Pattern recognition display methods for the analysis of computed molecular properties

Summary Pattern recognition methods, particularly the unsupervised learning techniques, are well suited for the preliminary analysis of the large data sets produced by computer chemistry. The use of linear and non-linear display methods for such exploratory analysis are exemplified with the aid of two data sets of biologically active molecules. Advantages and disadvantages of these techniques are discussed.     

GRCA(1)模型中误差方差自加权估计的渐近分布

考虑随机系数自回归模型Y_t =Φ_ty_t-1+ u_t,其中 Φ_t为随机系数,u_t为随机误差。在允许Φ_t与u_t相依以及Eu_t无穷的条件下,构造了误差方差的自加权估计,并证明了该估计的渐近正态性。最后通过数值模拟,说明 自加权估计的稳健和有效性。     

On Hsu's theorem in multivariate regression

The paper deals with optimal quadratic unbiased estimation of the unknown dispersion matrix in multivariate regression models without assuming normality of the errors. We show that Hsu's theorem for univariate regression models continues to multivariate models with no additional assumptions. Furthermore optimal quadratic plus linear estimating functions for regression coefficients are considered, and we investigate whether the ordinary linear estimates are the best. This leads to a new theorem which is similar to that of Hsu.     

Orbits of Positive Operators from a Differentiable Viewpoint

Let be a unital C^*-algebra and G the group of units of . A geometrical study of the action of G over the set ⁺ of all positive elements of is presented. The orbits of elements with closed range by this action are provided with a structure of differentiable homogeneous space with a natural connection. The orbits are partitioned in 'components' which also have a rich geometrical structure.     

Amplification Coefficient of the Anti‐Stokes Component of Raman Scattering

The theory of intracavity parametric interaction of the components of Raman scattering is developed in the prescribedintensity approximation, which takes into account the reverse reaction of the excited waves to the pumpingwave phase. It is shown that one can substantially improve the conversion efficiency or the amplification coefficient of the antiStokes component by selection of the intracavity geometry, the optimum phase relation between the interacting waves, the pumping level, and the phase mismatch.     

Statistical Inference in a Linear Model for Spatially Located Sensors and Random Input

In the paper we consider a random linear model for observations provided by spatially located sensors measuring signals coming from one source. For this model a set of sufficient and complete statistics are found, and it is shown that the maximum likelihood estimators of unknown parameters (characteristics of the source) are functions of those statistics. The problem of nonnegative estimators of variance components of the model is shortly discussed. Comparisons of the mean squared errors of several estimators are given. Numerical example concerning hunting for defects in solar cells is considered in details.     

ESR spectroscopy as a tool for identifying joining fragments of antique marbles: the example of a pulpit by Donatello and Michelozzo

ESR spectroscopy is one of the physicochemical techniques used to characterize archaeological white marbles and obtain information about their quarries of provenance. This is done by measuring selected spectral features of the Mn(2+) impurity ubiquitously present in marbles and developing a statistical classification rule from the variable vectors measured for a significant number of samples of known provenance (the quarry database). Now we show that the overall variability exhibited by the same spectroscopic features decreases rapidly with the linear dimensions of the sampled block and can be used to distinguish fragments belonging to the same piece of stone from those simply originating from the same quarry. Application of the method to the seven marble panels of the Donatello pulpit in Prato (Tuscany) shows that they have all been cut from the same single block and their different degradation must be ascribed to differential weathering and to the different conservation treatments undergone in the past. The limits and possible drawbacks of the method are also discussed.     

恐龙不同部位化石的激光拉曼光谱

应用波长为785nm的激光拉曼光对来自武定九厂地区的两个不同部位的恐龙化石样品研究测试,首次在1000 cm-1~1800 cm-1波数段得到碳氢物质的拉曼峰图谱。在该波数范围内,颈椎化石和尾椎化石都有强、弱两类特征峰。它们的强特征峰与源地关系不大,即同一地区的化石特征峰并不很相似。弱拉曼峰与围岩的拉曼峰相似。恐龙化石的强拉曼峰来源于生物遗体分解剩下的碳氢类物质成分,弱拉曼峰源于石化过程中外部填充物质的成分。     

一种复杂车辆图像中的多车牌定位方法

针对复杂背景中多个车牌的定位问题,提出一种新的定位方法.该方法综合利用边缘检测、连通域分析、倾斜矫正等多种方法,解决了复杂背景中定位难的问题.能够准确定位杂乱背景中的车牌,对天气、光照变化、车牌在图像中的移动和旋转等,具有良好的适应能力.该方法为后续的字符分割和字符识别提供旋转角度、字符区域定位信息.     

A Mean–variance analysis of arbitrage portfolios

Based on the careful analysis of the definition of arbitrage portfolio and its return, the author presents a mean–variance analysis of the return of arbitrage portfolios, which implies that Korkie and Turtle's results ( B. Korkie, H.J. Turtle, A mean–variance analysis of self-financing portfolios, Manage. Sci. 48 (2002) 427–443) are misleading. A practical example is given to show the difference between the arbitrage portfolio frontier and the usual portfolio frontier.