关于非参数回归核估计的强相合性

令Z_n={(X_1,Y_1),(X_2,Y_2),…,(X_n,Y_n)}是来自于R~d×R~1随机向量(X,Y)的一个随机样本,m(x)是Y给定X=x时的回归函数,由m_n(x)表示m(x)的建基于Z_n的核估计,在加于核函数K(x)上的一般性条件下,我们得出m_n(x)的当E|Y|~p<∞,p>1时的强相合性.     

概率密度函数法研究重构吸引子的结构

Probability density function (PDF) method is proposed for analysing the structure of the reconstructed attractor in computing the correlation dimensions of RR intervals of ten normal old men.PDF contains important information about the spatial distribution of the phase points in the reconstructed attractor.To the best of our knowledge, it is the first time that the PDF method is put forward for the analysis of the reconstructed attractor structure.Numerical simulations demonstrate that the cardiac systems of healthy old men are about 6-6.5 dimensional complex dynamical systems.It is found that PDF is not symmetrically distributed when time delay is small, while PDF satisfies Gaussian distribution when time delay is big enough.A cluster effect mechanism is presented to explain this phenomenon.By studying the shape of PDFs, that the roles played by time delay are more important than embedding dimension in the reconstruction is clearly indicated.Results have demonstrated that the PDF method represents a promising numerical approach for the observation of the reconstructed attractor structure and may provide more information and new diagnostic potential of the analyzed cardiac system.     

Probability Density Function Method for Observing Reconstructed Attractor Structure

Probability density function (PDF) method is proposed for analysing the structure of the reconstructed attractor in computing the correlation dimensions of RR intervals of ten normal old men. PDF contains important information about the spatial distribution of the phase points in the reconstructed attractor. To the best of our knowledge, it is the first time that the PDF method is put forward for the analysis of the reconstructed attractor structure. Numerical simulations demonstrate that the cardiac systems of healthy old men are about 6 - 6.5 dimensional complex dynamical systems. It is found that PDF is not symmetrically distributed when time delay is small, while PDF satisfies Gaussian distribution when time delay is big enough. A cluster effect mechanism is presented to explain this phenomenon. By studying the shape of PDFs, that the roles played by time delay are more important than embedding dimension in the reconstruction is clearly indicated. Results have demonstrated that the PDF method represents a promising numerical approach for the observation of the reconstructed attractor structure and may provide more information and new diagnostic potential of the analyzed cardiac system.     

构式的操作界定：认知固化与条件概率

学界对构式范畴的争议源于没有厘清其理论／ 操作层面,本文提出基于频次的认知固化可以作为构式的操作界定。认知固化的渐变性、层级性、动态性对应构式的原型性、抽象度、动态性。通过对英语本族语者的关系代词取舍开展基于条件概率的共现词分析发现：1）隐性／ 显性关系代词从句呈现基于条件概率的认知固化,可以被界定为构式;2）隐性关系代词从句比显性关系代词从句更加靠近具体词语层面,认知加工负载更小。     

一般FPK方程近似求解的局部Galerkin方法

１　Ｉｎｔｒｏｄｕｃｔｉｏｎ　Ｔｈｅｓｔｏｃｈａｓｔｉｃｄｉｆｆｅｒｅｎｔｉａｌｅｑｕａｔｉｏｎｓ（ＳＤＥ）ａｒｅｕｓｅｄｉｎｍａｎｙａｒｅａｓｏｆｓｃｉｅｎｃｅａｎｄｅｎｇｉｎｅｅｒｉｎｇ．ＴｈｅｍａｉｎｐｕｒｐｏｓｅｆｏｒｓｏｌｖｉｎｇｐｒｏｂｌｅｍｓｗｉｔｈＳＤＥｉｓｔｏｏｂｔａｉｎｔｈｅｐｒｏｂａｂｉｌｉｔｙｄｅｎｓｉｔｙｆｕｎｃｔｉｏｎ（ＰＤＦ）ｏｆｔｈｅｓｔａｔｅｖａｒｉａｂｌｅｓｇｏｖｅｒｎｅｄｂｙｔｈｅＳＤＥｂｅｃａｕｓｅｍａｎｙｏｔｈｅｒｓｔａｔｉｓｔｉｃａｌａｎａｌｙｓｉｓａ…     

Adaptive foreground and shadow segmentation using hidden conditional random fields

Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).     

基于融合模板的均值移动头部跟踪算法(英文)

针对被跟踪头部目标特征状态随时间变化而与参考模板不匹配的问题,提出一种基于融合参考模板的均值移动算法,即将被跟踪目标在不同状态下所呈现出的不同特征使用采样的方法进行融合,如将头部跟踪过程中正面的肤色信息和后面的发色信息进行融合,从而形成一个包含不同特征的参考模板.在跟踪过程中,使用该融合模板可以有效地克服由被跟踪目标特征变化导致跟踪失败而不能实现头部连续跟踪的问题.通过头部跟踪实验可以看出,该算法实现了复杂环境下的具有360°旋转的头部跟踪,并且在一定程度上提高了跟踪精度.     

