多值函数

The example are also given to show that the two Expect Bayes estimation formula are both steady and the precision of Expect Bayes estimation of the reliability for geometric distribution under the entropy loss function is higher than that of the square loss function.

通过实例验证，在熵损失函数下计算出的几何分布可靠度的多层Bayes估计是稳健的，并进一步表明在熵损失函数下计算出的几何分布可靠度的多层Bayes估计值比其在平方损失函数下算出的结果精度更高。

It is shown that many of the existing integral transforms (including their logically equivalents) such as chirplet transform, dispersion transform, wavelet transform, chirp-Fourier transform, short-time Fourier transform, Gabor transform, Fourier transform, cosine transform, sine transform, Hartley transform, Laplace transform, z transform, Mellin transform, Hilbert transform, autocorrelation function, cross-correlation function, and the energy and mean of a signal, can each be considered as a special case of the FMmlet transform with specific parameters. In fact, an inventory of subspaces of FMmlet transform runs into countless numbers. The subspaces mentioned above are merely a few among a zoo of subspaces. They are essentially obtained by cutting the transform space of FMmlet transform at different positions, and can be likened to the computed tomography in medical diagnosis. Through these subspaces we actually see different slices or profiles of the FMmlet transform.

将现有诸多变换置于统一的 FMmlet 变换中加以审视，发现 chirplet 变换、频散变换、小波变换、 chirp-Fourier 变换、短时 Fourier 变换、 Gabor 变换、 Fourier 变换、余弦变换、正弦变换、 Hartley 变换、 Laplace 变换、变换、 Mellin 变换、 Hilbert 变换、自相关函数、互相关函数、能量和均值等，均为 FMmlet 变换在其参数取特定值时的特例；上述诸变换之间的差别，主要在于变换空间的维数有别，以及在不同空间维上取值的不同；这些变换有如医学诊断中的 CT，均由压缩 FMmlet 变换域空间所致，可以说我们通过这些变换看到的，是 FMmlet 变换的不同剖面。

Because we mainly involve visual fields of medical science , have placed more contents on the development in the field of medical image of visual technology and argumentation used. Second part It is the visual technology knowledge, the generalization in such respects as the basic principle , basic functions, function store and three-dimensional animation technology to OpenGL ,etc. The realization of the system using OpenGL functions finish that three-dimension demonstration. The third part It is number value that calculate knowledge, three-dimension rebuild technology is it is it is it punish to fit to go on to need, the research of interpolator technology that cant leave, So this part has quoted the Hermite function principle , define cubic Hermite function to begin, calculate the differential coefficient among them draws cubic spline again.

由于我们主要是涉及医学可视化领域，所以将更多的内容放在了可视化技术在医学影像领域的发展与应用的论述；第二部分是可视化技术方面的知识，主要对 OpenGL 的基本原理、基本功能、函数库及三维动画技术等方面的概括，在系统实现时就是通过调用 OpenGL 函数库实现三维显示的；第三部分是数值计算方面的知识，三维重建技术需要进行拟合处理，离不开插值技术的研究，所以这一部分从埃尔米特函数原理开始讨论，引入三次埃尔米特函数，进一步计算时又引用三次样条函数。

The multivariate polynomial interpolation problem is a classical mathematical problem that is widely used in many fields, such as multivariate function list, surface design and finite element method. In recent years, multivariate polynomial interpolation has been focused by many people, of which the geometric topological struction of sets of interpolation nodes is also much concerned by us.

多元多项式插值问题是一个十分具有研究意义和实际应用价值的数学问题，它广泛应用于多元函数列表，以及曲面的外形设计和有限元法等诸多领域，近年来多元多项式插值越来越受到人们的广泛关注，其中有关插值结点组的几何拓扑结构问题也是人们十分关注的内容。1998年，梁学章和吕春梅在文献[2]中借助代数几何中的有关理论，进一步讨论了沿无重复分量平面代数曲线上的Lagrange插值问题，并应用Cayley ？

On the basis of determining interpolation neighborhood, this paper factures many geochemistry plots by using more spatial interpolation of the deep penetrating geochemical data in the study area. The methods include inverse distance weighted interpolation, global polynomial interpolation, local polynomial interpolation, radial basis function, simple Kriging and universal Kriging, etc.

