形式模型

We first state general linear model, ridge-type estimator and general ridge-type estimator, and the constraint biased estimator. And then, we introduce some basic theory about matrix and some conclusion about the admissibility of estimator in Gauss-Markov model. In the third chapter, we discussion several equivalent characterization of the best linear unbiased estimation, we proved that admissible characterization of admissible of linear estimation is as conditional general ridge-type estimation in general linear model. A necessary and sufficient condition that homogeneous linear estimator is admissible estimator is obtained.

本文首先概述了一般线性模型，岭估计及约束岭估计的发展历史和研究现状，在第二章介绍了矩阵的一些基本知识和可容许性的一些基本结论，第三章讨论了一般线性模型最佳线性无偏估计的几个等价条件，以及线性估计的可容许性特征，得到了一般线性模型的可容许线性估计均具有条件广义岭估计的形式，给出了一个齐次线性估计为可容许估计的充分必要条件。

On the basis of analyzing the classification principle of Bayesian classification model and a variant of Bayes theorem, a new classification model based on Bayes theorem, DLBAN (double-level Bayesian network augmented naive Bayes), which adds the dependence among attributes by selecting the key attributes, is proposed.

通过分析贝叶斯分类模型的分类原则以及贝叶斯定理的变异形式，提出了一种基于贝叶斯定理的新的分类模型DLBAN(double-level Bayesian network augmented naive Bayes)。该模型通过选择关键属性建立属性之间的依赖关系。

Large disparities can be found in textbooks' treatments of different neoclassical growth models. Models without technical progress and with exogenous technical progress deliver themselves of dynamic equations of capital per labor and capital per efficient labor, respectively. Models with endogenous technical progress, however, make consistent use of dynamic equations of output-capital ratio.

各类新古典增长模型在现有教科书中的表述形式存在很大的差异：无技术进步和外生技术进步的模型分别使用"劳均资本"和"有效劳均资本"的动态方程，内生技术进步的模型则使用"产出资本比"的动态方程。

It solves the problem that the unitary contour presentation can not correctly extract face contour in a face image which suffers from scale, rotation etc. The definition of the internal and external energy function is provided. At the same time, the global matching algorithm and local matching algorithm is given. The experiment shows that this presentation and the accompanying matching algorithm can be used to extract the face contour very well. So the image segmentation can be implemented by using it.②By analyzing the recognition principle of PCA method, we can conclude that the face images coming from different surrounding consist of different face image space. This is the essential reason that makes the generality of PCA method worse. Also, we give a measurement means to measure the distance from different face image space, so we can analyze face image space more conveniently.③We also construct various scale models and rotation pose models to detect the scale and rotating angle of face image to be recognized. The experiment results show that the detecting precision is very high. So it is good for face image feature extraction and face image representation.④Similarly, we construct local feature models of face image and utilize them to detect the local feature of face image. At the same time, we put forward a novel face image local feature detection algorithm, locating step by step. The experiment results show that this method can accurately detect the location of local face feature in a image.⑤A novel face image presentation model, dual attribute graph , is put forward. Firstly, it utilizes attribute graph to present the face image, then exact the local principal component coefficient and Gabor transform coefficient of thc pixels which corresponds to the nodes of the graph as the attribute of the nodes. This representation fully makes use of the statistical characteristic of the local face feature and utilizes Gabor transform to present the topographical structure of face image. So DAG has more general property.⑥Based on the DAG presentation, we give a DAG matching function and matching algorithm. During the design of the function and algorithm, the noise factor, e. g., lighting, scale and rotation pose are considered and tried to be eliminated. So the algorithm can give more general property.⑦A general face image recognition system is implemented. The experiment show the system can get better recognition performance under the noise surrounding of lighting, scale and rotation pose.

