生猪市场价格风险预警的GRNN建模及其实证研究

为了对生猪市场价格风险进行预警,根据我国2009年1月-2011年8月14个指标的32组样本数据,建立了广义回归神经网络(GRNN)预警模型,其中训练样本29组,测试样本3组.训练样本和测试样本的均方根误差、平均绝对误差(AAE)和相关系数都非常接近,说明建立的模型具有较强的泛化能力和鲁棒性,测试样本的AAE为0.0062,平均相对误差为2.3%,说明建立的GRNN模型具有很高的预测精度,可用于我国生猪市场价格风险预警研究和实际预测,并为政府有关部门指导生猪生产和进行市场调控提供决策依据.     

基于粗糙集的经济预警规则发现

应用粗糙集的理论和方法对经济预警有关数据进行分析,挖掘其中隐含的有用信息,提取规则并对规则进行约简,从而求取表达经济预警信息的最小决策规则,为经济预警有用信息的获取提供一种有效的方法.     

风险投资的模糊数学评价模型

目前风险投资市场发展迅速,但是由于自身的高风险性和不确定性,难以利用传统的风险评价与控制方法,造成风险投资家投资困扰.针对风险投资评估指标标准模糊、难以控制的特点,建立模糊数学评价模型和AHP模型相结合的风险预警控制方法,可以提高分析指标的可靠性及灵敏性,并进行实证分析说明其科学性和有效性.为风险投资公司有效筛选投资项目、实现投资收益提供具体、可行的预警方法.     

基于混沌粒子群优化算法的灰色GM(1,1)模型在地下水埋深预测中的应用

将混沌优化算法与粒子群优化算法相结合,形成新的混沌粒子群优化算法.利用混沌运动的遍历性,避免陷入局部最优.同时,粒子群算法能加快混沌优化算法的收敛速度,使搜索效率得到提高.用混沌粒子群优化算法优化灰色GM(1,1)模型中的参数,通过横向和纵向比较,优化效果良好,模型预测精度得到了提高.运用该模型对三江平原地下水埋深进行动态预测,预测结果可为有关决策部门提供参考.     

海上通道关键节点风险预警研究

海上通道关键节点风险预警研究是保障海上通道安全的重要环节,为准确地预警关键节点的风险,通过对历史案例的统计分析,得出主要风险源因素,构建预警指标体系,以粗糙集理论和粒子群优化原理为基础,建立了基于最小网络误差的最优风险预警模型.通过实例分析证明了该模型可对海上通道关键节点的风险进行有效预警,为保障我国国际海运通道安全,降低海上运输风险和建设"21世纪海上丝绸之路"提供决策参考.     

基于三角模糊层次分析法的农产品滞销风险等级决策评价

为了有效预警和弱化农产品滞销事件危害,提出农产品滞销风险等级评估方法.首先,搜集近3年来发生的农产品滞销较大事件209起,分析确定农产品滞销风险等级评价指标体系.其次,考虑到决策过程的复杂性和不确定,提出三角模糊数的层次分析法确定评价指标权重.将农产品滞销风险划分为五个等级,构建各等级的标准模糊状态向量,利用模糊模式识别法计算农产品与等级标准模糊状态向量之间的贴近度.然后,基于权重和贴进度建立农产品滞销风险等级决策模型.最后,实例和对比分析研究验证了基于三角模糊数的层次分析法和模糊模式识别的农产品滞销风险等级评估模型的有效性和可行性.     

基于不同风险偏好的退货可再销报童模型研究

考虑退货可再销售的情况下,应用条件风险价值(CVaR),构建纳入不同风险偏好的报童模型,并给出了不同环境下的最优订货量.通过解析和数值仿真,进一步分析了决策者的风险偏好水平、产品退货率以及残值对最优订货量决策的影响.研究结果表明:最优订货量随着决策者风险追逐偏好水平的增加而增加,随着风险规避偏好水平的增加而减小;最优订货量随着退货率的增加而减小,随着产品残值的增加而增加.结合订货决策的实际特点,给出了不同环境下的最优订货量,为决策者提供了全面且动态的决策建议.     

自由飞行环境下的碰撞风险安全评估

针对自由飞行的安全性,对自由飞行环境下的碰撞风险进行研究.首先,通过对飞机在航迹上任意时刻的三维坐标的研究,建立了自由飞行环境下的碰撞风险安全评估模型.然后,在三维坐标系的基础上加入了时间变量,推导出纵向重叠概率计算公式.分析自动相关监视(ADS)对纵向碰撞风险影响,据此建立了自由飞行环境下基于ADS性能的纵向碰撞风险评估模型.最后,通过实例对纵向碰撞风险进行了安全评估计算,计算结果符合实际情况,评估模型是可行的.并在此基础上提出了自由飞行环境下的碰撞风险安全评估的未来研究方向.     

选择与评价新产品开发的风险决策研究

本文针对企业投资决策者在新产品开发中的风险决策,基于贝叶斯决策理论及其相关研究建立了评估外部情报信息价值的数学模型,探讨投资决策者风险倾向、新产品开发风险投资未来市场需求以及情报费用对投资决策的影响机制,并用于评估新产品开发决策。研究结果有助于理解企业决策者进行新产品开发决策时应考虑的因素和情境,并能够辅助决策。最后,将这一数学模型应用到一家大型高科技企业的案例中。应用案例分析结果表明:本文的研究结论能够为企业开发新产品提供相关的决策依据。     

规定安全间隔的CNS性能环境研究

对平行航路下规定安全间隔的CNS性能环境评估问题进行了研究.首先分析了CNS性能环境对飞机碰撞风险的影响,并结合Reich模型和概率论方法建立了CNS性能环境下飞机纵向、侧向和垂直方向上的碰撞风险模型;其次对碰撞风险模型进行分析转化得到了规定的安全间隔和安全目标水平下CNS性能环境的评估计算方法.最后对平行航路的CNS性能环境进行了评估计算,得到符合航路安全目标水平1.5×10~(-8)的CNS性能环境为RNP10、RCP400、RSP20.     

