• 품질경영학회지
• /
• 제22권2호
• /
• pp.20-32
• /
• 1994

This paper is concerned with the design of four control charts for real-time monitoring of the continuous flow processes. Control charts for both uncorrelated data and correlated data are designed using the Kalman filtering techinque. The relative performance between the designed control charts and traditional control charts is evaluated in terms of the Average Run Length(ARL). Results show that the Adaptive EWMA control charts designed for uncorrelated data has better performance when process mean is shifted, while the residual control charts for correlated data has better performance when process is in control.

• 품질경영학회지
• /
• 제20권2호
• /
• pp.55-66
• /
• 1992

The sampling plan CSP-1 for continuous production was first proposed by Dodge in 1943. Continuous production refers to products which are flowing past the inspection station such as products moving on a conveyor belt. One important measure of the effectiveness of a CSP is the average outgoing quality(AOQ). A concept for a short run of production length time, denoted by AOQ(t), is provided. The assumption of a s-independence in CSP-1 is unrealistic. It is possible to relax the assumption of a s-independence. The need for Markov model in a continuous production process can be discussed in this paper. The Markov and renewal theory are used to describe the property of AOQ in CSP-1.

• 품질경영학회지
• /
• 제40권2호
• /
• pp.176-185
• /
• 2012

After a work of Derman and Ross(1997) that considered simple main runs rules and derived ARL (Average Run Length) using Markov chain modeling, $\bar{X}$ control chart based on diverse alternative main and supplementary runs rules that is the most popular control chart for monitoring the mean of a process are proposed. This paper reviews and discusses the-state-of-art researches for these runs rules and classifies according to several properties of runs rules. ARL derivation for a proposed runs rule is also illustrated.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 춘계 학술발표회 논문집
• /
• pp.197-201
• /
• 2005

In this article, we will compare the performance of the mean control chart, the median control chart, the transformed mean control chart, the transformed median control chart, and the precedence control chart by simulation study. For control charts with transformed data, Yeo-Johnson transformation is used. Under the in-control condition, ARL's in all control charts coincide with the designed ARL in the normal distribution, but in the other distributions, only the precedence control chart provides the in-control ARL as designed. Under the out-of-control condition, the mean control chart is preferred in the normal distribution and the median control chart is preferred in the heavy-tailed distribution and the precedence control chart outperforms in the short-tailed distribution.

• 산업경영시스템학회지
• /
• 제21권47호
• /
• pp.211-218
• /
• 1998

In start-up process control applications it may be necessary to limit the sample size to one measurement. A control chart for individual measurements is used whenever it is desirable to examine each individual value from the process immediately. A possible option would be to use an exponential weighted moving(EWM), using modifying statistics with individual measurement, chart for monitoring the process center, and using a moving range (MR) chart for monitoring process variability. In this paper it is shown that there is scheme in using the EWM procedure based on average run length. An expression for the ARL is given in terms of an integral equation, approximated using numerical quadrature. In this case, where it is reasonable to assume normality and negligible autocorrelation in the observations, provide graphs that simplify the design of EWM-MR chart and taking method of exponential smoothing constant(λ) and constant(K) are suggested. The charts suggested above evaluate using the conditional probability.

• Journal of the Korean Data and Information Science Society
• /
• 제28권4호
• /
• pp.937-945
• /
• 2017

The purpose of using a control chart is to detect any change that occurs in the process. When control charts are used to monitor processes, we want to identify this changes as quickly as possible. Many problems in quality control involve a vector of observations of several characteristics rather than a single characteristic. Multivariate CUSUM or EWMA charts have been developed to address the problem of monitoring covariance matrix or the joint monitoring of mean vector and covariance matrix. However, control charts tend to work poorly when we use the highly correlatted variables. In order to overcome it, Hawkins (1991) proposed the use of regression adjustment variables. In this paper, to monitor covariance matrix, we investigate the performance of MEWMA-type control charts with and without the use of regression adjusted variables.

• 대한산업공학회지
• /
• 제31권1호
• /
• pp.87-98
• /
• 2005

This research investigates economic-statistical characteristics of variable sampling size and interval (VSSI)$\bar{X}$charts under two assignable causes. A Markov chain approach is employed in order to calculate average run length (ARL) and average time to signal (ATS). Six transient states are derived by carefully defining the state. A steady state cost rate function is constructed based on Lorenzen and Vance(1986) model. The cost rate function is optimized with respect to six design parameters for designing the VSSI $\bar{X}$ charts. Computational experiments show that the VSSI $\bar{X}$ chart is superior to the Shewhart $\bar{X}$ chart in the economic-statistical sense, even under two assignable causes. A comparative study shows that the cost rate may increase up to almost 30% by overlooking the second cause. Critical input parameters are also derived from a sensitivity study and a few guideline graphs are provided for determining the design parameters.

