Bayesian Multiscale Smoothing for Making Inferences About Features in Scatterplots

A rather common problem of data analysis is to find interesting features, such as local minima, maxima, and trends in a scatterplot. Variance in the data can then be a problem and inferences about features must be made at some selected level of significance. The recently introduced SiZer technique uses a family of nonparametric smooths of the data to uncover features in a whole range of scales. To aid the analysis, a color map is generated that visualizes the inferences made about the significance of the features. The purpose of this article is to present Bayesian versions of SiZer methodology. Both an analytically solvable regression model and a fully Bayesian approach that uses Gibbs sampling are presented. The prior distributions of the smooths are based on a roughness penalty. Simulation based algorithms are proposed for making simultaneous inferences about the features in the data.     

n链码对异形纤维特征参数的作用

通过n链码对图形特征参数影响的研究,讨论了n链码对异形纤维轮廓的平滑作用以及不同的n取值对轮廓曲线的不同平滑效果.通过面积误差、周长误差以及轮廓相似度3个误差模型,分析了6种标准几何图形在不同的n值作用下轮廓的失真,讨论了n的计算方法,并在异形纤维识别应用中对该计算方法进行了验证.     

拟矩形剖分上的样条空间的维数

矩形剖分~(记为$\Delta_{QR}$)~是指在矩形剖分~(记为$\Delta_{R}$)的基础上进行局部修改后得到的剖分,通常包括T-剖分~(记为$\Delta_{T}$)~和L-剖分~(记为$\Delta_{L}$).本文利用光滑余因子协调方法讨论了该剖分上的二元样条空间$S^\mu_k(\Delta_{QR})$的维数.在满足一定约束条件下, 得到了仅依赖于样条空间的次数,光滑度和剖分拓扑结构的显式维数公式.     

Log-Sigmoid Multipliers Method in Constrained Optimization

In this paper we introduced and analyzed the Log-Sigmoid (LS) multipliers method for constrained optimization. The LS method is to the recently developed smoothing technique as augmented Lagrangian to the penalty method or modified barrier to classical barrier methods. At the same time the LS method has some specific properties, which make it substantially different from other nonquadratic augmented Lagrangian techniques.We established convergence of the LS type penalty method under very mild assumptions on the input data and estimated the rate of convergence of the LS multipliers method under the standard second order optimality condition for both exact and nonexact minimization.Some important properties of the dual function and the dual problem, which are based on the LS Lagrangian, were discovered and the primal–dual LS method was introduced.     

An Algorithm Based on Active Sets and Smoothing for Discretized Semi-Infinite Minimax Problems

We present a new active-set strategy which can be used in conjunction with exponential (entropic) smoothing for solving large-scale minimax problems arising from the discretization of semi-infinite minimax problems. The main effect of the active-set strategy is to dramatically reduce the number of gradient calculations needed in the optimization. Discretization of multidimensional domains gives rise to minimax problems with thousands of component functions. We present an application to minimizing the sum of squares of the Lagrange polynomials to find good points for polynomial interpolation on the unit sphere in ℝ³. Our numerical results show that the active-set strategy results in a modified Armijo gradient or Gauss-Newton like methods requiring less than a quarter of the gradients, as compared to the use of these methods without our active-set strategy. Finally, we show how this strategy can be incorporated in an algorithm for solving semi-infinite minimax problems.     

气体团簇离子束两步能量修形法的平坦化效应

本文提出采用气体团簇离子束的两步能量修形法来改善4H-SiC(1000)晶片表面形貌.先用15 keV的高能Ar团簇离子进行整体修形,再用5 keV的低能团簇离子优化表面.结果表明,在相同的团簇离子剂量下,与单一15 keV的高能团簇处理相比,两步法修形后的表面具有更低的均方根粗糙度,两者分别为1.05 nm和0.78 nm.本文还以原子级平坦表面为研究对象,揭示了载能团簇引起的半球形离子损伤(弧坑)与团簇能量的关系,及两步能量修形法在弧坑修复中的优势.在原子力显微镜表征的基础上,引入了二维功率谱密度函数,以直观全面地给出材料的表面形貌特征及其随波长(频率)的分布.结果表明,经任何能量的团簇离子轰击的表面,在0.05—0.20μm波长范围内,团簇轰击都能有效地降低粗糙度,而在0.02—0.05μm范围内,则出现了粗化效应,这是由于形成了半球形离子损伤,但第二步更低能量的团簇离子处理可以削弱这种粗化效应.     

非线性优化问题的光滑化序列二次规划方法

为了获得序列二次规划方法的全局收敛性,通常需要借助一个罚函数,但常用的罚函数由于具有不可微性从而给计算带来一定的困难,拉格朗日函数虽然可以克服此困难,但其形式较为复杂,为解决该问题,给出了一类光滑化罚函数.基于一类双曲余弦型光滑化罚函数,提出了等式约束优化问题的一个光滑化序列二次规划方法.该光滑化函数具有良好的连续、可微性和凸性质,在适当条件下,获得了算法的全局收敛性,并给出数值测试说明了算法的有效性.     

血糖近红外光谱分析的Savitzky-Golay平滑模式与偏最小二乘法因子数的联合优选

利用偏最小二乘法(PLS)和光谱Savitzky-Golay(SG)平滑方法,建立血清葡萄糖近红外光谱分析的优化模型。基于最优单波数模型的预测效果,提出划分校正集和验证集的一种新方法。采用10000～5300cm-1和4920～4160cm-1的组合波段,光谱经过SG平滑处理,利用PLS方法建立定标预测模型。将平滑点数扩充为5,7,…,87(奇数),多项式次数扩充为n=2,3,4,5,6,得到包含582个平滑模式的14个平滑系数表。对所有平滑模式和PLS因子数(1～40)分别建立PLS模型。按照预测效果进行优选,得到最优SG平滑模式为1阶导数平滑,3、4次多项式类型,SG平滑点数为53,最优PLS因子数为7,最优RMSEP达到0.376mmol/L。所采用的划分校正集和验证集的方法、SG平滑模式的扩充、SG平滑模式和PLS因子数的联合大范围筛选能够有效地应用于近红外光谱分析的模型优化。     

Cubic smoothing splines background correction in on-line liquid chromatography–Fourier transform infrared spectrometry

A background correction method for the on-line coupling of gradient liquid chromatography and Fourier transform infrared spectrometry (LC–FTIR) is proposed. The developed approach applies univariate background correction to each variable (i.e. each wave number) individually. Spectra measured in the region before and after each peak cluster are used as knots to model the variation of the eluent absorption intensity with time using cubic smoothing splines (CSS) functions. The new approach has been successfully tested on simulated as well as on real data sets obtained from injections of standard mixtures of polyethylene glycols with four different molecular weights in methanol:water, 2-propanol:water and ethanol:water gradients ranging from 30 to 90, 10 to 25 and from 10 to 40% (v/v) of organic modifier, respectively. Calibration lines showed high linearity with coefficients of determination higher than 0.98 and limits of detection between 0.4 and 1.4, 0.9 and 1.8, and 1.1 and 2.7 mg mL⁻¹ in methanol:water, 2-propanol:water and ethanol:water, respectively. Furthermore the method performance has been compared with a univariate background correction approach based on the use of a reference spectra matrix (UBC-RSM) to discuss the potential as well as pitfalls and drawbacks of the proposed approach. This method works without previous variable selection and provides minimal user-interaction, thus increasing drastically the feasibility of on-line coupling of gradient LC–FTIR.