Ritz and harmonic Ritz values and the convergence of FOM and GMRES

The Ritz and harmonic Ritz values are approximate eigenvalues, which can be computed cheaply within the FOM and GMRES Krylov subspace iterative methods for solving non‐symmetric linear systems. They are also the zeros of the residual polynomials of FOM and GMRES, respectively. In this paper we show that the Walker–Zhou interpretation of GMRES enables us to formulate the relation between the harmonic Ritz values and GMRES in the same way as the relation between the Ritz values and FOM. We present an upper bound for the norm of the difference between the matrices from which the Ritz and harmonic Ritz values are computed. The differences between the Ritz and harmonic Ritz values enable us to describe the breakdown of FOM and stagnation of GMRES. Copyright © 1999 John Wiley & Sons, Ltd.     

Diversity and Popularity in Organizations and Communities

This paper examines social groupings whose structure depends only on the distribution of ability to attract attention. When people‘s attention is a scarce resource, those individuals who are rated highest by a large number of other individuals will have to ration their attention, resulting in constraints on the social structure of the group. The incidence of popular individuals by that definition reflects the extent to which individuals agree on who their highest-rated colleague is. We propose three basic distributions or ways to generate the matrix of perceived ability so as to yield popularity profiles that can be parametrically adjusted to match observations. We demonstrate that each of these assumption sets leads to a slightly different correlation between the value of the assumption‘s parameter and the set of observable popularity patterns. Since popularity, in real life, often determines such things as power, centrality, over-utilization and perhaps reduced accessibility, having more realistic ways of representing it is important for modeling and understanding virtual organizations and communities.     

Polytopes and arrangements: Diameter and curvature

We introduce a continuous analogue of the Hirsch conjecture and a discrete analogue of the result of Dedieu, Malajovich and Shub. We prove a continuous analogue of the result of Holt and Klee, namely, we construct a family of polytopes which attain the conjectured order of the largest total curvature.     

Navier and Stokes meet Poincare and Dulac

This paper surveys various precise (long-time) asymptotic results for the solutions of the Navier-Stokes equations with potential forces in bounded domains. It turns out that the asymptotic expansion leads surprisingly to a kind of Poincare-Dulac normal form of the Navier-Stokes equations. We will also discuss some related results and a few open issues.     

Singular quasilinear and Hessian equations and inequalities

We solve the existence problem in the renormalized, or viscosity sense, and obtain global pointwise estimates of solutions for quasilinear and Hessian equations with measure coefficients and data, including the following model problems:

     

Lebesgue测度等测包及其应用

利用Lebesgue测度的等测内核和等测外包讨论内外测度的一系列性质,给出外测度有限可加的一个充要条件,该条件改进了原有外测度有限可加性相关问题的结果.     

Dual and triple equations and q-orthogonal polynomials

In this paper, we solve dual and triple sequences involving q-orthogonal polynomials. We also introduce and solve a system of dual series equations when the kernel is the q-Laguerre polynomials. Examples are included.     

Proper and Unit Trapezoid Orders and Graphs

We show that the class of trapezoid orders in which no trapezoid strictly contains any other trapezoid strictly contains the class of trapezoid orders in which every trapezoid can be drawn with unit area. This is different from the case of interval orders, where the class of proper interval orders is exactly the same as the class of unit interval orders.     

Vertex- and edge-minimal and locally minimal graphs

Given a family of graphs , a graph is called edge-minimal (vertex-minimal) if for every subgraph (induced subgraph) G^′ of G; furthermore, G is called locally edge-minimal (locally vertex-minimal) if whenever G^′ is obtained from G by deleting an edge (a vertex). Similarly, the concepts of minimality and local minimality are introduced for directed graphs (digraphs) and, more generally, for partially ordered sets.For example, by the Strong Perfect Graph Theorem, the only vertex-minimal graphs with χ>ω are odd holes and anti-holes. In contrast, the only locally vertex-minimal graphs with χ>ω are partitionable graphs. Somewhat surprisingly, there are infinitely many non-trivial perfect graphs that are locally edge-minimal and -maximal simultaneously. In other words, such a graph is perfect but it becomes imperfect after any edge is deleted from or added to it.In this paper we consider vertex- and edge-minimal and locally minimal graphs in the following families: (i) perfect and imperfect graphs, (ii) graphs with χ=ω and with χ>ω, (iii) digraphs that have a kernel and kernel-free digraphs, and finally, (iv) vertex-minimal complementary connected d-graphs.     

Crossings and nestings of matchings and partitions

We present results on the enumeration of crossings and nestings for matchings and set partitions. Using a bijection between partitions and vacillating tableaux, we show that if we fix the sets of minimal block elements and maximal block elements, the crossing number and the nesting number of partitions have a symmetric joint distribution. It follows that the crossing numbers and the nesting numbers are distributed symmetrically over all partitions of , as well as over all matchings on . As a corollary, the number of -noncrossing partitions is equal to the number of -nonnesting partitions. The same is also true for matchings. An application is given to the enumeration of matchings with no -crossing (or with no -nesting).