• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.391-401
• /
• 2011

본 논문에서는 자료 내의 군집 중에 '부(父) 군집'과 모(母) 군집'이라 부르는 두 군집 사이에, 합성된 평균 분산을 가지는 '합성군집' 즉 '자식 군집'이라 부르는 한 군집이 있을 경우에 주목하여, 그들의 관계를 평균과 분산에 관해 모형화하고 각각의 군집을 식별하는 방법을 제공하였다. 관측치는 정규혼합모형을 따른다고 가정하고, EM 알고리즘을 통해 모형 추정을 시도하였다. 추정 과정에 여러 난제가 있었으나, 근사적 방법으로 비교적 잘 극복할수 있었다. 그리고 수치실험을 통해 제안방법은 성공적으로 주어진 세 군집 즉 '군집족(族)'을 식별할수 있음을 보였다.

• 대한수학회보
• /
• 제48권3호
• /
• pp.523-537
• /
• 2011

A receiver operating characteristic (ROC) curve plots the true positive rate of a classier against its false positive rate, both of which are accuracy measures of the classier. The ROC curve has several interesting geometrical properties, including concavity which is a necessary condition for a classier to be optimal. In this paper, we study the nonparametric maximum likelihood estimator (NPMLE) of a concave ROC curve and its modification to reduce bias. We characterize the NPMLE as a solution to a geometric programming, a special type of a mathematical optimization problem. We find that the NPMLE is close to the convex hull of the empirical ROC curve and, thus, has smaller variance but positive bias at a given false positive rate. To reduce the bias, we propose a modification of the NPMLE which minimizes the $L_1$ distance from the empirical ROC curve. We numerically compare the finite sample performance of three estimators, the empirical ROC curve, the NMPLE, and the modified NPMLE. Finally, we apply the estimators to estimating the optimal ROC curve of the variance-threshold classier to segment a low depth of field image and to finding a diagnostic tool with multiple tests for detection of hemophilia A carrier.

• Asian-Australasian Journal of Animal Sciences
• /
• 제12권7호
• /
• pp.1015-1018
• /
• 1999

Single trait mixed models have been dominantly utilized for genetic evaluation of the reproductive traits in swine. However employing multiple trait approach may lead to more accurate genetic evaluations. For 5 litter size and litter weight traits of Danish Landrace, genetic parameters were estimated with a multiple trait mixed model. The heritability estimates were 0.02, 0.03, 0.03, 0.05, and 0.07, respectively for litter size at birth, litter size born alive, litter weight at birth, litter size at weaning, and litter weight at weaning. Negative genetic correlations were all positive. The litter weight at birth showed genetic antagonism with litter size born alive (-0.65) and litter size at weaning (-0.31), but positive with litter size at birth (0.47) and litter weight at weaning (0.31). The estimates of environmental correlations were larger than their corresponding genetic correlation estimates except for those between litter weight at birth and the other four traits. This study recommends simultaneous selection for two or more traits with multivariate mixed models in order to improve overall economic response.

• 응용통계연구
• /
• 제17권2호
• /
• pp.281-301
• /
• 2004

본 논문에서는 일변량 정규분포를 따르는 확률변수의 관측치열에 대한 변화점 문제(change point problem)를 고찰한다. 변화점의 존재유무, 그리고 만일 변화점이 존재한다면 어떠한 유형으로 발생했는지 즉, 변화점 발생 이후로 평균만 변화, 분산만 변화, 또는 평균과 분산 모두가 변화했는지를 밝힌다. 가능한 여러 유형의 변화모형들 가운데 최적의 모형을 선택하기 위해 베이지안 모형선택 기법을 이용하고, 선택된 모형에 내재된 모수를 추정 하기 위해 메트로폴리스-혜스팅스 알고리 즘을 포함한 깁스샘플링 을 이용한다. 이러한 방법론은 모의실험을 통해 검토되고, 또한 서울지역의 겨울철 평균기온 자료에 적용된다.

• 대한기계학회논문집A
• /
• 제33권8호
• /
• pp.745-752
• /
• 2009

In robust design, the mean and variance of design performance are frequently used to measure the design performance and its robustness under uncertainties. In this paper, we present the Gauss-type quadrature formula as a rigorous method for mean and variance estimation involving arbitrary input distributions and further extend its use to robust design optimization. One dimensional Gauss-type quadrature formula are constructed from the input probability distributions and utilized in the construction of multidimensional quadrature formula such as the tensor product quadrature (TPQ) formula and the univariate dimension reduction (UDR) method. To improve the efficiency of using it for robust design optimization, a semi-analytic design sensitivity analysis with respect to the statistical moments is proposed. The proposed approach is applied to a simple bench mark problems and robust topology optimization of structures considering various types of uncertainty.

