线性模型M—估计下误差密度估计的相合性

线性模型Ｙｉ＝ｘ′ｉβ＋ｅｉ,ｉ＝１,２,…,其中ｅｉ｛｝∞ｉ＝１ｉｄ．,有未知密度ｆ（ｘ）．讨论了在对β作一般估计后,基于残差作出的误差密度核估计的相合性．在比文献［７,８］弱的条件下,证明了误差密度核估计的逐点弱相合,逐点强相合和一致强相合．     

基于量化的DCT系数统计特性的运动残差编码算法

针对离散余弦变换(DCT)的运动残差编码效率低下的问题,从残差量化DCT系数的统计特性出发,提出了一种全新的运动残差视频编码算法.对于残差的非零量化DCT系数,按照其在当前编码图像中对应位置的量化DCT系数是否为零被分为两类,然后分别对两类不同的残差量化DCT系数逐类进行编码.本算法在编码效率上相对于MPEG2编码方法可提高2～2.5 dB.     

线性边值问题的一类新型边界元法

本文由加权残值法导出了边界元法的一类新型积分公式,并提出了相应的内点公式和边界点公式联立求解方法。在这类公式中,不一定要取权函数为控制方程的基本解,在许多问题中。当用常规边界元法而找不到基本解时,可以改用本文的新型积分公式来解决。本文给出了这类积分方程的一般推导方法,就一些具体线性边值问题作了讨论,建立了相应的积分公式和求解方法。这种方法为用边界元法求解名类问题编制系统电算程序提供了方便。     

大挠度缺陷旋转壳数值分析

借助于微分几何、矢量分析的工具,导出了小应变、大转动、大位移薄壳考虑初始几何缺陷的非线性几何方程,用双向样条试函数及离散最小二乘配点法给出了残值表达式,采用联合法求解,以降低初值要求,减少求逆运算及避免奇异出现,算例证明:本文方法未知量少、精度好、计算速度快、占用计算机内存少。     

Utilizing Water Treatment Residuals for Phosphorus Removal: Batch Trials,Column Trials and Effects of Three Low-Molecular-Weight Organic Acids

Phosphorus（ P） has been recognized as a major limited nutrient responsible for the eutrophication of surface waters. Water treatment residuals（ WTRs） are safe by-products of water treatment plants and are cost-efficient adsorbents. In this study, batch experiments and column experiments based on WTRs were employed to study the characteristics of P adsorption and the effects of lowmolecular-weight organic acids（ LMWOAs）（ citric acid, oxalic acid,and tartaric acid） on P adsorption. Different models of adsorption were used to describe equilibrium and kinetic data. The adsorption data were fitted well by a pseudo-second order kinetic model. The adsorption process was determined to be controlled by three steps of diffusion mechanisms through the intra-particle model.The adsorption equilibrium was well described by the Langmuir,Freundlich,Redlich-Peterson,and Sips isotherm models. Batch and continuous flow experiments indicated that the LMWOAs exhibited inhibitory action,and as pH increased,the inhibitory action became weaker for all the three acids. The effect of LMWOAs concentration was not significant on inhibition. The effects of LMWOAs were closely related to reaction time.     

改进的基于残差加权的稀疏表示人脸识别

为进一步有效提升稀疏表示人脸识别系统的识别率和可靠性,在分析人脸图像稀疏表示系数分类能力的基础上,提出了一种基于残差加权的稀疏表示人脸识别新方法.该方法通过对类残差图像关于所属类稀疏表示系数的l2范数进行归一化加权,有效提升了原始基于类残差判决的识别能力.仿真实验结果表明：改进的基于残差加权的稀疏表示方法能够有效提高系统的识别性能.     

高速公路交通量预测的GM(1,1)残差改进模型

针对传统GM(1,1)模型在预测高速公路交通量中存在误差过大、计算复杂的问题,通过定义残差序列,对预测序列与残差序列进行累加再处理,构造新的序列数据;并且对新序列数据构造GM(1,1)残差改进模型,以进行预测。模型应用于某高速公路某收费站,对9期序列数据进行了模拟预测。结果表明,GM(1,1)残差改进模型的平均预测误差为7.25%,优于传统GM(1,1)模型预测的平均相对误差12.7%。     

关于学生化残差的一点注记

残差分析在回归诊断中十分重要,常用的残差有普通残差δi、内学生化残差ri和外学生化残差ri等.本文通过影响函数推导出ri和ri间一个关系式.     

我国高等教育与区域经济增长相互关系的定量分析

以每万人口中大学生数的对数为因变量,以人均GDP的对数为自变量,利用计量经济的方法,建立了我国除北京、天津、上海、重庆外的27个省、自治区的1990-2005年期间的两变量之间的线性回归模型和1994-2005年期间的固定效应变截距面板模型.采用残差分析的方法来分析我国高等教育与区域经济增长的不协调性问题,并讨论了几个典型省份在此期间不协调状况的时间变化趋势及全国不协调状况的总体变化趋势.     

Some comparisons of the relative power of simple tests for structural change in regression models

The power of Chow, linear, predictive failure and cusum of squares tests to detect structural change is compared in a two-variable random walk model and a once-for-all parameter shift model. In each case the linear test has greatest power, followed by the Chow test. It is suggested that the linear test be used as the basic general test for structural change in time series data, and tests of forecasting performance be confined to the last few observations. Analysis of recursive residuals and recursive parameter estimates should be regarded as forms of exploratory data analysis and tools for understanding discrepancies with previous results rather than a basis for formal tests of structural change.