期刊文献+
共找到9篇文章
< 1 >
每页显示 20 50 100
具有约束条件的最小φ散度估计
1
作者 刘常胜 张晓果 《黑龙江科技信息》 2009年第28期39-39,148,共2页
在多项抽样分布和对数线性模型下,给出了在一般约束条件下,未知参数的最小F散度约束估计,并证明了该估计的渐进正态性。
关键词 约束估计 最小F 散度估计 渐近正态性
下载PDF
INAR模型的条件最小密度功效散度估计及应用
2
作者 杨凯 孙明昱 赵志文 《吉林师范大学学报(自然科学版)》 2024年第4期34-45,共12页
为了克服极大似然估计对异常值的敏感性,提出了一种条件最小密度功效散度估计,研究了该估计的渐近性质,包括强相合性和渐近正态性.通过数值模拟研究了该估计的估计效果.通过对季度地震数据的拟合与预测,证明了当数据集中存在异常值时,... 为了克服极大似然估计对异常值的敏感性,提出了一种条件最小密度功效散度估计,研究了该估计的渐近性质,包括强相合性和渐近正态性.通过数值模拟研究了该估计的估计效果.通过对季度地震数据的拟合与预测,证明了当数据集中存在异常值时,条件最小密度功效散度估计的参数估计结果比极大似然估计的结果更加准确. 展开更多
关键词 整数值时间序列 整数值自回归模型 最小密功效散度估计 稳健估计
下载PDF
对数线性模型下基于Φ-散度测度的均值滑动检验
3
作者 金应华 向思源 《广东工业大学学报》 CAS 2018年第4期32-36,44,共6页
研究了对数线性模型的均值滑动检验.基于Φ-散度和最小Φ-散度估计提出了3类检验统计量,它们是似然比检验统计量和Pearson检验统计量的推广.研究了这3类统计量的渐近分布,并用此理论结果分析了一组实际数据.最后通过模拟研究表明,在小... 研究了对数线性模型的均值滑动检验.基于Φ-散度和最小Φ-散度估计提出了3类检验统计量,它们是似然比检验统计量和Pearson检验统计量的推广.研究了这3类统计量的渐近分布,并用此理论结果分析了一组实际数据.最后通过模拟研究表明,在小样本量下,这3类统计量中有比似然比检验统计量和Pearson检验统计量表现更好的统计量. 展开更多
关键词 对数线性模型 Φ- 最小Φ-散度估计 均值滑动检验
下载PDF
An Improved Multi-scale Estimation Method of Signal
4
作者 胡长流 文成林 《Chinese Quarterly Journal of Mathematics》 CSCD 2000年第2期102-107,共6页
In this paper an improved multi_scale estimation method of signal is gaven.The detail signals on each scale are further more decomposed with wavelet transform.The subdetail signals and subsmoothing signals are process... In this paper an improved multi_scale estimation method of signal is gaven.The detail signals on each scale are further more decomposed with wavelet transform.The subdetail signals and subsmoothing signals are processed with different threshold respectively. The smoothing signals on the coarsest scale are processed with Kalman fitering and reconstructed with the detail signal on each scale.At last the signal estimate value on the original scale is obtained. 展开更多
关键词 multi_scale analysis discrete wavelet transform Kalman filtering
下载PDF
A modified method to estimate eddy diffusivity in the North Pacific using altimeter eddy statistics 被引量:3
5
作者 张志伟 李亚汝 田纪伟 《Chinese Journal of Oceanology and Limnology》 SCIE CAS CSCD 2013年第4期925-933,共9页
The method proposed by Stammer (1998) is modified using eddy statistics from altimeter observation to obtain more realistic eddy diffusivity (K) for the North Pacific. Compared with original estimates, the modified K ... The method proposed by Stammer (1998) is modified using eddy statistics from altimeter observation to obtain more realistic eddy diffusivity (K) for the North Pacific. Compared with original estimates, the modified K has remarkably reduced values in the Kuroshio Extension (KE) and North Equatorial Counter Current (NECC) regions, but slightly enhanced values in the Subtropical Counter Current (STCC) region. In strong eastward flow areas like the KE and NECC, owing to a large difference between mean flow velocity and propagation velocity of mesoscale eddies, tracers inside the mesoscale eddies are transported outside rapidly by advection, and mixing length L is hence strongly suppressed. The low eddy probability (P) is also responsible for the reduced K in the NECC area. In the STCC region, however, L is mildly suppressed and P is very high, so K there is enhanced. The zonally-averaged K has two peaks with comparable magnitudes, in the latitude bands of the STCC and KE. In the core of KE, because of the reduced values of P and L, the zonally-averaged K is a minimum. Zonally-integrated eddy heat transport in the KE band, calculated based on the modified K, is much closer to the results of previous independent research, indicating the robustness of our modified K. The map of modified K provides useful information for modeling studies in the North Pacific. 展开更多
关键词 eddy diffusivity mesoscale eddy North Pacific
下载PDF
Optimal sensor scheduling for hybrid estimation
6
作者 LIU Jian-liang SUN Yao +2 位作者 YANG Jian LIU Wei-yi CHEN Wei-min 《Journal of Central South University》 SCIE EI CAS 2013年第8期2186-2194,共9页
