变异系数的新性质及其在图像处理中的应用

给出了数据分析中常用的统计量之一变异系数新的表达式，揭示了变异系数用于图像处理时的几何意义，同时还借助该公式对变异系数在图像处理中的取值范围和取值意义进行研究．作为本文的一个应用实例，我们在处理图像块分类算法中纹理区与边缘区的划分问题时，用变异系数代替以往常用的方差进行计算，避免了方差阈值选取的不稳定性，取得了很好的效果．     

基于滑动窗口的一类非负可变权组合预测方法

针对基于结果的组合预测赋权问题,通过引入预测残差数据的变异系数和滑动窗口模型,给出一类基于滑动窗口和改进变异系数的组合预测时变权重确定方法.将传统基于预测数据层面的变异系数转移到预测残差数据层面,能有效消除传统变异系数由于数据数量级引起的数据变异程度被弱化的情况.结合滑动窗口模型,对已有的赋权方法和提出的基于改进变异系数的赋权方法进行调整,实现非时变权重向时变权重的过渡.实例分析表明,改进变异系数的有效性以及滑动窗口技术的引入能够有效提高组合预测精度.     

基于局部统计特征的边缘检测

该文通过分析图像灰度信息的变化,提出局部变异系数的概念,并指出使用该特征进行图像边缘检测的可行性。对于提出的算法,该文结合不同图像进行了实验仿真,并对实验结果进行了分析。由实验结果表明,针对某些图像,使用局部变异系数能较好的提取出图像的边缘。最后,还指出了该算法一些改进的方法。     

宁夏不同地区农田土壤磷素养分的空间变异特征

在宁夏灌区和旱区30块农田分别采集了0~120 cm深土壤剖面样品,测定了土壤全磷和速效磷含量,分析了土壤磷素养分含量的空间变异性。结果表明,在0~120 cm深土壤剖面中的全磷和速效磷含量,灌区土壤显著高于旱区土壤,在剖面点之间和土壤层次之间存在极显著差异,而且在土层间还存在着正相关。其变异系数总体上是旱区土壤大于灌区土壤,速效磷大于全磷。从地区来看,旱区土壤全磷和速效磷含量的变异系数随剖面深度的增加而增大,灌区土壤全磷量的变异系数在剖面层次之间差别不大,而速效磷的变异系数随剖面深度的增加而呈降低趋势。在0~120 cm深土壤剖面中,土壤全磷和速效磷的累积量灌区较旱区分别高出26.8%和65.0%,在土类间也存在较大差异。     

变异系数来度量区块链网络去中心化程度

区块链网络的最主要优点是去中心化,但大多数关于这个问题的研究缺乏量化,而且都没有针对区块链在实践中的去中心化程度进行度量.提出了一种基于统计学中变异系数来量化区块链网络去中心化程度的方法.利用变异系数,计算了出块数量和地址余额的数据离散程度,从而来量化区块链网络(以比特币和以太坊为例)的去中心化程度.计算结果表明,基于...     

Web访问流的局部性特征建模

网络访问流的局部性特征包括时间局部性和空间局部性,利用数学建模方法研究局部性特征对于缓存和预取系统的设计及性能提高具有重要的作用.通过分析和讨论,利用信息熵和变异系数建立了网络流量局部性特征新的度量方法,信息熵比Zipf定律更能反映访问流的时间局部性,变异系数则解决了访问流的相同文档间的空间局部性建模问题.实验和分析表明,这些参数能较好地描述网络访问流的局部性特征且易于使用.     

