冲击模型:进展与应用

综述了近30年来冲击模型研究的主要进展.介绍了一个新模型(δ-冲击模型)及其最新工作.基于簇生标值点过程的结构,给出了冲击模型的一个一般性框架,最后作为特例提出并分析了一个新的保险风险模型.     

基于数据和整体的航空网络静态定价模型

建立了一个静态定价与座位分配联合模型.利用模型的性质,将问题简化为一个可分的凹规划模型.特别地,在一个三航段网络上,从模型的网络流形式推出最优目标函数具有良好的性质,并对模型的最优价格决策进行了灵敏度分析.最后给出了一个双枢纽网络上对细分产品定价的算例.     

带ARMA(1,1)条件异方差相关的随机波动模型的MCMC算法

我们首先提出了一个带ARMA(1,1)条件异方差相关的随机波动模型,它是基本的随机波动模型的一个自然的推广.进一步,对于这一新模型,我们给出了一个马尔可夫链蒙特卡罗(M CM C)算法.最后,利用该模型的模拟数据,展示了M CM C算法在这种模型中的应用.     

一个多因子信用违约互换定价模型

考虑一个违约互换的多因子的简化模型,通过测度的转化并求解一个多变量Riccati常微分方程而得出了这个模型的解析解.此模型是Duffie-Pan-Singleton(2000)模型的特例,但是这个模型存在解析解,而Duffie-Pan-Singleton模型并不存在解析解.模型的解析解对获得直觉的判断和进行模型的计算都非常有帮助,而且模型的解析解对实证检验也是有帮助的.     

基于可信性理论的生产计划期望值模型

基于可信性理论,提出一类新的模糊生产计划期望值模型.然后,讨论这个模糊生产计划模型的基本性质.最后,利用这个模糊模型的基本性质我们可以把模糊生产计划期望值模型转化为一个线性规划模型并且设计相应的算法求解模糊生产计划问题的一个数值例子.     

模糊反向物流网络设计模型的一种改进遗传算法

反向物流是物流研究中的一个重要分支,其相关问题是目前研究的热点问题。该研究在模糊环境中根据不同的决策标准,建立了关于反向物流问题中的回收问题的三种不同类型的模型:期望值模型,机会约束模型和相关机会模型,并设计了一个模糊模拟和遗传算法相结合的混合智能算法来解决提出的模型,最后给出了一个数值例子,结果证明了将此混合智能算法用于求解模糊反向物流网络设计模型问题的有效性。     

部分线性函数多项式模型的联合探测北大核心CSCD

本文提出了一个新的部分线性函数多项式回归模型,该模型中响应变量依赖于一个p阶函数多项式和一些非函数型数据的协变量．函数多项式模型、函数线性模型和部分函数线性模型是该模型的特殊情形．本文提出了一个模型探测方法,它能同时探测部分线性函数多项式回归模型中哪些阶是重要的以及哪些非函数型变量是重要的．提出的方法能相合地识别真实的模型并有好的预测表现．数值模拟能清晰地证实我们的理论结果．     

电路二等分问题的一个强化半定松驰模型

由于电路二等分问题在超大规模集成电路 (VLSI)设计中的基础地位 ,电路二等分半定松驰问题一直引人关注 .能否找到更好的半定规划模型 ,使其为电路二等分问题提供一个更好的下界 ,成为一个重要的研究方向 ;本文在已有半定规划松驰模型的基础上 ,通过增加非线性约束 ,得出电路二等分问题的等价模型 ,再利用提升技巧 ,得到一个强化半定规划松驰模型 .理论证明该模型给出了原有问题的一个更好的下界 ,数值实验也说明了这一点 .     

