A Bayesian propensity score adjustment for latent variable modeling and MCMC algorithm

The estimation of the differences among groups in observational studies is frequently inaccurate owing to a bias caused by differences in the distributions of covariates. In order to estimate the average treatment effects when the treatment variable is binary, Rosenbaum and Rubin [1983. The central role of the propensity score in observational studies for causal effects. Biometrika 70, 41-55] proposed an adjustment method for pre-treatment variables using propensity scores. Imbens [2000. The role of the propensity score in estimating dose-response functions. Biometrika 87, 706-710] extended the propensity score methodology for estimation of average treatment effects with multivalued treatments.However, these studies focused only on estimating the marginal mean structure. In many substantive sciences such as the biological and social sciences, a general estimation method is required to deal with more complex analyses other than regression, such as testing group differences on latent variables. For latent variable models, the EM algorithm or the traditional Monte Carlo methods are necessary. However, in propensity score adjustment, these methods cannot be used because the full distribution is not specified.In this paper, we propose a quasi-Bayesian estimation method for general parametric models that integrate out the distributions of covariates using propensity scores. Although the proposed Bayes estimates are shown to be consistent, they can be calculated by existing Markov chain Monte Carlo methods such as Gibbs sampler. The proposed method is useful to estimate parameters in latent variable models, while the previous methods were unable to provide valid estimates for complex models such as latent variable models.We also illustrated the procedure using the data obtained from the US National Longitudinal Survey of Children and Youth (NLSY1979-2002) for estimating the effect of maternal smoking during pregnancy on the development of the child's cognitive functioning.     

Formation of composites fabricated by exothermic dispersion reaction in A1-TiO2-B2O3 system

The formation of aluminum matrix composites fabricated by exothermic dispersion reaction in A1-TiO2-B2O3 system was investigated. The thermal analysis results show that the reactions are spontaneous and exothermic. The Gibbs free energy of α-Al2O3 is the lowest among all the combustion products, followed by TiB2 and Al3Ti. It is noted that when the B2O3/TiO2 mole ratio is below 1, the reaction products are composed of particle-like α-Al2O3, TiB2 and rod-like Al3Ti. The α-Al2O3 crystallites, resulting from the reaction between A1 and TiO2 or B2O3, are segregated at the grain boundaries due to a lower wettability with the matrix. SEM micrographs show that rod-like Al3Ti phase distributes uniformly in the matrix. When the BEO3/TiO2 mole ratio is around 1, the Al3Ti phase almost disappears in the composites, and the distribution of α-Al2O3 particulates is improved evidently.     

Preparation and Compressive Stress Effect of Polymer Matrix RE-Fe Giant Magnetostrictive Composite

Polymer matrix RE-Fe giant magnetostrictire composite （GMPC） was prepared using bonding and magnetic field forming technique, and magnetostriction of samples was measured for different compressive stress. The experimental results show thai there is certain compressive effect in GMPC. And the influence of compressive stress on magnetostriction of sample was investigated. It offers essential reference for application and device design of GMPC.     

Conceptual damage-sensitive features for structural health monitoring: Laboratory and field demonstrations

The use of damage-sensitive features to evaluate structural condition or health is a very critical aspect of structural health monitoring. The purpose of this paper is to investigate the potential of two different damage-sensitive features for detecting damage. Different damage scenarios are simulated on a large-scale laboratory structure and a three-span highway bridge for demonstration. The features presented in this paper are the modal flexibility-based deflection and curvature both of which are obtained directly from dynamic properties. In the literature, flexibility associated with mode shapes and mode shapes curvatures have been mostly explored. In this study, multi-input–multi-output dynamic data are used to obtain modal flexibility, which is a close approximation to the actual flexibility. A main novelty is that the curvature is calculated from the deflected shapes using the modal flexibility as opposed to using modal vectors. In this paper, the theory of the methodology is explained and then experimental studies and results are presented. For the experimental studies, the laboratory specimen and the three-span bridge were gradually damaged. It is shown that both deflection and curvature are conceptual and physically meaningful features for damage detection and localization. The issues and the requirements for these features to perform successfully are also presented.     

