• 한국통신학회논문지
• /
• 제30권11C호
• /
• pp.1116-1124
• /
• 2005

We investigated the mean and variance of the MSE and the MI-based image registration methods that have been widely applied for image registration. By using the first order Taylor series expansion, we have approximated the mean and the variance for one-dimensional image registration. The asymptotic results show that the MSE based method is unbiased and efficient for the same image registration problem while the MI-based method shows larger variance. However, for the different modality image registration problem, the MSE based method is largely biased while the MI based method still achieves registration. The results imply that the MI based method achieves robustness to the different image modalities at the cost of inefficiency. The analytical results are supported by simulation results.

• Communications for Statistical Applications and Methods
• /
• 제27권5호
• /
• pp.523-533
• /
• 2020

This paper suggests three available methods for finding nonnegative estimates of variance components of the random effects in mixed models. The three proposed methods based on the concepts of projections are called projection method I, II, and III. Each method derives sums of squares uniquely based on its own method of projections. All the sums of squares in quadratic forms are calculated as the squared lengths of projections of an observation vector; therefore, there is discussion on the decomposition of the observation vector into the sum of orthogonal projections for establishing a projection model. The projection model in matrix form is constructed by ascertaining the orthogonal projections defined on vector subspaces. Nonnegative estimates are then obtained by the projection model where all the coefficient matrices of the effects in the model are orthogonal to each other. Each method provides its own system of linear equations in a different way for the estimation of variance components; however, the estimates are given as the same regardless of the methods, whichever is used. Hartley's synthesis is used as a method for finding the coefficients of variance components.

• 한국컴퓨터정보학회논문지
• /
• 제14권10호
• /
• pp.73-82
• /
• 2009

본 논문은 자연이미지에 포함된 텍스트 영역을 찾기 위한 방법으로서 기존에 제안한 색 분산 특징을 이용한 방법에서 분산이 제대로 추출되지 않는 문자 획들에 대한 복원 방법을 제안한다. 이전의 색 분산 특징을 이용한 추출방법에서는 고정된 크기의 수평 및 수직 분간 추출 윈도우를 사용함으로서 문자 획이 두껍거나 긴 경우에는 색 분산이 제대로 추출되지 않는 단점이 있었다. 따라서 본 논문에서는 미 추출된 색 분산을 연결요소 외곽사각형의 기하학적인 정보와 경험적인(Heuristic) 지식을 함께 이용하여 복원하는 방법을 제안한다. 제안한 방법은 다양한 종류의 디지털 카메라와 휴대폰 카메라를 이용해서 취득한 문서 유형의 이미지와 간판, 거리 표지판 등의 자연이미지를 사용하여 테스트 하였으며, 특히 큰 글자를 포함하는 자연이미지에 대해서도 텍스트 추출의 정확성이 향상된 것을 확인할 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제30권4호
• /
• pp.403-410
• /
• 2023

Two-Phase sampling, which was first introduced by Neyman (1938), has various applications in different forms. Variance estimation for two-phase sampling has been an important research topic because conventional variance estimators used in most softwares are not working. In this paper, we considered a variance estimation for two-phase sampling in which stratified two-stage cluster sampling designs are used in both phases. By defining a conditionally unbiased estimator of an approximate variance estimator, which is calculable when all elements in the first phase sample are observed, we propose an explicit form of variance estimator of the double expanded estimator for a two-phase sample. A small simulation study shows the proposed variance estimator has a negligible bias with small variance. The suggested variance estimator is also applicable to other linear estimators of the population total or mean if appropriate residuals are defined.

• 한국컴퓨터그래픽스학회논문지
• /
• 제7권1호
• /
• pp.11-17
• /
• 2001

프랙탈 이미지 코딩은 높은 압축율을 비롯하여 많은 장점을 가지고 있다. 그러나 압축 과정은 일반적으로 domain 블록 pool에 대한 긴 탐색시간으로 효율이 나빠진다. 본 논문에서는 블록 분류와 분산 기반의 탐색을 병용한 domain 블록 pool 탐색 방법을 소개한다. 이 방법은 블록 분류에 대하여 분류 블록의 분산 값은 독립적이라는 사실을 이용한다. 따라서 이 방법은 단순한 분산 기반의 탐색 방법보다 O(number of classes)에 비례하는 탐색 속도향상이 된다. 실험의 결과는 본 방법이 단순히 분산 값을 적용한 탐색 방법과 비교하여 이미지 품질은 거의 그대로 유지하면서 17배 이상의 속도 향상을 이루었음을 보인다. 또한 이미지 품질의 가시적인 손실 없이 탐색 속도를 더욱 향상시키는 분산 기반의 탐색 방법을 제안한다.