模糊环境下动态供应商选择的混合整数非线性规划模型

基于供应商选择问题的动态性和模糊性,考虑在每个周期内生产商的需求能力及供应商的供应能力为模糊变量,本文将一个多阶段多商品多渠道的供应商选择问题视为一个0-1混合整数模糊动态非线性规划问题,目标函数为总成本最小化。然后建立了0-1混合整数模糊动态非线性规划模型。为了求解该模型,通过可信性理论把模型中模糊机会约束清晰化,将该模型转化为一个确定型的0-1混合整数动态非线性规划模型。最后给出了一个数值算例验证了模型的可行性。     

Kumaraswamy Binomial分布

在Binomial模型中考虑over-dispersion时,每一个独立事件成功的概率通常被视为一个连续随机变量.在本文中,我们提出了成功概率服从Kumaraswamy分布的混合Binomial模型.讨论了这个模型的随机序和相依性;并用数据来拟合这些模型,数值计算结果表明在拟合某些数据时KB模型比BB模型拟合效果更好.     

Ruin theory in the linear model

The probability of ruin is examined in a model where the annual gains of an insurance company are dependent random variables. The model used is the linear model (well known in time-series analysis) which includes the autoregressive model and the moving average model as special cases. It is also shown that a certain credibility model can be interpreted as a first-order model of the mixed type.     

Non-linear model parameter estimation–estimating a feasible parameter set with respect to model use

This article deals with non-linear model parameter estimation from experimental data. As for non-linear models a rigorous identifiability analysis is difficult to perform, parameter estimation is performed in such a way that uncertainty in the estimated parameter values is represented by the range of model use results when the model is used for a certain purpose. Using this approach, the article presents a simulation study where the objective is to discover whether the estimation of model parameters can be improved, so that a small enough range of model use results is obtained. The results of the study indicate that from plant measurements available for the estimation of model parameters, it is possible to extract data that are important for the estimation of model parameters relative to a certain model use. If these data are improved by a proper measurement campaign (e.g. proper choice of measured variables, better accuracy, higher measurement frequency) it is to be expected that a valid model for a certain model use will be obtained. The simulation study is performed for an activated sludge model from wastewater treatment, while the estimation of model parameters is done by Monte Carlo simulation.     

论大学数学实验课的教学设计

数学既是演绎科学也是实验科学,大学数学实验体现了数学的教育价值.大学数学实验课的教学设计范式包括:基础实验式和综合实验式,基础实验式包括验证性实验式和计算性实验式,综合实验式包括探索性实验式(探究、猜想、模拟)和应用性实验式.针对不同的实验内容,采用不同的教学设计范式来提高大学数学实验课的教学效率.     

A duopolistic model of dynamic competitive advertising

This paper proposes a differential game model of competitive advertising decisions for non-durable products by extending the Lanchester model and the Deal model of competitive advertising in the literature. The proposed model is compared empirically with the Lanchester model for model fitting and forecast accuracy. It is shown that the model is suitable for an actual market and out-performs the Lanchester model in forecast accuracy. The model provides a sensible modeling alternative to the Lanchester model for the study of dynamic competitive advertising decisions. Necessary and sufficient conditions for open-loop and closed-loop Nash equilibrium solutions to the model are discussed. A numerical algorithm for open-loop and closed-loop Nash strategies to the model is developed.     

Neural net versus classical models for the detection and localization of leaks in pipelines

Four models of a pipeline are compared in the paper: a nonlinear distributed-parameter model, a linear distributed-parameter model, a simplified lumped-parameter model and an extended neural-net-based model. The transcendental transfer function of the linearized model is obtained by a Laplace transformation and corresponding initial and boundary conditions. The lumped-parameter model is obtained by a Taylor series extension of the transencdental transfer function. Based on the experience of linear models the structure of the neural net model, as an addendum to the nonlinear distributed-parameter model, is obtained. All four models are tested on a real pipeline data with an artificially generated leak.     

Four equivalent lot-sizing models

We study the following lot-sizing models that recently appeared in the literature: a lot-sizing model with a remanufacturing option, a lot-sizing model with production time windows, and a lot-sizing model with cumulative capacities. We show the equivalence of these models with a classical model: the lot-sizing model with inventory bounds.     

