Optimizing Ridge Generalized Least Squares for Structural Equation Modeling

Ridge generalized least squares (RGLS) is a recently proposed estimation procedure for structural equation modeling. In the formulation of RGLS, there is a key element, ridge tuning parameter, whose value determines the efficiency of parameter estimates. This article aims to optimize RGLS by developing formulas for the ridge tuning parameter to yield the most efficient parameter estimates in practice. For the formulas to have a wide scope of applicability, they are calibrated using empirical efficiency and via many conditions on population distribution, sample size, number of variables, and model structure. Results show that RGLS with the tuning parameter determined by the formulas can substantially improve the efficiency of parameter estimates over commonly used procedures with real data being typically nonnormally distributed.     

Inter-Circuit Fault Location Algorithm for Two-Parallel Transmission Line

Transmissionlinesformthebackboneofpowerutilityoperationsandachievethecontinuityofservicefromgenerat ingplantstotheusers.Linesaresubjecttomultifariouskindsoffaultsbecausetheyareexposedtotheelements .Thecausesoffaultaremultifarious .Linefaultmaybetriggeredbylight ningstrokes.Treesmayfallacrosslines .Fogandsaltsprayondirtyinsulatorsmaycausetheinsulatorstringstoflashover.Iceandsnowloadingmaycauseinsulatorstringstofailmechanically .Followingtheoccurrenceofalinefault,itisnecessaryforthemaintenance…     

关于小离差主成分在经济计量分析中的应用研究

本文分析了小离差主成分与线性回归的几何意义,研究了利用小离差主成分建立线性方程或方程组,解决经济计量模型中参数估计问题,并得到了比较满意的结果。这种方法还具有能确定多重共线性、计算相对拟合度、减少回归次数、综合利用样本资料信息等有点。     

指数失效模型的Bayes分析及Bayes风险问题

针对指数失效模型研究了单参数指数分布的Bayes估计,确定了该分布的可信区间;同时,讨论了单参数指数分布与两参数指数分布的Bayes风险问题.     

人体姿态估计网络的轻量化设计

以金字塔残差模块为基础,设计了一个轻量化的网络模型。使用深度可分离卷积代替普通的卷积以减少训练的参数,同时加入通道分离模块和通道混合模块来改变特征图通道维数,以加强特征的融合。为保证网络仍然能更完整的提取特征,只对恒等映射部分进行了通道分离处理,在最后的特征融合加入了通道混合模块,在标准MPII数据集上进行测试。结果表明,轻量化的金字塔残差网络有效地减少了网络的参数,减少了约1/2的参数存储空间并保持相当的准确度,同时复杂度仅为2.83 GFLOs。     

对数正态分布的几个性质及其参数估计

给出对数正态分布的几个性质,分别利用矩估计法和最大似然估计法求出对数正态分布参数的点估计,并讨论其参数的区间估计。     

基于图像复原的规整化方法研究

图像降噪与图像去模糊方法研究在众多专业领域都具有重要的研究意义。去模糊问题是一个图像估计问题,处理这个问题的一般框架是规整化,本文研究了图像复原问题的典型规整化方法。     

加性高斯白噪声信道中典型信号的信噪比估计

信噪比是衡量通信质量的重要参数,正确估计出信号的信噪比能为后续信号的研究提供重要信息。现结合多种信噪比估计的方法,在仅需调制方式的先验信息下,对不同种类的调制信号有针对性地进行信噪比估计,能够有效估计6种典型信号。其中包括调幅信号AM和2ASK,调相信号BPSK、QPSK,调频信号MSK、2FSK。仿真实验表明,该法对信噪比在0¹8dB的信号能有效进行估计,估计偏差在0.5dB以内。     

Interference cancellation scheme for uplink cognitive radio systems

This paper investigates the interference cancellation (IC) scheme for uplink cognitive radio systems, using the spectrum underlay strategy where the primary users (PUs) and the secondary users (SUs) coexist and operate in the same spectrum. Joint MMSE-based parallel interference cancellation (PIC) and Turbo decoding scheme is proposed to reduce the interference to the PUs, as well as to the SUs, in which the minimum mean square estimation (MMSE) filter is only employed in the first iteration, regarded as the “weakest link” of the whole detection process, to improve the quality of the preliminary detections results before they are fed to the Turbo decoder. Simulation results show that the proposed scheme can efficiently eliminate the interference to the PUs, as well as to the SUs.     

复矩阵特征值及其最小奇异值的估计

讨论了复方阵特征值的分布及其最小奇异值的下界问题．给出了复方阵特征值的一个新包含区域和复方阵最小奇异值的一个新下界,这个新下界改进了文献[1]中的定理4所给的下界．文中数值算例表明所得结果是有效的．