残差

并经残差分析和F检验证明了模型的有效性。

The model has been verified available with residual error and F test .

基于GM（1,1）的残差修正模型及应用

Residual Error Modified Model Based on GM ( 1,1 ) and its Application

海城大地震前远震P波走时残差的变化

Variations in teleseismic P wave residuals before the Haicheng earthquake

基于残差变化特性分析的双假设KALMAN滤波算法

Double Hypothesis Kalman Filter Based on Variety of Innovation Property

用logistic映射混沌点修正选权迭代法估计残差方法

On methods of modifying selection weight iteration and estimating residual error by logistic projected chaotic point

有AR残差的回归模型的参数估计和定阶

On determining the order and estimating the parameter for regression models with AR residuals

基于ANN和残差修正的电力系统短期负荷预测

Electric power system short-term load forecasting based on artificial neural network and residual error amendment

灰色残差GM（1,1）模型在大气二氧化硫预测中的应用

Application of remnant GM ( 1,1 ) to prediction of content of sulfur dioxide in atmosphere

用于Logistic回归诊断的经验Pearson残差图

Empirical Pearson residual plot in Logistic regression diagnostics

目前预测酸雨频率多采用传统的残差GM（1,1）模型。

We usually use the traditional remnant GM ( 1,1 ) model to forecast the acid rain frequency .

残差GM（1,1）模型平均相对误差为4.73%，模型精度为优。

Average relative error of ameliorated grey model ( 1,1 ) was 4.73 % , model accuracy was good .

基于DCT的残差自适应编码压缩

Image Residual Adaptive Encoding Based on DCT

可以证明，BP神经网络对自相关统计过程的控制能力高于休哈特控制图、残差控制图。

Can proof , the BP neural network on the relevant statistical process control ability than Hugh hart control charts , residual control chart .

残差X-图对平稳可逆ARMA过程数据的检验能力

Detection Capability of Residual X - Chart for Stationary Reversible ARMA Process Data

以山东省工业废水排放量为例，建立了GM（1，1）高阶残差预测模型。

As an example , such a model for predicting the discharge quantity of industrial wastewaters in Shandong province is developed .

使用灰色GM（1.1）残差修正模型获得较高精度条件的探讨

Inquiry into the condition for employing the grey gm ( 1:1 ) residual correction model to obtain higher class of accuracy

但是在处理运动残差时，DCT变换编码的效率很低。

But the coding efficiency of DCT will be low when it does with the motion residuals .

基于残差图像的ROI编码研究

ROI Coding Research Based on Residual Image

对模型显著性进行残差检验、F检验和Arrhenius检验。

The significance of the model was tested by residual test , F test and Arrhenius test .

周期性残差修正GM（1.1）在海事直接经济损失预测中的应用

Applying the Modifying of Periodicity Remnant Difference of GM ( 1.1 ) to the Forecast of the Direct Expense of Maritime Accident

第三，研究多层前馈神经网络及相应的BP（ErrorBackwardPropagation误差反向传播）算法，设计基于模型残差的故障分类器，并通过其来完成全局舵面的故障检测与分类。

Thirdly , Multi-layer Feed-forward ANN and Error Backward Propagation ( BP ) algorithm are studied and are utilized as control surfaces ' failure detection and sortation .

一种基于LPC残差的语音激励脉冲逼近方法

A New Method for Approaching Speech Exciting Pulse Based on LPC Residual

利用气象站点实测资料，建立多元回归方程，同时结合GIS插值，对模拟残差进行修正，得到研究区≥0℃年积温和年中降水量的模拟结果。

Based on meteorologic data , the paper established multi-regression equation to simulate ≥ 0 ℃ annual total temperatures and precipitation by amending the error with GIS interpolation .

残差噪声模型在PMC技术中的应用

A Novel Use of Residual Noise Model in PMC

本文从另一个角度提出了Class方法，先按最小方差原则，找到了截断变量的最优估计；再利用Class方法对区间截断数据作残差分析。

In this paper , A Class method was proposed . According to least variance rule , the best estimation of Interval-Censored data was found , and then residual was analyzed by the Class method .

利用远参考与Robust技术手段对新疆北天山地区大地电磁原始资料进行去噪处理，以及静态校正、逐级反演、梯度法、残差法等处理与综合地质解释，取得了较好成效。

Using the Far Reference and Robust methods , the magnetotelluric sounding data of Northern Tianshan region in Xinjiang Uygur Autonomous Region are processed and the geological interpretation is given .

对每一个IMF分量建立AR模型，取模型的自回归参数和残差的方差作为故障特征向量，并以此作为输入来建立支持向量机分类器，判断转子系统的工作状态和故障类型。

Then , the support vector machines used as fault classifiers are established to identify the condition and fault pattern of the rotor system .

分别通过对静态数据和星载数据进行仿真计算分析，提出了利用运用观测值的组合二次差分与电离层残差法联合进行星载GPS载波相位周跳探测及修复的方法；

According to the imitation computation and analysis , bring forward using the double difference of the observation value and the ionosphere remnant way to detect and repair the cycle slip .

研究方法：主成分分析法。利用主元相关变量残差统计量代替平方预测误差Q统计量，并采用累积方差贡献率及复相关系数确定PCA模型的主元数。

Method of principal components was employed . The principal components in PCA is decided by virtue of ( cumulative ) percent variance and multi-correlation coefficients .

目的探讨Cho/NAA残差Z积分（即CNI）在星形细胞瘤分级中的价值。

Objective To discuss the value of Cho / NAA residual Z-score for histological grading of astrocytoma .