A novel grey forecasting model and its optimization

Although the grey forecasting model has been successfully employed in many fields and demonstrated promising results, its prediction results may be inaccurate sometimes. For the purposes of enhancing the predictive performance of grey forecasting model and enlarging its suitable ranges, this paper puts forward a novel grey forecasting model termed NGM model and its optimized model, develops a calculative formula for solving the parameters of the novel NGM model through the least squares method, and obtains the time response sequence of NGM model by using differential equation as a procedure for reasoning. It performs a numerical demonstration on the prediction accuracy of NGM model and its optimized models. As shown in the results, the proposed model and it optimized model can enhance the prediction accuracy. Numerical results illustrate that the proposed NGM model and its optimized model are effective. They are suitable for predicting the data sequence with the characteristics of non-homogeneous exponential law. This work makes important contribution to the enrichment of grey prediction theory.     

A Hessian Regularized Nonlinear Time Series Model

We introduce a nonparametric nonlinear time series model. The novel idea is to fit a model via penalization, where the penalty term is an unbiased estimator of the integrated Hessian of the underlying function. The underlying model assumption is very general: it has Hessian almost everywhere in its domain. Numerical experiments demonstrate that our model has better predictive power: if the underlying model complies with an existing parametric/semiparametric form (e.g., a threshold autoregressive model (TAR), an additive autoregressive model (AAR), or a functional coefficient autoregressive model (FAR)), our model performs comparably; if the underlying model does not comply with any preexisting form, our model outperforms in nearly all simulations. We name our model a Hessian regularized nonlinear model for time series (HRM). We conjecture on theoretical properties and use simulations to verify. Our method can be viewed as a way to generalize splines to high dimensions (when the number of variates is more than three), under which an analogous analytical derivation cannot work due to the curse of dimensionality. Supplemental materials are provided, and will help readers reproduce all results in the article.     

VLES turbulence model for an Eulerian–Lagrangian modeling concept for bubble plumes

Traditional Reynolds-averaged Navier–Stokes (RANS) approaches to turbulence modeling, such as the k-ϵ model, have some well-known shortcomings when modeling transient flow phenomena. To mitigate this, a filtered URANS model has been derived where turbulent structures larger than a given filter size (typically grid size) is captured by the flow equations and smaller structures are modeled according to a modified k-ϵ model. This modeling approach is also known as a VLES model (Very Large Eddy Scale model), and provides more details of the transient turbulence than the k-ϵ model at little extra computational cost.In this study a two-phase extension to the VLES model is described. A modeling concept for bubble plumes has been developed in which the bubbles are tracked as particles and the flow of liquid is solved by the Navier–Stokes equations in a traditional mesh based approach. The flow of bubbles and liquid is coupled in an Eulerian–Lagrangian model. Turbulent dispersion of the bubbles is treated by a random walk model. The random walk model depends on an estimation of the eddy life time. The eddy life time for the VLES model differs from a k-ϵ model, and its mathematical expression is derived.The model is applied to ocean plumes emanating from discharge of gas at the ocean floor. Validation with experiments and comparison with k-ϵ model are shown.     

带有不可忽略缺失数据的广义部分线性模型的贝叶斯分析

广义部分线性模型是广义线性模型和部分线性模型的推广,是一种应用广泛的半参数模型.本文讨论的是该模型在线性协变量和响应变量均存在非随机缺失数据情形下参数的Bayes估计和基于Bayes因子的模型选择问题,在分析过程中,采用了惩罚样条来估计模型中的非参数成分,并建立了Bayes层次模型;为了解决Gibbs抽样过程中因参数高度相关带来的混合性差以及因维数增加导致出现不稳定性的问题,引入了潜变量做为添加数据并应用了压缩Gibbs抽样方法,改进了收敛性;同时,为了避免计算多重积分,利用了M-H算法估计边缘密度函数后计算Bayes因子,为模型的选择比较提供了一种准则.最后,通过模拟和实例验证了所给方法的有效性.