact GMRES if there were not enough savings in the matrix-vector products. In this paper, we assess the benefit of the inexact approach in terms of actual CPU time derived from realistic problems, and we provide cases that provide instructive insights into results affected by the build-up of the inexactness. Such information is of vital importance to practitioners who need to decide whether switching their workflow to the inexact approach is worth the effort and the risk that might come with it. Our assessment is drawn from extensive numerical experiments that gauge the effectiveness of the inexact scheme and its suitability for use in addressing certain problems, depending on how much inexactness is allowed in the matrix-vector products.     

Exploring the latent segmentation space for the assessment of multiple change-point models

This paper addresses the retrospective or off-line multiple change-point detection problem. Multiple change-point models are here viewed as latent structure models and the focus is on inference concerning the latent segmentation space. Methods for exploring the space of possible segmentations of a sequence for a fixed number of change points may be divided into two categories: (i) enumeration of segmentations, (ii) summary of the possible segmentations in change-point or segment profiles. Concerning the first category, a dynamic programming algorithm for computing the top $N$ most probable segmentations is derived. Concerning the second category, a forward-backward dynamic programming algorithm and a smoothing-type forward-backward algorithm for computing two types of change-point and segment profiles are derived. The proposed methods are mainly useful for exploring the segmentation space for successive numbers of change points and provide a set of assessment tools for multiple change-point models that can be applied both in a non-Bayesian and a Bayesian framework. We show using examples that the proposed methods may help to compare alternative multiple change-point models (e.g. Gaussian model with piecewise constant variances or global variance), predict supplementary change points, highlight overestimation of the number of change points and summarize the uncertainty concerning the position of change points.