• 품질경영학회지
• /
• 제29권4호
• /
• pp.38-53
• /
• 2001

In resolving industrial quality control problems, a vector of multiple quality characteristic variables is involved rather than a single variable. However, it is not guaranteed that a multivariate control chart based on statistical methods can monitor abnormal signal in case that small changes of relationship between each variables causes abnormal production process. Hence a quality control system for real-time monitoring of the multi-dimensional quality characteristic vector under a multivariate normal process is needed to enhance tile production system quality performance. A pattern analysis approach based on self-organizing map (SOM), an unsupervised learning technique of neural network, is applied to the design of such a quality control system. In this study we present a new material quality control system based on pattern analysis approach and illustrate the effectiveness of proposed system using actual electronic company material data.

• 산업공학
• /
• 제24권1호
• /
• pp.8-14
• /
• 2011

Principal Component Analysis (PCA) reduces the dimensionality of the process by creating a new set of variables, Principal components (PCs), which attempt to reflect the true underlying process dimension. However, for highly nonlinear processes, this form of monitoring may not be efficient since the process dimensionality can't be represented by a small number of PCs. Examples include the process of semiconductors, pharmaceuticals and chemicals. Nonlinear correlated process variables can be reduced to a set of nonlinear principal components, through the application of Kernel Principal Component Analysis (KPCA). Support Vector Data Description (SVDD) which has roots in a supervised learning theory is a training algorithm based on structural risk minimization. Its control limit does not depend on the distribution, but adapts to the real data. So, in this paper proposes a non-linear process monitoring technique based on supervised learning methods and KPCA. Through simulated examples, it has been shown that the proposed monitoring chart is more effective than $T^2$ chart for nonlinear processes.

• 동아시아경상학회지
• /
• 제10권2호
• /
• pp.31-42
• /
• 2022

Purpose - The main research goals by macroeconomic analysis is to assess the effectiveness of state regulation, the sustainability of development, and the financial stability of the state. Research design, Data, and methodology - The research were analyzed using the methods of multivariate statistics and application of the software package Stat graphics. The volume of data from the 1995 to the 2021 was analyzed by Russian Federation. The scale of research on Belarus: to be analyzed the amount of data from the 2015 by 2021, on Kazakhstan - from the 19941, on Kyrgyzstan - from the 2002, on Tajikistan - from the 2008, on Armenia - from the 2021, on Japan - since the 1970, on China - since the 1950, on South Korea - since the 1953. Result - The methods of multivariate statistics was demonstrated exact of result in forecasting of macroeconomic indicators. The most of tendency with the accurate results of are described using the second-degree polynomials. In the most research of country there are the macroeconomic proportion are broken. Conclusion - In the countries studied, the monetary aggregates have a significant growth rate. The shares with a substantial monetary stock and the speed of its growth are divided in the two groups: having placements in the real sectors of the economy and not having received the same result of development from the growth of the monetary stock.

• 응용통계연구
• /
• 제22권1호
• /
• pp.129-140
• /
• 2009

In this paper, we consider simultaneous confidence intervals for the difference of proportions between two groups taken from multivariate binomial distributions in a nonparametric way. We briefly discuss the construction of simultaneous confidence intervals using the method of adjusting the p-values in multiple tests. The features of bootstrap simultaneous confidence intervals using non-pooled samples are presented. We also compute confidence intervals from the adjusted p-values of multiple tests in the Westfall (1985) style based on a pooled sample. The average coverage probabilities of the bootstrap simultaneous confidence intervals are compared with those of the Bonferroni simultaneous confidence intervals and the Sidak simultaneous confidence intervals. Finally, we give an example that shows how the proposed bootstrap simultaneous confidence intervals can be utilized through data analysis.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.407-410
• /
• 1996

This paper presents how to build a human sensibility database by multivariate method. And, we discribe a fuzzy based inference system which converts human sensibility data to design factors using the human sensibility database. We are able to obtain the values of multiple correlation coeffcient, partial correlation coefficient, and categories by the quantification theory which is multivariate analysis. So, the human sensibility database is constructed from those values. The inference system will be more useful, if the human sensibility database and graphic design factor database were integrated.

