Flexible Distribution-Based Regression Models for Count Data: Application to Medical Diagnosis

Abstract

Data mining techniques have been successfully utilized in different applications of significant fields, including medical research. With the wealth of data available within the health-care systems, there is a lack of practical analysis tools to discover hidden relationships and trends in data. The complexity of medical data that is unfavorable for most models is a considerable challenge in prediction. The ability of a model to perform accurately and efficiently in disease diagnosis is extremely significant. Thus, the model must be selected to fit the data better, such that the learning from previous data is most efficient, and the diagnosis of the disease is highly accurate. This work is motivated by the limited number of regression analysis tools for multivariate counts in the literature. We propose two regression models for count data based on flexible distributions, namely, the multinomial Beta-Liouville and multinomial scaled Dirichlet, and evaluated the proposed models in the problem of disease diagnosis. The performance is evaluated based on the accuracy of the prediction which depends on the nature and complexity of the dataset. Our results show the efficiency of the two proposed regression models where the prediction performance of both models is competitive to other previously used regression models for count data and to the best results in the literature.     

多信道光纤环形网络结构分析

本文对多信道光纤环形网络结构进行了详细分析，推导出环网内平均路经长度和最大直径计算公式，并分析了最佳多信道光纤环网结构。     

Signed line intercept count

Elements of surfaces that bound a phase (β) in a two phase mixture (α+β) may be classified as: (a) convex (++) if both principal curvatures are positive; (b) concave (? ?) if both are negative; and (c) saddle (+ ?) if one is positive and the other negative. This classification excludes the limiting cases for which one or both of the principal curvatures is zero. The traces of these surfaces that form the boundaries of the β areas on a representative two dimensional section may also be: (a) convex (+) if the local curvature is positive; or (b) concave (?) if it is negative. Line intercepts may be tabulated separately for intersections with convex (+) and concave (?) segments of boundary. This paper presents a derivation of fundamental stereological formulae that relate these counting measurements to three-dimensional geometric properties of the structure they sample.     

节能降耗提高矿山效益

节能降耗是每一个矿山提高经济效益的有效途径。我们采取提高球磨机处理能力，降低单耗；利用“分时计价”政策，采用“避峰作业”；使用新设备等措施节能降耗，提高矿山经济效益。     

Fabricated Beef Product: Effect of Handling Conditions on Microbiological, Chemical, and Sensory Properties

Total microbial count was not adversely affected by lowering the holding temperature of fabricated beef roast from 60°C to 54°C or by 12 hr holding time. If a reduction in holding temperature is anticipated, then initial roast contamination and sanitation of the food facility are of critical importance. A stabilizing period of 20 min at room temperature (～23°C) did not decrease yield, but caused a slight lowering of sensory scores. Tenderness was more acceptable in product held at 54°C compared to 60°C. In general, all sensory evaluation ratings were slightly lower with increased holding time.     

高层印制线路板正面临的对位挑战

封装工业正在推动着印制线路板技术水平朝着半导体要求的方向发展。高密度印制线路板正广泛用于网络路由器、自动测试设备和服务器领域。高密度要求(>150 IO/cm~2)正成为客户的普通需求。为满足现有的高密度封装要求,由于线宽、线距和通孔孔径正接近传统制作极限,普遍的方法就是不断增加印制线路板的层数。这些特征正驱动着印制线路板在基材、图像转移、蚀刻、电镀、阻焊、测试流程和对位系统的变化。此文主要讲述了印制线路板特性的变化趋势和利用对位模式和雷利分布去预测满足高级对位要求的能力以及印制线路板各流程中有关对准度的控制要点。     

Inference for pth‐order random coefficient integer‐valued autoregressive processes

Abstract. A pth‐order random coefficient integer‐valued autoregressive [RCINAR(p)] model is proposed for count data. Stationarity and ergodicity properties are established. Maximum likelihood, conditional least squares, modified quasi‐likelihood and generalized method of moments are used to estimate the model parameters. Asymptotic properties of the estimators are derived. Simulation results on the comparison of the estimators are reported. The models are applied to two real data sets.     

Synthesis, Characterization, and Cytotoxicity Analysis of a Biodegradable Polyurethane

A polyester urethane was synthesized for use in a biodegradable scaffold. The polyurethane was synthesized in a two-step process: first, ester diol was synthesized from lactic acid and polyethylene glycol 400 (PEG 400), then it was polymerized with toluene diisocyanate using dibutyl tin dilaurate (DBTDL) as a catalyst to form a polyester urethane. Polyester urethane has tensile strength of 51-59 MPa and elongation at fracture of 369-439%. FTIR and XRD were used to confirm the formation and structure of the polymer. Hydrolytic degradation was studied in different alkali solutions and in saline water. In order to assess the cellular response of this material, cytotoxicity analysis was carried out against the cell line.     

Correlation study between standard plate count and flow cytometry for determination of raw milk total bacterial count

Milk samples were collected in the dry season ( n =  155) and in the rainy season ( n =  68) to establish a correlation between electronic flow cytometry and standard plate count for the determination of total bacterial count of raw milk. Results were expressed in individual bacterial count (ibc) and colony forming unit (cfu) for electronic flow cytometry (Bactocount) and standard plate count, respectively. The accuracy of Bactocount, denoted by the residual standard deviation ( s ( y,x )), was 0.309 log cfu/mL. The predictive interval of estimated values was broad and it is suggested that total bacterial count should be expressed in ibc without transformation to cfu.     

跳数加权DV-Hop定位算法

针对DV-Hop定位算法中距离估计误差对定位结果的影响,提出了一种信标节点优选方案和跳数加权DV-Hop定位算法。首先通过设定跳数阈值,保留跳数较少的信标节点,然后剔除近似在一条直线上的信标节点,完成信标节点优选,避免未知节点无法定位的情形。此外,利用Friis模型推导出距离估计误差与信号传播跳数之间的映射关系,采用传播跳数作为加权因子对定位结果进行了修正。仿真结果表明该算法降低了距离估计误差对定位精度的影响,提高了定位精度。