本文在上述研究的基础上，取得了如下主要研究成果：①构造了一个通用的人脸轮廓模型表示，解决了由于人脸图象尺度、旋转等因素而使得仅用单一轮廓表示无法正确提取人脸轮廓的问题，并给出了模型内、外能函数的定义，同时给出了模型的全局与局部匹配算法，实验表明，使用这种表示形式以及匹配算法，能够较好地提取人脸图象的轮廓，可实际用于人脸图象的分割；②深入分析了PCA方法的识别机制，得出不同成象条件下的人脸图象构成不同的人脸图象空间的结论，同时指出这也是造成PCA方法通用性较差的本质原因，并给出了不同人脸空间距离的一种度量方法，使用该度量方法能够直观地对人脸图象空间进行分析；③构造了各种尺度模板、旋转姿势模板以用于探测待识人脸图象的尺度、旋转角度，实验结果表明，探测精确度很高，从而有利于人脸图象特征提取，以及图象的有效表示；④构造了人脸图象的各局部特征模板，用于人脸图象局部特征的探测；同时提出了一种新的人脸图象局部特征探测法---逐步求精定位法，实验结果表明，使用这种方法能够精确地得到人脸图象各局部特征的位置；⑤提出了一种新的人脸图象表示法---双属性图表示法；利用属性图来表示人脸图象，并提取图节点对应图象位置的局部主成分特征系数以及Gabor变换系数作为图节点的属性，这种表示方法充分利用了人脸图象的局部特征的统计特性，并且使用Gabor变换来反映人脸图象的拓扑结构，从而使得双属性图表示法具有较强的通用性；⑥在双属性图表示的基础上，给出双属性图匹配函数及匹配算法，在函数及算法设计过程中，考虑并解决了光照、尺度、旋转姿势变化等因素对人脸图象识别的影响，使得匹配算法具有较强的通用性；⑦设计并实现了一个通用的人脸图象识别系统，实验结果表明，该系统在图象光照、尺度、旋转姿势情况下，得到了较好的识别效果。

This paper disserts the represent form of space data model, and discusses three dimensional space data model based on the grid, and points out the integrated necessariness and integrated represent method about the grid-vector spatial data model, and provids a Euclidean distance converting model and algorithm with regard to change from vector data to grid data, as well as establishes the foundation for spatial data handing and spatial data mining.

文章论述了空间数据模型的表示形式，重点讨论了基于栅格的三维空间数据模型，指出了栅格矢量空间数据模型集成化的必要性以及集成化表示方法，给出了将矢量数据转换为栅格数据的欧氏距离变换与算法，为基于栅格空间数据的空间数据处理和空间数据挖掘奠定了基础。

Two kinds of models by estimating pool equations and panel estimation have been constructed. Based on the idea of Reduced Form Model, by adopting lags-adjustment or not, time-series dynamics models of the fluctuation of urban residential real estate market, in which the endogenetic and the exogenous sensitive variable include, have been estimated. In logarithmic form the models are applied in a case.

同时，借助缩约模型的基本思想，将住宅市场波动的外生和内生敏感性因素纳入到城市住宅市场的动态分析中，从纵向角度引入非时滞调整和时滞调整的两类模式，构筑了不同形式的住宅市场波动的时序动态模型，采用对数模型估算案例城市商品住宅市场的时序动态波动状况。

Studied present measuring methods" advantages and disadvantages, and presented the necessity and importance of researching propellant transient heat transfer.2.according to 130 and aeronautic 90 rocket projectiles" structure, analysed and acquired physical and mathematical models for propellant transient heat transfer, also designed propellant temperature field simulation units for test.3.acquired discrete transient heat balance equation and temperature calculation program, and gave contrasting curves between experimental temperature values and program calculating temperature values as well as maximum errors and average square root errors between them.4.by programs based on the first class boundary condition, worked out temperature distribution in propellant temperature field simulation units at different time, analysed temperature field distribution law and main elements affecting heat transfer, acquired propellant mass weighted average temperature and one at the half position of propellant maximum thickness as well as maximum errors and average square root errors between them.5.established transient heat transfer mathematical model and temperature calculation program for the third class boundary condition, drew contrasting curves between temperature experimental values and calculation values and gave maximum errors and average square root errors between them, got temperature distribution in the simulation unit at different time and main elements affecting heat conduction, figured out propellant mass weighted average temperature and one at the half position of propellant maximum thickness as well as maximum errors and average square root errors between them.

