• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.1
• /
• pp.31-40
• /
• 2022

Six Sigma is a philosophy and systematic methodology for quality improvement. It encourages continuous quality improvement efforts to achieve the ideal goal of 6σ. Sigma(σ) is a statistic representing the standard deviation of the normal distribution, and 6σ level means a level where the tolerance of the specification is six times the standard deviation of the process distribution. In terms of the defective rate, the 6σ level achieves the 0.002 defectives per one million units. However, in the field, the 6σ level is used in the sense of achieving 3.4 defects per one million opportunities, which shows a large gap from the 6σ level in the statistical viewpoint. This is because field practitioners accept a 1.5σ shift of the mean of process when calculating the defective rate under sigma level. It said that the acceptance of 1.5σ shift of the mean is from experience, but there is no research or theoretical explanation to support it logically. Although it is a non-scientific explanation based on experience, considering that there has been no objection to the 1.5σ shift for a long time and it is rather accepted, it is judged that there is a reasonable basis for the 1.5σ shift. Therefore, this study tries to find a reasonable explanation through detective power of control chart via the run-rules to the 1.5σ shift empirically recognized by practitioners.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.247-250
• /
• 2006

Maximizing the productivity in reactive ion etching, early detection of process equipment anomaly became crucial in current high volume semiconductor manufacturing environment. To address the importance of the process fault detection for productivity, support vector machines (SVMs) is employed to assist the decision to determine process faults in real-time. SVMs for eleven steps of etching runs are established with data acquired from baseline runs, and they are further verified with the data from controlled (acceptable) and perturbed (unacceptable) runs. Then, each SVM is further utilized for the fault detection purpose utilizing control limits which is well understood in statistical process control chart. Utilizing SVMs, fault detection of reactive ion etching process is demonstrated with zero false alarm rate of the controlled runs on a run to run basis.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.3
• /
• pp.52-61
• /
• 2012

The design method for cumulative sum (CUSUM) control charts, which can be robust to autoregressive moving average (ARMA) modeling errors, has not been frequently proposed so far. This is because the CUSUM statistic involves a maximum function, which is intractable in mathematical derivations, and thus any modification on the statistic can not be favorably made. We propose residual-based robust CUSUM control charts for monitoring autocorrelated processes. In order to incorporate the effects of ARMA modeling errors into the design method, we modify parameters (reference value and decision interval) of CUSUM control charts using the approximate expected variance of residuals generated in model uncertainty, rather than directly modify the form of the CUSUM statistic. The expected variance of residuals is derived using a second-order Taylor approximation and the general form is represented using the order of ARMA models with the sample size for ARMA modeling. Based on the Monte carlo simulation, we demonstrate that the proposed method can be effectively used for statistical process control (SPC) charts, which are robust to ARMA modeling errors.

• Journal of Pharmacopuncture
• /
• v.8 no.2
• /
• pp.11-16
• /
• 2005

Objective : The aim of the study was to investigate the therapeutic effect of BVA in the treatment of patients with acute ankle sprain. Design : A prospective randomized double-blind study of BVA was conducted. Setting : The study was done in the Kyungwon University Seoul Hospital from August 1st, 2004 to June 15th, 2005. Patients : 30 patients diagnosed with acute ankle sprain, especially 2nd degree on the Ankle grade pain chart(AGPC) participated in the study, who were divided into two groups (A and B) randomly by a coordinator flipping a coin. Group A and B were relevant to control and BVA group respectively, of which a coordinator never informed any other participant involved. Eventually 13 of 17 in group A and 11 of 13 in Group B finished all the process of the clinical trial. Intervention : In both group A and B, The Procedure of acupuncture treatment was made similar by appearance that four acupoints such as 坵墟(GB40), 中封(LR4), 商丘(SP5), 解谿(ST41) of the injured side were selected and Normal saline aqua-acupuncture(control, as a placebo) or BVA was done and then acupuncture at 坵墟(GB40), 中封(LR4), 商丘(SP5), 解谿(ST41), 足三里(ST36), 陽陵泉(G34) of the affected side was given again. the needles were retained for 20 minutes under the infrared rays. The treatment was given daily for a week. Outcome Measures : Ankle-Hindfoot Scale (AHS) and Visual Analogue Scale(VAS) were followed by three treatments. Statistical Analysis : Analysis regarding variations in AHS and VAS is carried out by applying Mann-Whitney test and Wilcoxon signed rank test sign test with level of significance at 5%. Results : At the end of the treatment, there was significant statistical differences between the two groups in VAS and AHS as well, while at the 3rd day only a VAS showed statistical significance. In each group, both VAS and AHS showed statistical significance along with duration of treatment. Conclusions : BVA was thought to be effective alternatives for relieving symptoms of acute ankle sprain, although further study was needed on the large scale.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.191-207
• /
• 2024