• Asian-Australasian Journal of Animal Sciences
• /
• 제15권2호
• /
• pp.166-171
• /
• 2002

The main objective of the present study is to estimate the crossbreeding parameters in respect to serum lysozyme level in broilers. The experiment involved a complete $4{\times}4$ diallel design using four synthetic broiler lines namely Coloured Synthetic Male Line (CSML), White Synthetic Male Line (WSML), Coloured Synthetic Female Line (CSFL) and Naked Neck Line (NNL). The lyophilised Micrococcus lysodeikticus suspension was used to detect the lysozyme level in the serum of birds. The data were analysed by least-squares method to find the effects of genetic and non-genetic factors using appropriate model. The crossbreeding parameters for this trait were estimated by complete diallel model assuming the effect of each synthetic line as fixed. The results indicated that additive and non-additive genetic variation attributed to minor genes at many loci is important for the genetic control of serum lysozyme level in chickens. Total non-additive components of variance also showed significant amount of heterosis in crossbred progenies, and therefore exploitation of non-additive component of variance is possible for improvement in serum lysozyme level in broilers. The overall results suggested that for commercial broiler production system, the selection for specialised line on the basis of serum lysozyme level and subsequent crossing of parent lines could enhance the immunocompetence status in relation to serum lysozyme level in crossbred chickens.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.2928-2947
• /
• 2015

Adaptive Gaussian filter (AGF) is a recently developed switching filter to remove salt and pepper noise. AGF first directly identifies pixels of gray levels 0 and 255 as noise pixels, and then only restored noise pixels using a Gaussian filter with adaptive variance based on the estimated noise density. AGF usually achieves better denoising effect in comparison with other filters. However, AGF still fails to obtain good denoising effect on images with noise-free pixels of gray levels 0 and 255, due to its severe false alarm in its noise detection stage. To alleviate this issue, a modified version of AGF is proposed in this paper. Specifically, the proposed filter first performs noise detection via an image block based noise density estimation and sequential noise density guided rectification on the noise detection result of AGF. Then, a modified Gaussian filter with adaptive variance and window size is used to restore the detected noise pixels. The proposed filter has been extensively evaluated on two representative grayscale images and the Berkeley image dataset BSDS300 with 300 images. Experimental results showed that the proposed filter achieved better denoising effect over the state-of-the-art filters, especially on images with noise-free pixels of gray levels 0 and 255.

• Nuclear Engineering and Technology
• /
• 제40권7호
• /
• pp.551-560
• /
• 2008

Radiation has stochastic aspects in its generation, its choice of interaction mode during traveling in media, and its impact on living bodies. In certain circumstances, like in high dose environments resulting from low-LET radiation, the variance in its impact on a target volume is negligible. On the contrary, in low dose environments, especially when they are attributed to high-LET radiation, the impact on the target carries with it a large variance. This variation is more significant for smaller target volumes. Microdosimetric techniques, which have been developed to estimate the distribution of radiation energy deposited to cellular and subcellular-sized targets, contrast with macrodosimetric techniques which count only the average value. Since cells and DNA compounds are the critical targets in human bodies, microdosimetry, or dose estimation by microscopic approach, helps one better analyze the biological effects of radiation on the human body. By utilizing microbeam systems designed for individual cell irradiation, scientists have discovered that human cells exhibit radiosensitive reactions without being hit themselves (bystander effect). During the past 10 or more years, a new therapeutic protocol using discontinuous multiple micro-slit beams has been investigated for its clinical application. It has been suggested that the beneficial bystander effect is the essence of this protocol.

• 대한전자공학회논문지SP
• /
• 제45권5호
• /
• pp.87-94
• /
• 2008

본 논문에서는 손실된 블록의 은닉을 위한 방향성을 가지는 블록 복구 방법을 제안한다. 일반적으로 영상의 강한 에지는 웨이블릿 영역에서 큰 계수 값을 가지기 때문에 분산 또한 큰 값으로 나타난다. 손실 블록의 에지 방향을 추정하기 위해서 웨이블릿 계수들의 분산을 이용한 $X^2$ 가설 검증 기법을 적용한단. 추정된 에지의 방향에 따라 보간을 수행하며, 손실 화소를 보간하기 위하여 사용되는 화소는 에지 방향에 따라 결정된다. 제안 방법은 이전 방법과의 성능비교에서 주관적으로나 객관적으로 나 더 좋은 성능을 나타낸다.

• Structural Engineering and Mechanics
• /
• 제86권5호
• /
• pp.621-633
• /
• 2023

Stability analysis and support system estimation of the Beheshtabad water transmission tunnel is investigated in this research. A combination approach based on the rock mass rating (RMR) and rock mass quality index (Q) is used for this purpose. In the first step, 40 datasets related to the petrological, structural, hydrological, physical, and mechanical properties of tunnel host rocks are measured in the field and laboratory. Then, RMR, Q, and height of influenced zone above the tunnel roof are computed and sorted into five general groups to analyze the tunnel stability and determine its support system. Accordingly, tunnel stand-up time, rock load, and required support system are estimated for five sorted rock groups. In addition, various empirical relations between RMR and Q i.e., linear, exponential, logarithmic, and power functions are developed using the analysis of variance (ANOVA). Based on the significance level (sig.), determination coefficient (R²) and Fisher-test (F) indices, power and logarithmic equations are proposed as the optimum relations between RMR and Q. To validate the proposed relations, their results are compared with the results of previous similar equations by using the variance account for (VAF), root mean square error (RMSE), mean absolute percentage error (MAPE) and mean absolute error (MAE) indices. Comparison results showed that the accuracy of proposed RMR-Q relations is better than the previous similar relations and their outputs are more consistent with actual data. Therefore, they can be practically utilized in designing the tunneling projects with an acceptable level of accuracy and reliability.