一种融合变异系数的k-mean聚类分析方法

K-means聚类算法的性能依赖于距离度量的选择,k-means算法将欧几里德距离作为最常用的距离度量方法。欧氏距离认为所有属性在聚类中作用是相同的,但是这种距离度量方法并不能准确反映样本间的相异性。针对这种不足,提出了融合变异系数的k-means聚类分析方法（CV-k-means）,利用变异系数权重向量来减少不相关属性的影响。实验结果表明,该方法的聚类结果优于k-means算法。     

转向架临界速度的不确定性研究*

铁道车辆临界速度与很多参量有关,如何准确有效地建立它们之间的函数关系进行不确定性研究是一个比较复杂的问题.基于此,推导高维多阶基于正态分布场的Hermite正交多项式,采用拉丁超立方采样的配点方式建立某转向架临界速度与随机参量之间的函数关系;分析了不同变异系数下转向架悬挂系统部件左/右、前/后均服从独立正态分布时临界速度的变化规律.可靠性分析的结果表明:随着变异系数的不断增大,只有取较低的临界速度限定值,才能保证转向架系统具有低的失效概率.灵敏度分析的结果则显示:二系悬挂横向阻尼对临界速度影响最大,不同的前/后悬挂部件对临界速度有着不同的重要性影响,变异系数的变化不会根本性改变参量的灵敏度指标排序.     

直接扩频系统中极性消除算法的改进

为了消除直接扩频通信系统中宽带干扰信号,极性消除(Polar Exciser)算法被提出,其实质是极性转换和变换域陷波滤波的结合。但其在干扰功率较低时,系统性能急剧下降。本文提出了一种基于极性消除算法的改进算法,用以消除不同类型的宽带恒包络干扰信号。本文通过引入变异系数来选择使用极性消除干扰抑制器还是匹配滤波器。对通过改进后的极性消除算法来抑制宽带恒包络干扰信号后的误码率进行仿真,结果表明了该改进算法对宽带恒包络的干扰信号有着较好的抑制作用,且变异系数是一种有效的切换策略。     

基于变异系数的双聚类算法及其在电信客户细分的应用研究

针对传统客户价值细分方法不够精细化的问题,提出一种基于变异系数的双聚类算法。该算法选用了变异系数作为相似性度量,运用启发式贪心策略,通过迭代增删行列的方式挖掘出客户消费记录中局部消费行为相似的客户群体。以某电信公司的电信客户细分为实例,将所提算法与K均值(K-means)算法进行性能比较,实验结果表明,所提算法具有更优的客户细分能力和更强的客户行为可解释能力。因此,它更有助于指导企业制定差异化营销策略。     

Development of methods for registration of the force exerted by hand-fingers in industrial work

In a manufacturing industry producing ground hard metal inserts, a small strain-gauge pressure transducer was built into the work prefix to measure the force exerted by the fingers. The procedure did not interfere with the work. The variation of force and of the time sequences between each force measurement were measured. The coefficient of variation (CV) was used as a measure of precision of the work.     

四阶时变离散系统的一致渐近稳定性

特征建模的方法为智能控制器设计和一些高阶对象进行低阶控制器设计提供了理论依据．对于速度跟踪、加速度控制,基于特征模型设计的自适应控制方案其稳定性问题即为四阶时变离散系统的稳定性问题．首先给出了变系数二次三项式的系数满足一组较复杂的差分关系式时,其判别式的简洁表达式,在此基础上,利用Lyapunov直接方法定量地给出了四阶线性时变离散系统的一致渐近稳定性判据．获得的结果仅依赖于系统方程系数变化范围,从而简化了现有的依赖于系统方程系数函数变化范围的结论．     

Investigation of the discharge process in a shadow‐mask PDP cell using fluid models

Abstract— Two fluid models, LFA (local field approximation) and EME (electron mean energy), were applied to simulate the discharge process of a novel PDP with a shadow mask. In order to consider the variation of the secondary electron emission coefficient under different electric‐field and gas content, the secondary electron emission coefficient was calculated as a function of the energy of incident ions. The variation of the mean density of different particles as a function of time, electron temperature, and their space distributions in the discharge cell will be presented. And the simulation results of these two models are also compared in this paper. Then the EME model was used to investigate the relation between the discharge efficiency and the structure of the shadow mask, the xenon concentration, and the pressure.     

