A clustering approach to interpretable principal components

A new method for constructing interpretable principal components is proposed. The method first clusters the variables, and then interpretable (sparse) components are constructed from the correlation matrices of the clustered variables. For the first step of the method, a new weighted-variances method for clustering variables is proposed. It reflects the nature of the problem that the interpretable components should maximize the explained variance and thus provide sparse dimension reduction. An important feature of the new clustering procedure is that the optimal number of clusters (and components) can be determined in a non-subjective manner. The new method is illustrated using well-known simulated and real data sets. It clearly outperforms many existing methods for sparse principal component analysis in terms of both explained variance and sparseness.     

Forecasting lead times with economic data

Procurement lead time estimates are critical factors in production planning; however, they are generally based on a buyer's experience. The Westinghouse Corporation developed a linear model which successfully predicted procurement lead times for hot and cold rolled steel. This paper discusses nine models which use utilization and inventory data to predict lead time planning factors for aluminum, magnesium, steel and titanium products. The Lockheed-Georgia Company, which produces aerospace products, provided data for this research. The functional form of the models is significant and suggests that a nonlinear transformation of utilization based upon simple queueing models is a significant predictor of lead time duration.     

带稀疏惩罚的LCNN盲目图像复原

为了加强算法的稀疏性和稳定性,在SCAD基础上提出了一种新的稀疏惩罚函数,并加入到拉格朗日约束神经网络中,以克服传统盲源分离方法和独立分量分析方法的缺陷,有效地避免了方程的病态问题,提高盲目图像复原的稀疏性、稳定性和准确性。通过人工数据和真实数据的不同复原算法对比实验,证明了带稀疏惩罚的拉格朗日约束神经网络盲目图像复原技术具有良好的图像复原效果。     

快离子导体氯碘铜化铷电性能的研究

最近国外报道,在RbCl-CuCl-CuI系统中,发现了离子电导率最高的Cu~+离子导体Rb_4Cu_(16)I_7Cl_(13)。我们采用国产原料,在工艺上作了探索,研制出较纯净的单一相Rb_4Cu_(16)I_7Cl_(13)。其室温电性能:离子电导率达0.44(Ω.cm)~(-1),电子电导率为4.2×10~(-9)(Ω.cm)~(-1),分解电位0.66(V)。此外,还对该材料的x射线衍射谱作了研究,提出了改进电性能的主要依据。     

股指期货价格发现功能的实证研究——基于现货指数变化趋势

依据香港股指期货市场数据，分别对香港恒生指数在指数振荡上行与振荡下降两阶段，利用Granger因果关系检验、方差分解、脉冲响应等方法，对股指期货与股指现货价格的领先滞后关系进行研究，得出股指期货在恒指振荡上行阶段具有价格发现功能，在恒指振荡下降阶段，现货领先期货，股指期货不具备价格发现功能。     

基于QR分解的MIMO—OFDM信号检测算法

本文研究了MIMO—OFDM系统基于QR分解的几种信号检测方法，分析了各种算法的优缺点．并提出了基于MMSE—SQR的改进球形算法，此算法结合了排序的SQR分解、MMSE准则和改进的sD检测算法，充分利用了它们的优点，在低运算复杂度的前提下，达到较优的性能．     

Inference in model-based cluster analysis

A new approach to cluster analysis has been introduced based on parsimonious geometric modelling of the within-group covariance matrices in a mixture of multivariate normal distributions, using hierarchical agglomeration and iterative relocation. It works well and is widely used via the MCLUST software available in S-PLUS and StatLib. However, it has several limitations: there is no assessment of the uncertainty about the classification, the partition can be suboptimal, parameter estimates are biased, the shape matrix has to be specified by the user, prior group probabilities are assumed to be equal, the method for choosing the number of groups is based on a crude approximation, and no formal way of choosing between the various possible models is included. Here, we propose a new approach which overcomes all these difficulties. It consists of exact Bayesian inference via Gibbs sampling, and the calculation of Bayes factors (for choosing the model and the number of groups) from the output using the Laplace–Metropolis estimator. It works well in several real and simulated examples.     

酒精在人体血液中含量及分解时间的数学模型

本文以一类关于药物例如酒精在人体内的分解速度问题,建立数学模型并给出了求解过程和结果,依此模型解决了酒精在人体内的分解时间问题。此模型可以推广到药物在人体内的分解时间和含量问题。     

噪声背景下提取调制信息的改进奇异值分解技术

在介绍现有奇异值分离技术基本原理及其在故障诊断中的应用的基础上，研究了利用信号时间序列重构的吸引子轨迹矩阵奇异值分布特征与信号特征的关系，引入自相关函数定量计算重构矩阵的延时步长，改进了现有算法，使得吸引子轨迹矩阵的重构更加合理。研究表明该方法能在强噪声背景下提取出所需的调制信号，并成功用于齿轮箱调制故障信号的提取。     

Income Satisfaction Inequality and its Causes

In this paper, the concept of Income Satisfaction Inequality is operationalized on the basis of individual responses to an Income Satisfaction question posed in the German Socio-Economic Panel (GSOEP). Income satisfaction is the subjective analogue of the objective income concept. The paper introduces a method to decompose Income Satisfaction Inequality according to the contributions from variables such as income, education, and the number of children. Given the panel structure of the data, inequality may be attributed partly to permanent individual circumstances and partly to transitory changes. The paper shows that by far the largest part of the satisfaction inequality has to be ascribed to unobserved heterogeneity. Distinguishing between a structural and an unexplained part of inequality we find that income explains the largest part of structural Income Satisfaction Inequality together with household membership; for non-working individuals, the age distribution is very relevant as well.