Recently, Kundu and Gupta （Metrika, 48：83 C 97, 1998） established the asymptotic normality of the least squares estimators in the two dimensional cosine model. In this paper, we give the approximation to the genera...Recently, Kundu and Gupta （Metrika, 48：83 C 97, 1998） established the asymptotic normality of the least squares estimators in the two dimensional cosine model. In this paper, we give the approximation to the general least squares estimators by using random weights which is called the Bayesian bootstrap or the random weighting method by Rubin （Annals of Statistics, 9：130 C 134, 1981） and Zheng （Acta Math. Appl. Sinica （in Chinese）, 10（2）： 247 C 253, 1987）. A simulation study shows that this approximation works very well.展开更多
Orthogonal nonnegative matrix factorization(ONMF)is widely used in blind image separation problem,document classification,and human face recognition.The model of ONMF can be efficiently solved by the alternating direc...Orthogonal nonnegative matrix factorization(ONMF)is widely used in blind image separation problem,document classification,and human face recognition.The model of ONMF can be efficiently solved by the alternating direction method of multipliers and hierarchical alternating least squares method.When the given matrix is huge,the cost of computation and communication is too high.Therefore,ONMF becomes challenging in the large-scale setting.The random projection is an efficient method of dimensionality reduction.In this paper,we apply the random projection to ONMF and propose two randomized algorithms.Numerical experiments show that our proposed algorithms perform well on both simulated and real data.展开更多
The paper presents the improved element-free Galerkin （IEFG） method for three-dimensional wave propa- gation. The improved moving least-squares （IMLS） approx- imation is employed to construct the shape function, w...The paper presents the improved element-free Galerkin （IEFG） method for three-dimensional wave propa- gation. The improved moving least-squares （IMLS） approx- imation is employed to construct the shape function, which uses an orthogonal function system with a weight function as the basis function. Compared with the conventional moving least-squares （MLS） approximation, the algebraic equation system in the IMLS approximation is not ill-conditioned, and can be solved directly without deriving the inverse matrix. Because there are fewer coefficients in the IMLS than in the MLS approximation, fewer nodes are selected in the IEFG method than in the element-free Galerkin method. Thus, the IEFG method has a higher computing speed. In the IEFG method, the Galerkin weak form is employed to obtain a dis- cretized system equation, and the penalty method is applied to impose the essential boundary condition. The traditional difference method for two-point boundary value problems is selected for the time discretization. As the wave equations and the boundary-initial conditions depend on time, the scal- ing parameter, number of nodes and the time step length are considered for the convergence study.展开更多
The reasonable prior information between the parameters in the adjustment processing can significantly improve the precision of the parameter solution. Based on the principle of equality constraints, we establish the ...The reasonable prior information between the parameters in the adjustment processing can significantly improve the precision of the parameter solution. Based on the principle of equality constraints, we establish the mixed additive and multiplicative random error model with equality constraints and derive the weighted least squares iterative solution of the model. In addition, aiming at the ill-posed problem of the coefficient matrix, we also propose the ridge estimation iterative solution of ill-posed mixed additive and multiplicative random error model with equality constraints based on the principle of ridge estimation method and derive the U-curve method to determine the ridge parameter. The experimental results show that the weighted least squares iterative solution can obtain more reasonable parameter estimation and precision information than existing solutions, verifying the feasibility of applying the equality constraints to the mixed additive and multiplicative random error model. Furthermore, the ridge estimation iterative solution can obtain more accurate parameter estimation and precision information than the weighted least squares iterative solution.展开更多
研究时变结构模态参数辨识,基于泛函矢量时变自回归模型(Functional series vector time-dependent AR model,FS-VTAR)提出一种改进的移动最小二乘法的时变结构模态参数辨识方法。该方法源于无网格法中构造形函数进行局部近似的思想,引...研究时变结构模态参数辨识,基于泛函矢量时变自回归模型(Functional series vector time-dependent AR model,FS-VTAR)提出一种改进的移动最小二乘法的时变结构模态参数辨识方法。该方法源于无网格法中构造形函数进行局部近似的思想,引入带权正交基函数对移动最小二乘(Moving least square,MLS)的基函数进行改进,使得在辨识时间域内构造形函数矩阵过程中不再出现数值条件问题,从而提高了计算精度。把时变系数在形函数上线性展开,利用最小二乘法得到形函数的系数,从而得到时变系数。把时变模型特征方程转换为广义特征值问题提取出模态参数。利用时变刚度系统非平稳振动信号验证该方法,结果表明:改进的移动最小二乘法相比于传统的FS-VTAR模型能有效地避免基函数形式的选择和很高的基函数阶数且更加高效,相比于移动最小二乘法能有效地避免辨识过程中的数值问题,具有更高的模态参数辨识精度。展开更多
在MIMO-OFDM水声通信系统中,由于信道间的相互干扰和水声信道严重时延扩展产生的频率选择性衰落,系统的通信误码率较高。针对这一问题,研究了空频编码的MIMO-OFDM通信,提出空频迭代信道估计与均衡(Spatial Frequency Iterative Channel ...在MIMO-OFDM水声通信系统中,由于信道间的相互干扰和水声信道严重时延扩展产生的频率选择性衰落,系统的通信误码率较高。针对这一问题,研究了空频编码的MIMO-OFDM通信,提出空频迭代信道估计与均衡(Spatial Frequency Iterative Channel Estimation and Equalization,SFICEE)方法。该方法通过载波间的空频正交性进行各收发阵元对的信道估计,并通过空频均衡获得符号初始估计,迭代更新信道估计,而后通过符号后验软信息反馈进行迭代空频软均衡。仿真结果表明,当误码率为10^(-3)时,文中所提出的SFICEE方法经过二次迭代与STBC方法相比具有4.8 d B的性能增益,相对于SFBC方法有2.8 d B的性能提升。当输入信噪比相同时,文中所提出方法的星座图更加收敛,可以更好地降低水下通信系统的误码率。展开更多
基金Supported by the National Natural Science Foundations of China(No.11271193)Humanities and Social Sciences Planning Foundation of Chinese Ministry of Education(11YJA910004)+1 种基金Natural Science Foundation of the Jiangsu Higher Education Institutions of China(11KJB110005)Key Research Base for Humanities and Social Sciences of Zhejiang Provincial High Education Talents(Statistics of Zhejiang Gongshang University)
文摘Recently, Kundu and Gupta （Metrika, 48：83 C 97, 1998） established the asymptotic normality of the least squares estimators in the two dimensional cosine model. In this paper, we give the approximation to the general least squares estimators by using random weights which is called the Bayesian bootstrap or the random weighting method by Rubin （Annals of Statistics, 9：130 C 134, 1981） and Zheng （Acta Math. Appl. Sinica （in Chinese）, 10（2）： 247 C 253, 1987）. A simulation study shows that this approximation works very well.