Many studies have been conducted to quickly detect out-of-control situations in autocorrelated processes. The most traditionally used method is a residual control chart, which uses residuals calculated from a fitted time series model. However, many procedures for monitoring autocorrelated processes using statistical learning methods have recently been proposed. In this paper, we propose a monitoring procedure using the latent vector of LSTM Autoencoder, a deep learning-based unsupervised learning method. We compare the performance of this procedure with the LSTM Autoencoder procedure based on the reconstruction error, the RNN classification procedure, and the residual charting procedure through simulation studies. Simulation results show that the performance of the proposed procedure and the RNN classification procedure are similar, but the proposed procedure has the advantage of being useful in processes where sufficient out-of-control data cannot be obtained, because it does not require out-of-control data for training.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.6
• /
• pp.487-496
• /
• 2021

The analysis method of the microbiome has been evolving for a very long time, and the industrial field has grown rapidly with the start of human genome analysis 20 years ago. As continuous research continues, related industries have grown together, and among them, Illumina of the US has been leading the popularization of DNA analysis by developing innovative equipment and analysis methods since its establishment in 1998. In this paper, 'AiB Index', 'AiB Chart' using statistical process control and log-scale technique to analyze the gut microbiome analysis methodology and implement an algorithm that can analyze minute changes in the minor strains that can be overlooked in the existing analysis methods. want to implement. From the data analysis point of view, we proposed a platform for analyzing gut microbes that can collect fecal data, match and process gut microbes, and store and visualize the results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.962-969
• /
• 2006

To address the importance of the process fault detection for productivity, support vector machines (SVMs) is employed to assist the decision to determine process faults in real-time. The reactive ion etching (RIE) tool data acquired from a production line consist of 59 variables, and each of them consists of 10 data points per second. Principal component analysis (PCA) is first performed to accommodate for real-time data processing by reducing the dimensionality or the data. SVMs for eleven steps or etching m are established with data acquired from baseline runs, and they are further verified with the data from controlled (acceptable) and perturbed (unacceptable) runs. Then, each SVM is further utilized for the fault detection purpose utilizing control limits which is well understood in statistical process control chart. Utilizing SVMs, fault detection of reactive ion etching process is demonstrated with zero false alarm rate of the controlled runs on a run to run basis.

• Journal of Environmental Health Sciences
• /
• v.50 no.2
• /
• pp.125-137
• /
• 2024

Background: The Korea Risk Information Surveillance System (K-RISS) was developed to enable the early detection of food and drug safety-related issues. Its goal is to deliver real-time risk indicators generated from ongoing food and drug risk monitoring. However, the existing K-RISS system suffers under several limitations. Objectives: This study aims to augment K-RISS with more detailed indicators and establish a severity standard that takes into account structural changes in the daily time series of K-RISS values. Methods: First, a Delphi survey was conducted to derive the required weights. Second, a control chart, commonly used in statistical process controls, was utilized to detect outliers and establish caution, attention, and serious levels for K-RISS values. Furthermore, Bai and Perron's method was employed to determine structural changes in K-RISS time series. Results: The study incorporated 'closeness to life' and 'sustainability' indicators into K-RISS. It obtained the necessary weights through a survey of experts for integrating variables, combining indicators by data source, and aggregating sub K-RISS values. We defined caution, attention, and serious levels for both average and maximum values of daily K-RISS. Furthermore, when structural changes were detected, leading to significant variations in daily K-RISS values according to different periods, the study systematically verified these changes and derived respective severity levels for each period. Conclusions: This study enhances the existing K-RISS system and introduces more advanced indicators. K-RISS is now more comprehensively equipped to serve as a risk warning index. The study has paved the way for an objective determination of whether the food safety risk index surpasses predefined thresholds through the application of severity levels.