文中在确定插值邻域的基础上，应用多种空间插值方法对研究区的深穿透地球化学数据制作了多个地球化学图，如反距离加权插值法、全局多项式插值法、局部多项式插值法、径向基函数法、简单克里金法、泛克里金法等。

In chapter 4, the relation between Fatou components of a transcendental meromorphic function or a transcendental meromorphic solution of some differential equation and the set of singular values is discussed, the main considered question is the relation between wandering domains or Baker domains and the set of singular values.

第四章讨论了超越亚纯函数或微分方程超越亚纯解Fatou分支与奇值集的关系问题，主要是研究游荡域或Baker域与奇值集的关系，得到在一定条件下，某些超越亚纯函数的多连通游荡域以及某些微分方程超越亚纯解的Baker域必定含有奇值。

And giving the way to own the biggest coefficient in an inferior expansion; The third is that showing the mathematic expectation for multinomial distribution, covariance matrix, characteristic function as well as generating function; Finally, introducing some application instances about gaining maximum value and some simple applications of multinomial distribution in reality.

并且给出了M项N次多项展开式中最大系数的求法；3。介绍多项分布的数学期望、协方差阵、特征函数以及母函数；最后，介绍多项分布最大值求法的应用事例以及多项分布在实际中的简单应用。

MethodsBy means of orthogonally rotational combination design, microwave extraction mathematical simulation model was concluded by the linear regression analysis.

响应面法是采用多元二次回归方程来拟合因素与响应值之间的函数关系，通过对函数响应面和等高线的分析，能够精确地研究各因子与响应值之间的关系，寻求最优工艺参数，解决多变量问题的一种统计方法［3］。

The first-part of this paper evaluates the main stability theories concerned and concludes the conceptualization steps and essentials covering the various methods. Different disturbed-measure functions are studied in terms of their formulations and characteristics. Both Lyapunov functions and TEFs can be constructed only in a heuristic way of case-by-case. Ignoring changes in the disturbed-measure function's value after clearing the fault, Lyapunov functions and TEFs are applicable to neither nonautonomous one-machine infinite-bus systems nor any multimachine systems. Moreover, TEFs cannot guarantee the sign of errors because they don't satisfy the conditions for Lyapunov functions.

作为第1篇，文中归纳出这3种方法的共同分析步骤和要素，并比较各种受扰程度函数，指出：李雅普诺夫函数和TEF的建立都必须从具体模型出发并只能依靠启发的方式，它们没有考虑受扰程度函数的值在故障清除后的变化，因此既不适用于复杂模型的单机系统，也不适用于任何多机系统；又由于这2种方法都基于很强的假设，故分析的误差可能非常大，而TEF法更是由于不满足李雅普诺夫函数的条件而可能得到冒进的结果。

In the training of HMM, referring to the auxiliary function in reference〓, and the method in reference〓 to get the estimations of the parameters of Markov chain, we define the likelihood function and auxiliary function for the maximum likelihood estimation of CDHMM, and then induce systematically the forward-backward algorithm and the re-estimation formulas for parameters of CDHMM.

在HMM的建模方面，本文借鉴文献〓中求多变量观测值马尔可夫链参数时辅助函数的选取方法，定义了CDHMM的似然函数和辅助函数；借鉴文献〓中求解马尔可夫链参数时的求偏导方法，并针对本文辅助函数加以简化和改进，系统地推导了HMM的前向—后向算法，以及CDHMM各参数的极大似然估计公式。

And discuss some key point of integrated management system design, include hazard identification and risk assessment and risk control in the occupational health and safety management, the measure of satisfaction target of customer, the flawlessness of law system, the integration of the integrated management system and enterprise standardization system, unify lead institution and work orgnization, integreted internal audit and integrated management review.

同时，论述了一体化管理体系构建中的几个主要问题，包括职业健康安全管理中的危险源辨识、风险评价和风险控制、顾客满意度的科学监测、法律、法规体系的完善、一体化管理体系与企业标准化体系的有机结合、统一的领导机构和工作机构、一体化的内部审核和管理评审。

Deepwater Taranaki is investigated for its petroleum potential, using all available seismic data tied to shallow-water wells.

运用与浅水井相关的现有全部震波探测数据考察了深海区塔拉纳基盆地的油藏前景。