• 한국병원경영학회지
• /
• 제9권2호
• /
• pp.102-127
• /
• 2004

The objective of this study is to analyze a current trend of and relating factors on profitability of the Korean Public Corporation Medical Centers(KPCMCs, hereinafter, hospitals) in Korea. There are 34 hospitals in Korea as of 2004. Among these hospitals some are red ink hospitals, others are black inks in terms of profitability. Data were collected by Korea Health Industry Development Institute(KHIDI) Statistics for Hospital Management 2000-2002 and Ministry of Health and Welfare(MOHW) financial data of public hospitals which was planned to coordinate public health care services roadmap in the long run. The samples are 32 hospitals. Profitability was measured in the aspect of profit rate with normal profit to total assets, and normal profit to gross revenues as dependent variables in respective. Independent variables were classified by general factors, i.e., location, intern/resident training, period of opening, number of beds, and managerial factors(current ratio, fixed ratio, liability to total assets, total assets turnover, personnel costs, materials cost, administrative cost), and finally factors related to patient treatment(average length of stay, bed occupancy rate, admission ratio of outpatients). The methods of analysis are correlation and multiple regression analysis. This study shows firstly, a lot of hospitals are optimal current ratio. Hospitals in upper 100% current ratio are 81.2%. And the personnel cost in total costs are high. Secondly, the trend of normal profit to gross revenues of hospitals are deteriorating gradually. And lastly, as a result of multiple regression analysis, the factors had on significant effect on normal profit to total assets are fixed ratio(+), liability to total assets(-), bed occupancy rate(+), admissions of outpatients(+), etc. And the factors had on significant effect on normal profit to gross revenues are current ration(+), fixed ratio(+), personnel cost(-), administrative expenses(-), admissions of outpatients(+), etc. In conclusion, to improve the profitability of hospitals, the efforts to reduce personnel cost and average length of stay might be needed. And also beds utilization rate need to be increased.

• Journal of the Korean Data and Information Science Society
• /
• 제28권5호
• /
• pp.981-999
• /
• 2017

단순확률모형을 고려하는 표준관리도에서는 표본간 분산을 고려하지 않고 공정분산을 추정한다. 표본간 분산이 존재하는 경우에는, 공정분산이 과소추정된다. 공정분산이 과소추정되면 좁아진 관리한계로 인해 관리도의 민감도는 향상되지만 과도한 오경보율을 발생시킨다. 이 논문에서는 공정모형으로 분산성분모형, 즉 변동의 원인을 표본내 분산과 표본간 분산으로 구분하는 확률모형을 고려한다. 관리한계는 표본내 분산과 표본간 분산을 모두 사용하여 설정하고 그에 따른 평균런길이를 통하여 효율을 살펴 보았다. 관리형태는 가장 널리 사용되는 ${\bar{X}}$, EWMA, CUSUM 관리도를 고려하였다. 관리한계 설정에서 표본내 분산만을 사용한 경우 (Case I)와 표본간 분산도 함께 사용한 경우 (Case II)를 통해 관리도의 효율을 비교하였다. 또한, 공정 모수가 주어진 경우와 추정된 두 경우에 대해서도 관리도의 효율을 비교하였다. 그 결과, 표본간 분산이 증가할 때 Case I의 오경보율은 급격히 증가한 반면 Case II의 경우에는 동일하게 유지됨을 알 수 있었다.

• 한국통신학회논문지
• /
• 제13권5호
• /
• pp.390-399
• /
• 1988

계산 과장이 비교적 간단하고 실시간 처리가 가능한 coding방법 중의 하나인 BTC(Block Truncation Coding)를 이용하여 영상 데이터를 압축하기 위하여 2진 영상에서 주로 사용하는 quar tree 개념을 도입하여 압축율을 개선시키고, 기존의 BTC와 그 성능을 비교하였다. 이 논문에서 제안하는 방법은 그레이 레벨의 변화가 적은 영역에서는 부화상의 크기를 크게 하고, 그레이 레벨의 변화가 큰 영역에서는 부화상의 크기를 작게 하여 전체 부화상의 갯수를 줄임으\ulcorner\ulcorner영상 데이타의 압축을 행하였다. 또한 비트 평면의 효율적인 전송을 위하여 큰 크기의 부화상에 있어서는 Huffman run-length code를, 작은 크기의 부화상에 있어서는 lookup rable방식을 이용하였다. 컴퓨터 시뮬레이션 결과, 크기가 256x256이고, 그레이 레벨이 256인 영상에서 평균 0.8bit/pel의 압축 효과를 얻었다.