• 산업경영시스템학회지
• /
• 제35권3호
• /
• pp.129-135
• /
• 2012

Companies strive for quality improvement and use process data obtained through measurement process to monitor and control the process. Measurement data contain variation due to error of operator and instrument. The total variation is sum of product variation and measurement variation. Gage R&R is for repeatability and reproducibility of measurement system. Gage R&R study is usually conducted to analyze the measurement process. In performing the gage R&R study, several parameters such as the appropriate number of operators (o), sample size of parts (p), and replicate (r) are used. In this paper we propose how to determine the optimal combination of number of operators (o), sample size of parts (p), and replicates (r) considering measurement time and cost by statistical method.

• Communications for Statistical Applications and Methods
• /
• 제27권3호
• /
• pp.301-311
• /
• 2020

Schwarz's Bayesian information criterion (BIC) is one of the most popular criteria for model selection, that was derived under the assumption of independent and identical distribution. For correlated data in longitudinal studies, Jones (Statistics in Medicine, 30, 3050-3056, 2011) modified the BIC to select the best linear mixed effects model based on the effective sample size where the number of parameters in covariance structure was not considered. In this paper, we propose an extended Jones' modified BIC by considering covariance parameters. We conducted simulation studies under a variety of parameter configurations for linear mixed effects models. Our simulation study indicates that our proposed BIC performs better in model selection than Schwarz's BIC and Jones' modified BIC do in most scenarios. We also illustrate an example of smoking data using a longitudinal cohort of cancer patients.

• Communications for Statistical Applications and Methods
• /
• 제16권5호
• /
• pp.763-779
• /
• 2009

노래 연습장에서 연주되는 노래곡목별 히팅수를 정확하게 추정하기 위한 표본설계에서는 조사모집단 정의와 층화방안을 연구하고 기존데이터를 분석하여 표본크기를 산출한 후에 표본배분방법을 연구하였다. 표본설계에 의해서 선정된 표본업소들의 대표성을 온라인 노래연습장의 로그데이터를 이용하여 모수추정치의 오차를 분석하여 검토하였다. 오프라인 노래 연습장의 모수추정법을 제안하고 실제로 수집한 로그데이터로부터 모수추정치를 계산하여 온라인과 오프라인 노래연습장에서 연주되는 노래곡목별 히팅수에서 많이 차이가 있음을 보였다. 온라인과 오프라인 노래연습장의 특성차이를 반영한 분배방법의 개선안을 제안하고 비교분석을 통해서 최적 분배방법을 선정하였다.

• 품질경영학회지
• /
• 제16권2호
• /
• pp.82-91
• /
• 1988

This study is concerned with the development of the economic sampling inspection plan when it is possible to carry out a nondestructive screening inspection for the rejected lots by substitutive characteristics closely related to the original quality characteristic. It is assumed that the probabilities of those errors depend linearly on the fraction defective of the process. The inspection policies considered are as follows: take a random sample of size n from the lot of size N and perform a destructive test on the sample. If the number of the defective items is not greater than a critical number C, accept the lot. Expected cost functions are obtained when the process average can be considered to follow a beta distribution and the way of finding the optimal values of (n, c) is to be explored.

• 한국ITS학회 논문지
• /
• 제13권6호
• /
• pp.25-33
• /
• 2014

본 연구는 부산광역시의 전형적인 단속류 구간을 대상으로 DSRC를 통해 수집되는 구간교통정보의 신뢰성을 구간별 적정 차량 표본 수 산정기법을 통해 분석하였다. 해당 단속류 대상지를 구성하는 개별 구간에 대한 표본 수 산정을 위하여 VISSIM 모델을 이용하였다. 실제 DSRC를 통해 관찰된 하이패스 차량 수와 두 유의수준(90%와 95%)에서 산정된 적정 표본 수를 비교한 결과, 연속류에 비해 단속류에 더 많은 이상치의 발생요인이 존재한다는 점, 인접한 두 교차로와 다수의 진출입로로 구성된 하나의 구간을 통과하는 하이패스 차량의 부족으로 신뢰성 있는 구간교통정보의 집계가 어려운 점, 비첨두시간보다 첨두시간의 구간교통정보가 상대적인 신뢰성이 높은 점, 표본 수 산정의 유의수준에 따라 구간교통정보의 신뢰성이 차별화된다는 점 등을 확인할 수 있었다. 해당 구간의 길이에 따른 진출입로의 밀도와 교통신호운영의 차이는 유효 표본 수 산정에 직접적인 영향을 미치며 결국 구간교통정보의 신뢰성을 결정하게 된다. 따라서 구간의 길이에 따라 노변기지국의 개수를 조절하면 DSRC를 통해 수집되는 구간교통정보의 신뢰성이 개선될 것으로 기대된다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.901-905
• /
• 2005

Monte Carlo localization is known to be one of the most reliable methods for pose estimation of a mobile robot. Much research has been done to improve performance of MCL so far. Although MCL is capable of estimating the robot pose even for a completely unknown initial pose in the known environment, it takes considerable time to give an initial estimate because the number of random samples is usually very large especially for a large-scale environment. For practical implementation of the MCL, therefore, a reduction in sample size is desirable. This paper presents a novel approach to reducing the number of samples used in the particle filter for efficient implementation of MCL. To this end, the topological information generated off- line using a thinning method, which is commonly used in image processing, is employed. The topological map is first created from the given grid map for the environment. The robot scans the local environment using a laser rangefinder and generates a local topological map. The robot then navigates only on this local topological edge, which is likely to be the same as the one obtained off- line from the given grid map. Random samples are drawn near the off-line topological edge instead of being taken with uniform distribution, since the robot traverses along the edge. In this way, the sample size required for MCL can be drastically reduced, thus leading to reduced initial operation time. Experimental results using the proposed method show that the number of samples can be reduced considerably, and the time required for robot pose estimation can also be substantially decreased.