分析了现有测试方法的优缺点，提出了研究推进剂瞬态导热的必要性和重要性。 2。根据130和航90两种火箭弹的结构，分析得到了推进剂传热的物理模型和数学模型，设计了推进剂温度场模拟实验装置。 3。得到了离散形式的瞬态热平衡方程和温度场计算程序，给出了实验温度与程序计算温度值的对比曲线及其最大偏差与均方差。 4。利用程序求出了第一类边界条件下、不同时刻推进剂温度场模拟装置中的温度分布，分析了温度场的分布规律和影响传热的主要因素，求出了推进剂质量加权平均温度和最大肉厚1／2处的温度时间曲线并给出了两者之间的最大偏差与均方差。 5。建立了第三类边界条件下的瞬态导热数学模型和温度计算程序，求出了温度实测值与计算值的对比曲线并给出了两者之间的最大偏差与均方差，得到了不同时刻温度场模拟装置的温度分布与影响导热的主要因素，求出了推进剂质量加权平均温度和最大肉厚1／2处温度及两者之间的最大偏差与均方差，讨论并确定了能代表130和航90推进剂温度的特征点的位置。

Based on the Saint-venant equations describing the channel flow movement, the nonlinear algebraic equations derived by the use of Preissmann weighted implicit four-point scheme are solved with the Netwon-Raphson method. A combined Gauss main-element elimination method with compress-storage technique is proposed. The relaxation iterative method for solving branch river networks is extended, which can turn the problem of any complex river networks into the problem of a series of single rivers. The coupling of hydraulic model with water quality model is built up. The combined model was applied to a large complicated river networks with numerical hydraulic structure which influenced by strong tide, storm and heave rain. Visualization of computational results is realized by means of MapInfo, which displays the computational results in fast, convenient and accurate way.

水力模型以描述河道洪水波运动的Saint-Venant方程组为基础，用Newton-Raphson方法直接求解按Preissmann加权四点格式进行离散所得的非线性代数方程组，提出了压缩存贮形式的Gauss列主元消去法并对数值解的收敛性进行了讨论；将支流流量的松弛迭代方法从树状河系推广到了环状河网，使任意复杂河网水力计算的问题都可化为一系列的单一河道的水力计算问题；建立了水力模型与水质模型的联接，初步应用于既有洪水、暴雨、强潮等综合影响，又存在多种水工建筑物及水力调度问题的大型复杂河网中的非恒定流水力、水质计算问题；利用MapInfo对计算结果的可视化进行了研究，有利于决策者快速、方便、准确地作出决策。

This model can analyze the regression relation between covariate and log survival time, and its form and explanation of regression coefficient is close to the general linear regression equation, the explanation of analysis results is more simple, more direct and easier to understand than that of proportional hazard function model.

AFT模型研究协变量与对数生存时间之间的回归关系，模型的形式与对回归系数的解释与一般的线性回归方程相似，而对分析结果的解释则较比例风险回归模型简单、直观，更易于理解。

Mathematic proof of the hypertonicity for this model is given using two different cases. Furthermore, the Riemann invariants for the multi-class traffic flow LWR model are studied by using characteristic line method, and the physical interpret of the Riemann invariants are also pointed out. The information in transfer is obtained, that is, the total density and the relative density hold the same.

用两种方法给出了该模型在不同情形下双曲性的数学证明，运用特征线方法研究并计算了任意等级MCLWR交通流模型的Riemann不变量，得到了其传递的交通信息，给出了Riemann不变量物理意义的解释，即总密度保持不变和相对密度保持不变，最后又从形式上指出了在多等级车流并行时，MCLWR与LWR两种交通流模型实际上是等价的。

It has been put forward that there exists single Ball point and double Ball points on the symmetrical connecting-rod curves of equilateral mechanisms.

从鲍尔点的形成原理出发，分析对称连杆曲线上鲍尔点的产生条件，提出等边机构的对称连杆曲线上有单鲍尔点和双鲍尔点。

The factory affiliated to the Group primarily manufactures multiple-purpose pincers, baking kits, knives, scissors, kitchenware, gardening tools and beauty care kits as well as other hardware tools, the annual production value of which reaches US$ 30 million dollars.

集团所属工厂主要生产多用钳、烤具、刀具、剪刀、厨具、花园工具、美容套等五金产品，年生产总值3000万美元，产品价廉物美、选料上乘、质量保证，深受国内外客户的青睐