• Journal of the Korean Statistical Society
• /
• v.15 no.2
• /
• pp.97-106
• /
• 1986

Assume that $X_1, X_2, \cdots, X_N$ are iid p-dimensional normal random vectors ($p \geq 3$) with unknown covariance matrix. The problem of estimating multivariate normal mean vector in an empirical Bayes situation is considered. Empirical Bayes estimators, obtained by Bayes treatmetn of the covariance matrix, are presented. It is shown that the estimators are minimax, each of which domainates teh maximum likelihood estimator (MLE), when the loss is nonsingular quadratic loss. We also derive approximate credibility region for the mean vector that takes advantage of the fact that the MLE is not the best estimator.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1993.06a
• /
• pp.206-209
• /
• 1993

The main purpose of this paper is to verify the effectiveness of a high resolution direction finding method, so called the‘averaged MUSIC’. This method uses a new sample array covariance matrix that consists of diagonal components obtained by taking averages of the diagonal component values of the sample covariance matrix for the MUSIC. The paper shows that the proposed method performs higher resolved direction-of-arrival estimation and better resolution probability than the MUSIC in such cases as low signal-to-noise ratio, when the number of sensors used is finite, based on the statistical analysis.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.4
• /
• pp.741-747
• /
• 2009

Properties of multivariate Shewhart and EWMA (Exponentially Weighted Moving Average) control charts for monitoring variance-covariance matrix of quality variables are investigated. Performances of the proposed charts are evaluated for matched fixed sampling interval (FSI) and variable sampling interval (VSI) charts in terms of average time to signal (ATS) and average number of samples to signal (ANSS). Average number of swiches (ANSW) of the proposed VSI charts are also investigated.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.10a
• /
• pp.705-708
• /
• 2010

In the paper, we have studied on algorithms for two-dimensional positioning based on GPS pseudorange Technique. First, the linearized state equation was mathematically derived based on GPS pseudorange technique. Second, the geometry model with respect to triangles formed using unit-vectors were proposed for investigation of land-based radio positioning. Finally, the corresponding mathematical formulations for DOP values and covariance matrix were designed for two-dimensional positioning.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.45-49
• /
• 1989

The observability of an strapdown inertial navigation system(SDINS) is investigated. The piece-wise constant systems are defined and the stepped observability matrix scheme is applied to observability analysis of SDINS theoretically, the results are compared with that of covariance simulation. It is found that SDINS is more observable than gimballed inertial navigation system (GINS) in the case of the variation of vehicle attitude, and is found that the stepped observability matrix theory is simple and useful for the analysis of the system observability but the results are not completely same as that of covariance simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.834-838
• /
• 1992

Tracking performance depends on the quantity of the measurement data. In the Kalman-Bucy filter and other trackers, this dependence is well understood in terms of the measurement noise covariance matrix, which specifies the uncertainty in the value of measurement inputs. In this paper, we derived approximated error covariance matrix to evaluate the dependence of target detection probability and false alarm probability in the presence of uncertainty of measurement origin.

• Journal of applied mathematics & informatics
• /
• v.27 no.5_6
• /
• pp.1429-1433
• /
• 2009

The likelihood distance for the joint distribution of two multivariate normal distributions with common covariance matrix is explicitly derived. It is useful for identifying outliers which do not follow the joint multivariate normal distribution with common covariance matrix. The likelihood distance derived here is a good ground for the use of a generalized Wilks statistic in influence analysis of two multivariate normal data.

• Journal of the Korean Statistical Society
• /
• v.24 no.2
• /
• pp.407-417
• /
• 1995

The h-plot is a graphical technique for displaying the structure of one population's variance-covariance matrix. This follows the mathematical algorithem of the principle component biplot based on the singular value decomposition. But it is known that the singular value decomposition is not resistant, i.e., it is very sensitive to small changes in the input data. In this article, since the mathematical algorithm of the h-plot is equivalent to that of principal component biplot of Choi and Huh (1994), we derive the resistant h-plot.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.159-166
• /
• 2003

To reduce the high dimensionality required for training of feature vectors in speaker identification, we propose an efficient GMM based on local PCA with Fuzzy clustering. The proposed method firstly partitions the data space into several disjoint clusters by fuzzy clustering, and then performs PCA using the fuzzy covariance matrix in each cluster. Finally, the GMM for speaker is obtained from the transformed feature vectors with reduced dimension in each cluster. Compared to the conventional GMM with diagonal covariance matrix, the proposed method needs less storage and shows faster result, under the same performance.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1251-1256
• /
• 2011

Consider a p-variate ($p{\geq}4$) normal distribution with mean ${\theta}$ and identity covariance matrix. Using a simple property of noncentral chi square distribution, the generalized Bayes estimators dominating the Lindley estimator under quadratic loss are given based on the methods of Brown, Brewster and Zidek for estimating a normal variance. This result can be extended the cases where covariance matrix is completely unknown or ${\Sigma}={\sigma}^2I$ for an unknown scalar ${\sigma}^2$.