• 한국의류학회지
• /
• 제21권1호
• /
• pp.206-216
• /
• 1997

The purpose of this study was to determine the pore size distributions (PSDs) of polyester woven fabrics by using liquid extraction method. Three types of PSDs-percent PSD, PSD per unit area of sample and PSD per unit weight of sample-were evaluated. Plain, twill and satin polyester fabrics with various fabric counts were used as specimens. Results showed that the interyarn PSDs reflected the fabric characteristics such as the fabric count and the weave type and the intrayarn PSDs reflected the thread characteristics such as the number of fibers, the fiber diameter, the thread diameter and the thread twist. Of three types of PSDs, the PSD per unit area of sample best reflect fabric and thread characteritics. As the fabric count decreased, rc increased and interyarn pore volume increased. The PSDs were skewed to the small pore sizes and the pore volumes decreased in the order of plain> twill> satin. As the number of fibers, the fiber diameter and the thread twist decreased, the intrayarn pore volumes were increased.

• 대한원격탐사학회지
• /
• 제18권3호
• /
• pp.155-162
• /
• 2002

Neural networks have been focused on as a robust classifier for the remotely sensed imagery due to its statistical independency and teaming ability. Also the artificial neural networks have been reported to be more tolerant to noise and missing data. However, unlike the conventional statistical classifiers which use the statistical parameters for the classification, a neural network classifier uses individual training sample in teaming stage. The training performance of a neural network is know to be very sensitive to the discrepancy of the number of the training samples of each class. In this paper, the effect of the population discrepancy of training samples of each class was analyzed with three layered feed forward network. And a method for reducing the effect was proposed and experimented with Landsat TM image. The results showed that the effect of the training sample size discrepancy should be carefully considered for faster and more accurate training of the network. Also, it was found that the proposed method which makes teaming rate as a function of the number of training samples in each class resulted in faster and more accurate training of the network.

• 산업경영시스템학회지
• /
• 제42권1호
• /
• pp.151-157
• /
• 2019

This study is about the process capability index (PCI). In this study, we introduce several indices including the index $C_{PR}$ and present the characteristics of the $C_{PR}$ as well as its validity. The difference between the other indices and the $C_{PR}$ is the way we use to estimate the standard deviation. Calculating the index, most indices use sample standard deviation while the index $C_{PR}$ uses range R. The sample standard deviation is generally a better estimator than the range R. But in the case of the panel process, the $C_{PR}$ has more consistency than the other indices at the point of non-conforming ratio which is an important term in quality control. The reason why the $C_{PR}$ using the range has better consistency is explained by introducing the concept of 'flatness ratio'. At least one million cells are present in one panel, so we can't inspect all of them. In estimating the PCI, it is necessary to consider the inspection cost together with the consistency. Even though we want smaller sample size at the point of inspection cost, the small sample size makes the PCI unreliable. There is 'trade off' between the inspection cost and the accuracy of the PCI. Therefore, we should obtain as large a sample size as possible under the allowed inspection cost. In order for $C_{PR}$ to be used throughout the industry, it is necessary to analyze the characteristics of the $C_{PR}$. Because the $C_{PR}$ is a kind of index including subgroup concept, the analysis should be done at the point of sample size of the subgroup. We present numerical analysis results of $C_{PR}$ by the data from the random number generating method. In this study, we also show the difference between the $C_{PR}$ using the range and the $C_P$ which is a representative index using the sample standard deviation. Regression analysis was used for the numerical analysis of the sample data. In addition, residual analysis and equal variance analysis was also conducted.

• Asian-Australasian Journal of Animal Sciences
• /
• 제19권12호
• /
• pp.1702-1705
• /
• 2006

A simulation study was conducted to evaluate a fine-mapping method exploiting population-wide linkage disequilibrium. Data were simulated according to the pedigree structure based on a large paternal half-sib family population with a total of 1,034 or 2,068 progeny. Twenty autosomes of 100 cM were generated with 5 cM or 1 cM marker intervals for all founder individuals in the pedigree, and marker alleles and a number of quantitative trait loci (QTL) explaining a total of 70% phenotypic variance were generated and randomly assigned across the whole chromosomes, assuming linkage equilibrium between the markers. The founder chromosomes were then descended through the pedigree to the current offspring generation, including recombinants that were generated by recombination between adjacent markers. Power to detect QTL was high for the QTL with at least moderate size, which was more pronounced with larger sample size and denser marker map. However, sample size contributed much more significantly to power to detect QTL than map density to the precise estimate of QTL position. No QTL was detected on the test chromosomes in which QTL was not assigned, which did not allow detection of false positive QTL. For the multiple QTL that were closely located, the estimates of the QTL positions were biased, except when the QTL were located on the right marker positions. Our fine mapping simulation results indicate that construction of dense maps and large sample size is needed to increase power to detect QTL and mapping precision for QTL position.