多项式模型

Taking mapping QTL that affect leaf age growth trajectories in rice of a DH population as an example, we used 3 biological meaningful submodels and 2 orders Legendre polynomial to model the mean vector of QTL genotypes and 11 stationary and non-stationary models to fit residual covariance matrix.

以水稻一个DH群体的叶龄性状为例，我们分别用3个具有生物学意义的子模型和2阶Legendre多项式去拟合QTL基因型的均方向量，用13个平稳和非平稳模型去描述剩余协方差的变化。

Introduces the notion of Feynman's path integrals and path integrals approach to financial modeling; Derives the path-dependent options pricing formula by making use of the Lagrange form of path integrals; Discusses Ilinski(2003)'s Gauge model which based on path integrals and fibre bundle, and its application for real-options evaluation; Summarizes the general modeling framework of options evaluation, taking advantage of the Hamilton form of path integrals; Applies the Geske-Johnson's analytical approximation in the path integrals form to the real-options evaluation for investment decisions, detailed procedure is presented under the assumption that underlying asset price dynamic follows a geometric Brownian motion, and the integral reduction for multivariate normal integrals and polynomial approximation for real-options evaluation is given.

系统论述了路径积分概念方法及其在期权估值中的应用，利用路径积分方法的Lagrange表述推导了路径依赖期权定价公式：探讨了基于路径积分和纤维丛的Gauge模型思想方法在实物期权价值评估中的应用；利用路径积分的Hamilton表述形式，总结了基于Hamilton表述的期权估值一般化框架；基于路径积分的形式框架建立了一个新的投资期权估值模型，并在具体的估值算法中给出了多重正态积分的降阶计算和期权价值的多项式逼近方法。

The optimal amount of historical data for parameter estimation and for the determination of the order of error polynomial are studied by using real data.

结合实际数据研究了电价预测模型中参数辩识的最佳历史数据量及模型中残差多项式阶次的选择问题。

As to nonparametric and semiparametric regression models, the most widely used regression methods include: local smoothness, including Nadaraya-Watson kernel estimate, Gasser-Muller estimate, local polynomial method; spline method(such as smoothing spline, spline penalies and so on); other is orthogonal series estimates, such as Fourier series and so on.

本文主要介绍Nadaraya-Watson核估计方法对非参数模型估计的思路和估计方法，变系数模型中函数系数的局部多项式估计，包括估计思路，估计计算。

This paper considers a class of uncertainties with the polynomial function form of perturbation parameters, which is analogous to a fact that part information is known for some uncertainties.

考虑一类与摄动参数呈多项式函数关系的不确定性模型，这类模型反应了预知部分不确定性信息的物理意义。

Then, forecasting return is accomplished. Because of being free of probability distribution suppositions for the sale quantity and the return quantity, such as the binomial distribution and the polynomial distribution, the model is more flexible compared to previous forecasting models.

该预测方法的突出特点是，无需像以往预测模型那样假定回收量和前期销售量符合特定的概率分布(例如多项式概率分布或二项式分布)，因此模型具有较强的通用性。

The results show that the polynomial model based on least square method is the same as that based on FLANN network,demand of measurement can be satisfied with the model.

结果表明，基于多项式最小二乘和FLANN网络的模型基本相同，能够满足测量的要求，而基于BP网络的模型有着更高的辨识精度。

Based on the analysis of error, appropriate polynomial error model of the laser gyroscope is built to satisfy the error processing of the system. Recognition methods of model parameter and experiment results are given out as well.

在对其误差分析的基础上，建立了满足寻北系统误差处理需要的激光陀螺多项式误差模型，给出了模型参数的辨识方法和试验结果。

Many researchers have devoted their work to the development of modal analysis extraction techniques in order to obtain more reliable identification of the modal parameters. There are many damping identification methods, but each one has different merit and defect. In order to find which one is the most reliable method with respect to certain characteristics, this thesis focus on how to identify structure's damping in time domain. The following works have been done in this thesis: 1. Investigate four modal analysis methods——the LSCE Method, the Ibrahim Time Domain Method, the Time Domain Collectivity Modal Parameter Method, the Rational Fraction Polynomial Method and improve on the ITD Method in arithmetic.

本文主要做了如下工作： 1、集中研究了四种常用的模态识别方法，即最小二乘复指数法、Ibrahim时域法、时域总体模态参数辨识法及有理分式多项式法，并对ITD法在算法上进行了一定的改进； 2、建立结构动力模型，利用这四种方法在具体条件下识别结构的阻尼，并绘制相应的图； 3、讨论不同的情况下，不同的识别方法对阻尼识别精确性的影响； 4、基于业已明确的阻尼识别的精确性，根据研究的需要，指出在实际的识别过程中，如何选择最佳的识别方法以及识别过程中需要注意的问题； 5、选择最为精确的阻尼识别方法，以导师李书进教授在日本京都大学防灾研究所强震反应实验室所做的一足尺木制结构房屋的动力测试实验为实测模型，识别其阻尼； 6、在本文的最后，尽作者所知，提出了一些需要改进的地方，并对未来的研究方向给出了作者的建议。

RESULTS: The multiple component network pharmacokinetics follow a first order linear mammillary model. C is a polynomial of power index number e, which is similar to the whole compartment model. Various parameters were calculated by the expression of matrix consisting of α and the compartment parameters.

结果：药物多成分代谢网络动力学遵循一级线性乳突模型，c为e的幂指数多项式形式，与总室模型相似，各参数由其与各室间常数构成矩阵的特征值α的关系方程组算得。

Breath, muscle contraction of the buttocks; arch body, as far as possible to hold his head, right leg straight towards the ceiling (peg-leg knee in order to avoid muscle tension).

呼气，收缩臀部肌肉；拱起身体，尽量抬起头来，右腿伸直朝向天花板（膝微屈，以避免肌肉紧张）。

The cost of moving grain food products was unchanged from May, but year over year are up 8%.

粮食产品的运输费用与5月份相比没有变化，但却比去年同期高8％。