Impact of correlated inputs on the output of the integrate- and-fire model

For the integrate-and-fire model with or without reversal potentials, we consider how correlated inputs affect the variability of cellular output. For both models, the variability of efferent spike trains measured by coefficient of variation (CV) of the interspike interval is a nondecreasing function of input correlation. When the correlation coefficient is greater than 0.09, the CV of the integrate-and-fire model without reversal potentials is always above 0.5, no matter how strong the inhibitory inputs. When the correlation coefficient is greater than 0.05, CV for the integrate-and-fire model with reversal potentials is always above 0. 5, independent of the strength of the inhibitory inputs. Under a given condition on correlation coefficients, we find that correlated Poisson processes can be decomposed into independent Poisson processes. We also develop a novel method to estimate the distribution density of the first passage time of the integrate-and-fire model.     

Variation and directional anisotropy of reflectance at the crown scale — Implications for tree species classification in digital aerial images

Tree species classification is still solved at insufficient reliability in airborne optical data. The variation caused by directional reflectance anisotropy hampers image-based solutions. In addition, trees show considerable within-species variation in reflectance properties. We examined these phenomena at the single-tree level, using the Leica ADS40 line sensor and XPro software, which constitute the first photogrammetric large-format multispectral system to provide target reflectance images. To analyze the influence of illumination conditions in the canopy, we developed a method in which the crown shape as well as between-tree occlusions and shading were modeled, using dense LiDAR data. The precision of the ADS40 reflectance images in well-defined surfaces was 5% as coefficient of variation when 1−4-km image data were fused. The range of reflectance anisotropy was ± 30% for trees near the solar principal plane, with differences between bands and species. Because of the anisotropy differences observed, the spectral separability of the tree species in different bands is dependent on the view-illumination geometry. The within-species variation was high; the coefficient of variation was 13−31%. The contribution of tree and stand variables to anisotropy-normalized reflectance variation was examined. The effects of the species composition of adjacent trees were substantial in NIR and this variation hampers spectral classification in mixed stands. We also studied species- and band-specific intracrown brightness patterns, and we suggest their use as high-order image features in species classification. A species classification accuracy of up to 80% was obtained using 4-km data, which showed the high potential of the ADS40.     

基于变异系数的边界点检测算法

为有效检测聚类的边界点,提出基于变异系数的边界点检测算法.首先计算出数据对象到它的k-距离邻居距离之和的平均值.然后用平均值的倒数作为每个点的密度,通过变异系数刻画数据对象密度分布特征寻找边界点.实验结果表明,该算法可在含有任意形状、不同大小和不同密度的数据集上快速有效检测出聚类的边界点,并可消除噪声.     

An analysis of globally connected active rotators with excitatory and inhibitory connections having different time constants using the nonlinear Fokker-Planck equations

The globally connected active rotators with excitatory and inhibitory connections having different time constants under noise are analyzed using the nonlinear Fokker-Planck equation, and their oscillatory phenomena are investigated. Based on numerically calculated bifurcation diagrams, both periodic solutions and chaotic solutions are found. The periodic firings are classified based on the firing period, the coefficient of variation, and the correlation coefficient, and weakly synchronized periodic firings which are often observed in physiological experiments are found.     

自适应总体变差图像去噪算法的扩散系数研究

自适应总体变差算法可以解决总体变差算法无法实现去噪的同时保留图像的细节纹理.对该算法的扩散系数研究表明当算法满足如下性质:φ'(|grad(I)|)≥0,φ"(|grad(I)|)≥0;当扩散系数法向量方向的值为'(|grad(I)|)/|grad(I)|,扩散系数切向量方向的值为φ"(|grad(I)|),并且|grad(I)|→ ∞时,法向量方向的值趋于0,法向量与切向量的比值趋于0;当|grad(I)|→0时,法向量方向和切向量方向的值均大于0时可以取得较好的试验结果,并认为最小曲面函数是合适的扩散系数.