An alternative teaching method of conditional probabilities and Bayes' rule: an application of the truth table

This paper presents a comparison of three approaches to the teaching of probability to demonstrate how the truth table of elementary mathematical logic can be used to teach the calculations of conditional probabilities. Students are typically introduced to the topic of conditional probabilities—especially the ones that involve Bayes' rule—with the help of such traditional approaches as formula use or conversion to natural frequencies. The truth table approach is an alternative method for explaining the concept and calculation procedure of conditional probability and Bayes' rule.     

多调和算子Dirichlet特征值下界的一种估计

通过构造热核函数的部分和,我们给出了多调和算子Dirichlet特征值的一个新的下界估计,新的估计式推广了已有的特征值估计的结果。     

基于矩理论正态分布和均匀分布的比较

计算了正态分布和均匀分布的峰度系数,分析了它们的几何性质,并基于此系数比较了这两类分布的概率密度曲线。     

“穷者越穷,富者恒富”发展格局的动态演化与产业成因:1978-2006

本文使用非参数的核密度估计测算了中国省域间人均GDP分布的动态发展趋势,并进一步对导致这种趋势下的产业成因进行估算。主要研究结论:第一,省域间的人均GDP分布出现"穷者越穷,富者恒富"的两极分化格局,且大多数省域的发展陷于"贫困化陷阱"状态;第二,两极分化格局的产业分解显示,"极化"主要表现在第二、三产业在省域间发展的差距,而第一产业在省域间的发展基本不存在差距;第三,第二产业在省域间的差距中起着最重要的作用,但是随着中国加入WTO,其作用正趋于弱化,而原本不起作用的第三产业在省域间的差距的扩大填补了第二产业的弱化作用,但第一产业在省域间的分布有助于省域间人均GDP分布的趋同。     

判定条件极值的充分条件的Hesse矩阵

在本文中，我们给出了判定条件极值的充分条件的Hesse矩阵，为判定条件极值提供了一般的判定方法。     

非参数方法在沪深股市收益率分布的应用

沪深大盘指数的收益率分布函数并小服从通常人们所认为的正念分布。本采用一种新的方法——非参数核密度估计，对大盘指数的收益率分布函数进行研究。这种新方法不仅很好地刻画了收益率分布的尖峰和肥尾特征，而且比一股的正态分布更能捕捉市场的风险特征，结论也更加准确。     

贝塔分布的有关性质及应用探讨

讨论了贝塔分布的部分性质，并对其应用进行了探讨。     

Interior-point algorithm based on general kernel function for monotone linear complementarity problem

A polynomial interior-point algorithm is presented for monotone linear complementarity problem (MLCP) based on:a class of kernel functions with the general barrier term, which are called general kernel functions. Under the mild conditions for the barrier term, the complexity bound of algorithm in terms of such kernel function and its derivatives is obtained. The approach is actually an extension of the existing work which only used the specific kernel functions for the MLCP.     

多维随机变量函数密度的求解方法

针对多维随机变量函数密度的求解问题,利用增补变量法、变量变换法求出变换后变量的联合密度函数,再根据联合密度函数与边际密度的关系,积分得出了多维随机变量函数的密度.该求解方法不仅可以使得计算更加简便,而且可以简化运算过程.     

关于一维与二维随机变量函数的分布的探讨

从一维与二维随机变量函数的分布的一般求法出发,对一维情形,给出了当随机变量函数非单调时其分布的求法;对二维情形,用随机变量变换的方法分别给出了当逆变换单值与多值时其分布密度的计算公式,并得到了若干推论.     

一维线性谐振子的波函数和几率密度作图方法探讨

针对一维线性谐振子教学中的难点,阐述了如何利用厄密多项式的递归或递推公式,通过计算机画出线性谐振子的波函数和几率密度曲线.既方便了多媒体的教学,又加深了学生对一维线性谐振子的理解.最后对几种绘图方法的特点进行了讨论.     

基于噪声与阴影抑制多模态背景模型的运动物体检测

针对场景照明变化、模型初始化以及阴影等问题, 提出了一种用于视频监视系统运动物体检测的统计多模态背景模型. 通过相隔固定的帧差值阈值化得到背景样本值, 并采用高斯核密度估计方法计算背景灰度的概率密度函数. 利用像素的邻域信息来去除由于摄像机抖动和场景小运动产生的噪声. HMMD色彩信息用来检测和抑制运动投射阴影. 实验结果验证了算法在交通监控前景物体分割中的有效性.     

Relationship between Compostion,Density and Refractive Index for Heavy Metal Fluoride Glasses

The density and the refractive index for various compositions of heavy metal fluoride(HMF) glasses,used to make low-loss optical wave-guides,have been measured by standard archimedes method and by using as Pulfrich refrctometer respectively.The density as a function of composition is calculated considering the effective volume of the ions contained in the glass to be invariant.The refractive index as a function of composition is also calcuated.based on the Lorenz-Lorentz equation,by computing the electronic polarizability of HMF glasses.All calculated results are in good agreement with the observed data.