线性模型

结果表明，线性模型有较强的定性分析作用但预测能力不强，而BP网络具有很强的预测能力。

The result showed that the linear model had strong qualitative analysis .

误差为MA（q）序列线性模型回归参数的近似M估计

Approximate M-estimates of Parameters in Linear Model with MA ( q ) Noise

这N个线性模型能够很好地近似原非线性模型。

Then N linearly simple models are obtained to represent the nonlinear ship model .

该文研究混合线性模型效应参数的Bayes局部影响评价问题。

This paper studies Bayes local influence in mixed linear model .

线性模型中参数向量的线性经验Bayes估计

A Linear Empirical Bayes Estimator of Parameter Vector in Linear Regression Model

线性模型的BL估计和BP估计

BL and BP estimates in linear models

具有MA（q）误差线性模型协方差阵参数的分步估计与Bootstrap算法

Two Steps Method and Bootstrap Algorithm for Covariance Parameters for Credibility Regression Models with Moving Average Errors

并对其作了适当的简化以得到线性模型，借鉴CT中的代数重建技术（ART）来进行求解。

Afterward , ART ( Algebra Reconstruction Technique ) which has been widely applied in CT ( Computerized Tomography ) field is used to search the solution of the model .

混合系数线性模型参数的Stein估计

Stein Shrunken Estimates of Parameters for Mixed-Effect Coefficient Linear Model

提出了一种基于三线性模型的多径信道中多用户检测和波达方向（directionofarrival，DOA）估计联合处理方法。

Joint processing of the multiuser detection and the direction of arrival ( DOA ) estimation in a multipath channel based on the trilinear model is presented .

当逐步回归法的前提条件不具备时，可考虑采用GM（1，n）灰色模型或广义线性模型。

If the premise condition to apply the step regression method is not satisfied , we can use GM ( 1 , n ) grey model or general linear model .

降秩多元线性模型参数阵的BLU估计

BLU Estimator of Parameter Matrix in Multivariate Linear Model with Deficient Rank

首先，采用传统方法，基于对象的简化线性模型来设计PI控制器，然后利用自适应模糊技术对摩擦干扰进行补偿。

First , a PI controller is designed based on the simplified linear model of motor system . Then , an adaptive fuzzy technique is used to compensate friction interference .

结果表明，采用非线性的BP神经网络方法其训练效果与预测效果均优于线性模型方法；

The accuracy of the model proposed was tested in four compounds , and it was shown that the non-linear model fitted by BP neural network analysis provides much better predictions than the commonly used linear models .

结果：采用混合线性模型协方差分析发现，与婴幼儿生长密切相关的主要因素为月龄、是否SGA、性别和出生体重；

Results : Mixed linear models statistical method revealed that the main factors of child growth were age , SGA or not , gender and birth weight .

通过广义线性模型（generalizedlinearmodels，GLM）拟合了草本层物种丰富度与地形因子、土壤因子以及地形相对湿度指数（TRMI）之间的关系。

The species richness of herb layer was fitted in the topographic and soil feature factors , as well as the topographic relative moisture index ( TRMI ) by the generalized linear models ( GLM ) .

所采用的网络为一种将线性模型与多层前向网络相结合的DLF网络。

The neural network used is called DLF network , which is the combination of multilayer feedforward network with linear model .

利用广义估计方程（GEE）和混合线性模型分析农药对大鼠体重的影响情况。

The change of rats ' weight is analyzed via generalized estimating equations ( GEE ) and mixed linear model and the order is sex > cypermethrin > methylparathion .

因此RTT时间序列能用线性模型从过去的和当前的RTT数据来预测其下一个RTT的特性。

Based on these findings , it is concluded that RTT time series can be characterized by linear models in estimating next RTT from past and current observations .

而考虑了文本特征及分类信息的潜在语义文本分类模型（LSC）也因为本质上是线性模型而性能不高。

A latent semantic classification LSC model , which considers both text feature and classification information , is virtually a linear model and could not gain higher effectiveness .

本文利用计算机数字仿真技术建立了平稳时间序列的线性模型的模拟模型，得到了该系统状态模拟模型的随机差分方程，给出了ARMA（p，q）模拟模型的新息递推方程。

In this paper , the simulations of linear models of stational time series are given by CAD , and obtain their stochastic difference equations . The equation for new information of simulation of ARMA ( p , q ) model is given in recursive form .

然而，本质上FDI与GDP之间存在非线性关系，略去非线性关系，用线性模型还不能深刻揭示FDI对GDP增长的作用。

Although it has been a generally accepted conclusion that there exists a linear relationship between FDI and GDP , essentially there is a nonlinear connection between them : omitting their nonlinear relations , we cannot profoundly reveal the effect of FDI upon the FDI growth .

应用广义线性模型通过对指数分布和Weibull分布的检验提出了对贮存寿命分布进行拟合检验的方法，并通过一数值例子说明这一方法的实用性。

Some methods of fitting test for storage life distributions using Generalized Linear Models ( GLM ) are proposed ; These methods are shown by testing exponential distribution and Weibull distribution , The utility of the methods is illustrated by a numerical example .

研究了非高斯噪声中具有未知参数的信号的渐进最优检测，应用非高斯噪声中线性模型信号以及随机信号的Rao检验，导出了Rao检测的解析式，并与广义似然比检验的性能做比较。

Insensible optimal detection method of unknown parameter signal in non-Gaussian noise is introduced . The analytic expression of Rao detection is presented based on the Rao detection of linear signal and random signal in non-Gaussian noise .

本论文从系统角度出发，以神经纤维为研究对象，基于FHN模型，利用近似的二极管模型，首先分析神经细胞的一阶线性模型，引入恢复变量，建立神经细胞的二阶线性模型。

Based on the diode model , the first order linear model is analyzed . After introducing the recovery variable into it , the second order linear model is built .

生产车间设备布局线性模型及算法研究

Research on Machine Layout Linear Model & Algorithm for Production Shop

摄像机线性模型标定中一种投影矩阵的修正方法

A Modification Approach for Projection Matrix in Camera Linear Model Calibration

将非线性混沌系统模糊化为局部线性模型。

The nonlinear chaotic system has been fuzzy into local linear model .

部分线性模型中非参数估计的强相合性

Strong Consistency of a Class of Nonparametric Estimators in Partial Linear Model

线性模型中的约束型有偏估计的研究

Study on the Restricted Biased Estimation in the Linear Model