基金the National Natural Science Foundation of China(No.11901359)Shandong Provincial Natural Science Foundation(No.ZR2019QA017)。
文摘Orthogonal nonnegative matrix factorization(ONMF)is widely used in blind image separation problem,document classification,and human face recognition.The model of ONMF can be efficiently solved by the alternating direction method of multipliers and hierarchical alternating least squares method.When the given matrix is huge,the cost of computation and communication is too high.Therefore,ONMF becomes challenging in the large-scale setting.The random projection is an efficient method of dimensionality reduction.In this paper,we apply the random projection to ONMF and propose two randomized algorithms.Numerical experiments show that our proposed algorithms perform well on both simulated and real data.
基金supported by the National Natural Science Foundation of China (11171208)Shanghai Leading Academic Discipline Project (S30106)
文摘The paper presents the improved element-free Galerkin （IEFG） method for three-dimensional wave propa- gation. The improved moving least-squares （IMLS） approx- imation is employed to construct the shape function, which uses an orthogonal function system with a weight function as the basis function. Compared with the conventional moving least-squares （MLS） approximation, the algebraic equation system in the IMLS approximation is not ill-conditioned, and can be solved directly without deriving the inverse matrix. Because there are fewer coefficients in the IMLS than in the MLS approximation, fewer nodes are selected in the IEFG method than in the element-free Galerkin method. Thus, the IEFG method has a higher computing speed. In the IEFG method, the Galerkin weak form is employed to obtain a dis- cretized system equation, and the penalty method is applied to impose the essential boundary condition. The traditional difference method for two-point boundary value problems is selected for the time discretization. As the wave equations and the boundary-initial conditions depend on time, the scal- ing parameter, number of nodes and the time step length are considered for the convergence study.
基金supported by the National Natural Science Foundation of China,Grant Nos.42174011,41874001 and 41664001Innovation Found Designated for Graduate Students of ECUT,Grant No.DHYC-202020。
文摘The reasonable prior information between the parameters in the adjustment processing can significantly improve the precision of the parameter solution. Based on the principle of equality constraints, we establish the mixed additive and multiplicative random error model with equality constraints and derive the weighted least squares iterative solution of the model. In addition, aiming at the ill-posed problem of the coefficient matrix, we also propose the ridge estimation iterative solution of ill-posed mixed additive and multiplicative random error model with equality constraints based on the principle of ridge estimation method and derive the U-curve method to determine the ridge parameter. The experimental results show that the weighted least squares iterative solution can obtain more reasonable parameter estimation and precision information than existing solutions, verifying the feasibility of applying the equality constraints to the mixed additive and multiplicative random error model. Furthermore, the ridge estimation iterative solution can obtain more accurate parameter estimation and precision information than the weighted least squares iterative solution.
文摘研究时变结构模态参数辨识,基于泛函矢量时变自回归模型(Functional series vector time-dependent AR model,FS-VTAR)提出一种改进的移动最小二乘法的时变结构模态参数辨识方法。该方法源于无网格法中构造形函数进行局部近似的思想,引入带权正交基函数对移动最小二乘(Moving least square,MLS)的基函数进行改进,使得在辨识时间域内构造形函数矩阵过程中不再出现数值条件问题,从而提高了计算精度。把时变系数在形函数上线性展开,利用最小二乘法得到形函数的系数,从而得到时变系数。把时变模型特征方程转换为广义特征值问题提取出模态参数。利用时变刚度系统非平稳振动信号验证该方法,结果表明:改进的移动最小二乘法相比于传统的FS-VTAR模型能有效地避免基函数形式的选择和很高的基函数阶数且更加高效,相比于移动最小二乘法能有效地避免辨识过程中的数值问题,具有更高的模态参数辨识精度。
文摘在MIMO-OFDM水声通信系统中,由于信道间的相互干扰和水声信道严重时延扩展产生的频率选择性衰落,系统的通信误码率较高。针对这一问题,研究了空频编码的MIMO-OFDM通信,提出空频迭代信道估计与均衡(Spatial Frequency Iterative Channel Estimation and Equalization,SFICEE)方法。该方法通过载波间的空频正交性进行各收发阵元对的信道估计,并通过空频均衡获得符号初始估计,迭代更新信道估计,而后通过符号后验软信息反馈进行迭代空频软均衡。仿真结果表明,当误码率为10^(-3)时,文中所提出的SFICEE方法经过二次迭代与STBC方法相比具有4.8 d B的性能增益,相对于SFBC方法有2.8 d B的性能提升。当输入信噪比相同时,文中所提出方法的星座图更加收敛,可以更好地降低水下通信系统的误码率。