Average consensus in networks of dynamic agents with switching topologies and multiple time-varying delays

In this paper, we discuss average consensus problem in undirected networks of dynamic agents with fixed and switching topologies as well as multiple time-varying communication delays. By employing a linear matrix inequality method, we prove that all the nodes in the network achieve average consensus asymptotically for appropriate communication delays if the network topology is connected. Particularly, several feasible linear matrix inequalities are established to determine the maximal allowable upper bound of time-varying communication delays. Numerical examples are given to demonstrate the effectiveness and the sharpness of the theoretical results.     

A parallel and scalable algorithm for ADI method with pre-propagation and message vectorization

It is hard to implement the ADI method in an efficient way on distributed-memory parallel computers. We propose “P-scheme” which parallelizes a tridiagonal linear system of equations for the ADI method, but its effectiveness is limited to the cases where the problem size is large enough mainly because of the communication cost of the propagation phase of the scheme.

In order to overcome this difficulty, we propose an improved version of the P-scheme with “message vectorization” which aggregates several communication messages into one and alleviates the communication cost. Also we evaluate the effectiveness of message vectorization for the ADI method and show that the improved version of the P-scheme works well even for smaller problems and linear and super-linear speedups can be achieved for 8194 × 8194 and 16,386 × 16,386 problems, respectively.     

CDMA系统中联合功率控制、波束赋形与多用户检测

应用功率控制、波束赋形和多用户检测可以有效地消除和减少CDMA系统中的干扰。本文结合波束赋形和多用户检测的特性，提出一种应用波束赋形增益和多用户相关矩阵的解相关算法。基于算法的复杂性，提出一种区分聚集用户进行多用户检测的的算法。由于波束赋形能够消减主瓣波束之外的多用户干扰，对聚集移动台采用解相关检测达到减少运算量和消除多用户干扰的目的。对算法进行了仿真分析，证明了本算法的优越性。     

电梯门机控制系统的运行曲线设计

为了实现电梯轿厢门的开门和关门快速且平稳地运行，介绍了一种基于高性能微型机的门机控制系统结构和门位移的检测原理，以门位移量作为控制系统的反馈量，对门机运行速度进行了分区设计。在高速附近的变化区，门机速度匀速变化时，进行了门机开门和关门控制曲线的计算，推导出运行位移与门机速度具有二次曲线的关系，进而对微型机控制的软件流程进行了设计，达到了门机高低速运行的平稳过渡。最后，给出了实际运行系统的主电路电压波形。     

The effect of particle distribution on damage formation in particulate reinforced metal matrix composites deformed in compression

Image analysis results are reported on the generation of damage in particulate reinforced metal matrix composites during compressive deformation. The technique allows the automated collection of data on the incidence of particle fracture and void formation in the matrix as a function of important microstructural parameters such as local particle volume fraction and particle size. There is a strong relationship between damage and the local volume fraction of the reinforcement proving that damage formation is accentuated in regions of particle clustering. With the SiC reinforced materials examined, there was observed to be a change in dominance of damage mechanism from particle fracture at low local volume fractions to void formation in the matrix within strongly clustered regions. The results are compared with finite element (FE) modelling of the compressive deformation of clustered particles using a simple cluster of equi-spaced particles. The FE results suggest that plastic flow is generally inhibited in clustered regions. In certain highly clustered configurations shielding is such that flow does not occur in the heart of the cluster even at high levels of average plastic strain. The modelling suggests that the change in dominance of damage mechanism is related to the dramatic increase in tensile hydrostatic stresses in the matrix with higher levels of particle clustering.     

The rank one mixed μ problem and ‘kharitonov-type’ analysis

The general mixed μ problem has been shown to be NP hard, so that the exact solution of the general problem is computationally intractable, except for small problems. In this paper we consider not the general problem, but a particular special case of this problem, the rank one mixed μ problem. We show that for this case the mixed μ problem is equivalent to its upper bound (which is convex), and it can in fact be computed easily (and exactly). This special case is shown to be equivalent to the so-called ‘affine parameter variation’ problem (for a polynomial with perturbed coefficients) which has been examined in detail in the literature, and for which several celebrated ‘Kharitonov-type’ results have been proven.