• 품질경영학회지
• /
• 제41권1호
• /
• pp.119-134
• /
• 2013

Purpose: The purpose of this paper is to show whether the results are changed with respect to the variance of the data, by analysis of data obtained from the Taguchi experimental techniques and general experiment. Because which cannot be prove by mathematical Formula, through experimental examples will show. Methods: Taguchi experiments were carried out with paper Helicopter experiment. Experimental Data are obtained by special designed Drop Test Equipment. While Experimental value arbitrarily changed, we looked at how Significant control Factor of Taguchi Methods and Factor experiments are changed. This process cannot be expressed as a Mathematical formula, but showed as a numerical example. Results: Saw significant changes in the factors when data is outside a certain range of the experimental data. By Test of Equivalence Variance, Experiment data is verified reliability. To find the Control Factor, Taguchi Method is better than the general experiment. Conclusion: We know that a Significant Factor is changed with the range of Variance of Experiment Data. The value of this paper is verified change process with Numerical Data obtained Experiment.

• Industrial Engineering and Management Systems
• /
• 제7권1호
• /
• pp.44-50
• /
• 2008

Focusing on the exponential smoothing method equivalent to (1, 1) order ARMA model equation, a new method of estimating smoothing constant using exponential smoothing method is proposed. This study goes beyond the usual method of arbitrarily selecting a smoothing constant. First, an estimation of the ARMA model parameter was made and then, the smoothing constants. The empirical example shows that the theoretical solution satisfies minimum variance of forecasting error. The new method was also applied to the stock market price of electrical machinery industry (6 major companies in Japan) and forecasting was accomplished. Comparing the results of the two methods, the new method appears to be better than the ARIMA model. The result of the new method is apparently good in 4 company data and is nearly the same in 2 company data. The example provided shows that the new method is much simpler to handle than ARIMA model. Therefore, the proposed method would be better in these general cases. The effectiveness of this method should be examined in various cases.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 춘계 학술발표회 논문집
• /
• pp.233-238
• /
• 2005

S${\"{a}}$rndal (1996) and Knottnerus (2003) had a critical look at the well known variance estimator of Sen (1953) and Yates and Grundy (1953) in probability proportional to size sampling. In this paper, we point out that although their approaches can avoid the difficulties in variance estimation with respect to the joint probabilities, there exist the disadvantages in practice. Also, we describe a sampling procedure available in statistical software that are useful for the variance estimation.

• Communications for Statistical Applications and Methods
• /
• 제13권1호
• /
• pp.61-72
• /
• 2006

When using the well-known variance estimator of Sen (1953) and Yates and Grundy (1953) in inclusion probability proportional to size sampling, we often encounter the problems due to the calculation of the joint probabilities. Sarndal (1996) and Knottnerus (2003) proposed alternative strategies for variance estimation to avoid those problems in the traditional method. We discuss some of practical issues that arise when they are used. Also, we describe the traditional strategy using a sampling procedure available in a statistical software. It would be one of the attractive choices for design-based variance estimation.

• Nuclear Engineering and Technology
• /
• 제49권6호
• /
• pp.1172-1180
• /
• 2017

The application of Monte Carlo (MC) to large-scale fixed-source problems has recently become possible with new hybrid methods that automate generation of parameters for variance reduction techniques. Two common variance reduction techniques, weight windows and source biasing, have been automated and popularized by the consistent adjoint-driven importance sampling (CADIS) method. This method uses the adjoint solution from an inexpensive deterministic calculation to define a consistent set of weight windows and source particles for a subsequent MC calculation. One of the motivations for source consistency is to avoid the splitting or rouletting of particles at birth, which requires computational resources. However, it is not always possible or desirable to implement such consistency, which results in inconsistent source biasing. This paper develops an original framework that mathematically expresses the coupling of the weight window and source biasing techniques, allowing the authors to explore the impact of inconsistent source sampling on the variance of MC results. A numerical experiment supports this new framework and suggests that certain classes of problems may be relatively insensitive to inconsistent source sampling schemes with moderate levels of splitting and rouletting.