• Communications for Statistical Applications and Methods
• /
• 제18권1호
• /
• pp.13-21
• /
• 2011

본 논문에서는 계절성을 가지는 다변량 비정상 시계열자료의 분석 방법을 연구한다. 이를 위하여, 3가지의 다변량 시계열분석 모형(계절형 공적분 모형, 계절형 가변수를 가지는 비계절형 공적분 모형, 차분을 이용한 벡터자기회귀모형)을 고려하고, 한국의 실제 거시경제 자료를 이용하여 3가지 모형의 예측력을 비교한다. 공적분 모형은 단기적 예측에서 우수하였고, 장기적 예측에서는 차분을 이용한 벡터자기회귀모형이 우수하였다.

• 한국환경과학회지
• /
• 제16권3호
• /
• pp.369-376
• /
• 2007

This study was conducted to evaluate water quality in coastal sea of Kunsan using multivariate analysis. The analysis data in Coastal Sea of Kunsan use of surveyed data by the NFRDI from April 2000 to November 2002. Twelve water Quality parameter were determined on each sample. The results was summarized as follow ; Water quality in coastal sea of Kunsan could be explained up to 62.782% by four factors which were included in loading of nitrogen-nutrients by Keum river(24.688%), suspended solids variation (12.180%), seasonal climate variation (18.367%) and variation of DIP (10.546%). To analyze spatially and monthly variation by factor score, it was divided by inner area and outer area spatially, and spring and summer monthly. The result of time series analysis by factor score, inner area of Kunsan coastal sea(St.1 and St. 2) was the most affected by nitrogen-nutrient and suspended solids due to runoff by Keum river. It could be suggested from these results that it is important to reduce tile pollution loads from Kuem river for the control of the water quality in coastal sea of Kunsan.

• Journal of the Korean Data and Information Science Society
• /
• 제18권4호
• /
• pp.1135-1143
• /
• 2007

The singular value decomposition and the spectral decomposition are the useful methods in the area of matrix computation for multivariate techniques such as principal component analysis and multidimensional scaling. These techniques aim to find a simpler geometric structure for the data points. The singular value decomposition and the spectral decomposition are the methods being used in these techniques for this purpose. In this paper, the singular value decomposition and the spectral decomposition are compared.

• Communications for Statistical Applications and Methods
• /
• 제11권3호
• /
• pp.465-474
• /
• 2004

Data visualization is the automation process and the discovery process to data sets in an effort to discover underlying information from the data. It provides rich visual depictions of the data. It has distinct advantages over traditional data analysis techniques such as exploring the structure of large scale data set both in the sense of number of observations and the number of variables by allowing great interaction with the data and end-user. We discuss the principles of data visualization and evaluate the characteristics of various tools of visualization according to these principles.

• 한국소프트웨어감정평가학회 논문지
• /
• 제17권1호
• /
• pp.75-82
• /
• 2021

젖소에 있어 유방염은 농가의 낙농 생산성을 저해하는 주된 요인이며 이를 해결하기 위해 지난동안 폭넓은 연구가 이루어졌다. 하지만 유방염에 대한 연구는 사후 진단에 국한되어왔으며 이마저도 단일 센서를 활용하는 것이 주류이다. 본 연구에서는 생체 데이터와 환경 데이터를 이용하여 다음 날의 유방염 발병여부를 예측하는 모델을 개발하였다. 데이터는 충청남도 농가에 설치된 착유기와 센서들로부터 수집되었으며 3주간의 데이터를 다변량 데이터로 구성하였다. 유방염 진단예측을 위해 순환 신경망 모델을 사용하였고, 그 결과 유방염을 82.9%의 정확도로 예측하였다. 데이터 수집 기간을 다양하게 하여 예측 성능을 비교하였고 여러 모델과 성능을 비교하여 모델의 우수성을 확인하였다.