A sensor scheduling problem was considered for a class of hybrid systems named as the stochastic linear hybrid system (SLHS). An algorithm was proposed to select one (or a group of) sensor at each time from a set ... A sensor scheduling problem was considered for a class of hybrid systems named as the stochastic linear hybrid system (SLHS). An algorithm was proposed to select one (or a group of) sensor at each time from a set of sensors. Then, a hybrid estimation algorithm was designed to compute the estimates of the continuous and discrete states of the SLHS based on the observations from the selected sensors. As the sensor scheduling algorithm is designed such that the Bayesian decision risk is minimized, the true discrete state can be better identified. Moreover, the continuous state estimation performance of the proposed algorithm is better than that of hybrid estimation algorithms using only predetermined sensors. Finallyo the algorithms are validated through an illustrative target tracking example. 展开更多
关键词 sensor scheduling hybrid systems Bayesian decision risk target tracking
下载PDF
Gradient Estimates for a Nonlinear Diffusion Equation on Complete Manifolds 被引量:1
7
作者 Jiaxian WU Qihua RUAN Yihu YANG 《Chinese Annals of Mathematics,Series B》 SCIE CSCD 2015年第6期1011-1018,共8页
This paper deals with the gradient estimates of the Hamilton type for the positive solutions to the following nonlinear diffusion equation:on a complete noncompact Riemannian manifold with a Bakry-Emery Ricci curvatu... This paper deals with the gradient estimates of the Hamilton type for the positive solutions to the following nonlinear diffusion equation:on a complete noncompact Riemannian manifold with a Bakry-Emery Ricci curvature bounded below by -K (K 〉 0), where φ is a C2 function, a(x) and b(x) are C1 functions with certain conditions. 展开更多
关键词 Gradient estimate Bakry-Emery Ricci curvature Nonlinear diffusion equation 58J35
原文传递
Gradient Estimates for a Nonlinear Parabolic Equation with Diffusion on Complete Noncompact Manifolds
8
作者 Liang ZHAO Zongwei MA 《Chinese Annals of Mathematics,Series B》 SCIE CSCD 2015年第1期57-66,共10页
The authors obtain some gradient estimates for positive solutions to the following nonlinear parabolic equation:αu/αt=△u-b(x,t)u~σ on complete noncompact manifolds with Ricci curvature bounded from below,where 0&... The authors obtain some gradient estimates for positive solutions to the following nonlinear parabolic equation:αu/αt=△u-b(x,t)u~σ on complete noncompact manifolds with Ricci curvature bounded from below,where 0<σ<1 is a real constant,and b(x,t) is a function which is C^2 in the x-variable and C^1 in the t-variable. 展开更多
关键词 Gradient estimates Positive solutions Harnack inequality
原文传递
A LEGENDRE GALERKIN SPECTRAL METHOD FOR OPTIMAL CONTROL PROBLEMS 被引量:1
9
作者 Yanping CHEN Nianshi XIA Nianyu YI 《Journal of Systems Science & Complexity》 SCIE EI CSCD 2011年第4期663-671,共9页
This paper considers the Legendre Galerkin spectral approximation for the unconstralnea optimal control problems. The authors derive a posteriori error estimate for the spectral approximation scheme of optimal control... This paper considers the Legendre Galerkin spectral approximation for the unconstralnea optimal control problems. The authors derive a posteriori error estimate for the spectral approximation scheme of optimal control problem. By choosing the appropriate basis functions, the stiff matrix of the discretization equations is sparse. And the authors use the Fast Legendre Transform to improve the efficiency of this method. Two numerical experiments demonstrating our theoretical results are presented. 展开更多
关键词 Legendre-Galerkin optimal control spectral method.
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部