• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3779-3784
• /
• 2012

Real-time process monitoring and diagnosis of industrial processes is one of important operational tasks for quality and safety reasons. The objective of fault diagnosis or identification is to find process variables responsible for causing a specific fault in the process. This helps process operators to investigate root causes more effectively. This work assesses the applicability of combining a nonlinear statistical technique of kernel Fisher discriminant analysis with a preprocessing method as a tool of on-line fault identification. To compare its performance to existing linear principal component analysis (PCA) identification scheme, a case study on a benchmark process was performed to show that the fault identification scheme produced more reliable diagnosis results than linear method.

• Journal of Applied Biological Chemistry
• /
• v.64 no.2
• /
• pp.127-131
• /
• 2021

Perilla frutescens var. crispa (Pfc), a herb belonging to the mint family (Lamiaceae), has been used for medicinal and aromatic purposes. In the present study, we analyzed the variation in the chemical composition of essential oils (EOs) obtained from five different genotypes of Pfc collected from different regions. Based on principal component analysis (PCA) and hierarchical cluster analysis (HCA), we identified three groups: PA type containing perillaldehyde, PP type containing dillapiole, and 2-acetylfuran type. To assess the correlation between EO components and antimicrobial activities, we compared classification results generated by PCA and HCA based on antimicrobial activity values. The findings suggested that the major compounds obtained from EOs of Pfc are responsible for their antimicrobial activities. Chemotypes of Pfc plants are essentially qualitative traits that are important for breeders. The present findings provide potential information for breeding Pfc as an antimicrobial agent.

• Journal of the Korean Society of Safety
• /
• v.38 no.4
• /
• pp.15-22
• /
• 2023

LPG-related accidents, which account for half of all gas accidents in Korea, have not shown any sign of decrease over the past decade, partially owing to the lack of effective safety improvement measures. The purpose of this study was to identify the effectiveness of improvement measures by analyzing the traits of accidents in terms of human factors, and to seek more effective accident prevention strategies. In this study, 108 accident cases were collected and analyzed in the aspect of accident characteristics such as violation type, human factors, and so on. The results showed that the work procedures of suppliers and engineers related to LPG accidents seemed to be similar in outward appearance; however, specific accident causes and unsafe behaviors were different. Particularly, type and target of violations were different, which could be visually confirmed by the Principal Component Analysis (PCA) and the Quantification Techniques (QT). Furthermore, for engineers, insufficient supervision was a major influencing factor. In conclusion, because the accident characteristics of suppliers and engineers are different, differentiated accident prevention strategies should be implemented, which was discussed in this study.

• Asia-Pacific Journal of Business
• /
• v.15 no.2
• /
• pp.71-88
• /
• 2024

Purpose - This study provides an overview of existing research and practices related to market risk premiums(MRP), and empirically estimates the MRP in Korea, particularly using the related option prices. We also seek to improve the current MRP practices and explore alternative solutions. Design/methodology/approach - We present the option price-based MRP estimation method, as proposed by Martin (2017), and implement it within the context of the Korean stock market. We then juxtapose these results with those derived from other methods, and compare the characteristics with those of the United States. Findings - We found that the lower limit of the MRP in the Korean stock market shows a much lower value compared to the US. There seems to be the possibility of a market crash, exchange rate volatility, or a lack of option trading data. We investigated the predictive power of the estimated values and discovered that the weighted average of the results of various methodologies using the Principal Component Analysis (PCA) is superior to the individual method's results. Research implications or Originality - It is required to explore various methods of estimating MRP that are suitable for the Korean stock market. In order to improve the estimation methodology based on option prices, it is necessary to develop the methods using the higher-order(third order or above) moments, or consider additional risk factors such as the possibility of a crash.

• Bulletin of the Korean Chemical Society
• /
• v.7 no.1
• /
• pp.73-77
• /
• 1986

Data on the concentration of Na, K, Sc, Cr, Fe, Co, Cu, Ga, Rb, Cs, Ba, La, Ce, Sm, Eu, Tb, Lu, Hf, Ta, and Th obtained by neutron activation analysis have been used to characterize Korean porcelainsherds by multivariate analysis. The mathematical approach employed is principal component analysis (PCA). PCA was found to be helpful for dimensionality reduction and for obtaining information regarding (a) the number of independent causal variables required to account for the variability in the overall data set, (b) the extent to which a given variable contributes to a component and (c) the number of causal variables required to explain the total variability of each measured variable.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.1
• /
• pp.151-159
• /
• 2012

This paper proposes to develop multi-currencies portfolio strategy using principal component analysis (PCA) and logistic regression (LR) in foreign exchange market. While there is a great deal of literature about the analysis of exchange market, there is relatively little work on developing trading strategies in foreign exchange markets. There are two objectives in this paper. The first objective is to suggest portfolio allocation method by applying PCA. The other objective is to determine market timing which is the strategy of making buy or sell decision using LR. The results of this study show that proposed model is useful trading strategy in foreign exchange market and can be desirable solution which gives lots of investors an important investment information.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.3
• /
• pp.751-759
• /
• 2008

Mixtures of factor analyzers(MFA) is useful to model the distribution of high-dimensional data on much lower dimensional space where the number of observations is very large relative to their dimension. Mixtures of common factor analyzers(MCFA) can reduce further the number of parameters in the specification of the component covariance matrices as the number of classes is not small. Moreover, the factor scores of MCFA can be displayed in low-dimensional space to distinguish the groups. We propose the factor scores of MCFA as new low-dimensional features for classification of high-dimensional data. Compared with the conventional dimension reduction methods such as principal component analysis(PCA) and canonical covariates(CV), the proposed factor score was shown to have higher correct classification rates for three real data sets when it was used in parametric and nonparametric classifiers.

• Journal of IKEEE
• /
• v.6 no.1 s.10
• /
• pp.72-79
• /
• 2002

This paper presents an efficient face detection algorithm for color images with a complex background. The presented algorithm utilizes the color information and eigenface that is calculated by PCA-LDA (Principle Component Analysis - Linear Discriminant Analysis). The method of using the color information is faster than any other methods. Eigenface includes average information of the whole test faces. Therefore eigenface can decide that the candidate region is a face. The whole process is composed of two steps. First, it finds first face candidates region of skin tone using a color information in image. We can get a size and position of face candidate region. Second, we compare first face candidate region with eigenface, so decide that an image whether include a face or not. The advantages of the proposed approach include that increasing the detection speed by deciding a size and position of first face candidates region. Also, Betting 97% of the detection rate by comparing the eigenfaces calculated in PCA-LDA.

• Annual Conference of KIPS
• /
• 2003.11a
• /
• pp.555-558
• /
• 2003

본 논문은 PCA(Principal Component Analysis)와 LDA(Linear Discriminant Analysis)를 적용하여 입력된 사용자 얼굴 사진과 가장 유사한 아바타를 자동으로 생성하기 위한 방법을 제안한다. 입력된 사진으로부터 알려진 영상처리 기법들을 이용하여 얼굴 영역을 추출하고, 추출된 얼굴로부터 얼굴 구성요소(눈썹,눈,코,입)를 추출한다. 추출된 얼굴 구성요소와 미리 분류하여 구축한 실제 얼굴 사진에서의 얼굴 구성요소 라이브러리를 PCA와 LDA를 적용하여 유사도를 계산한다. 최종적으로 계산된 유사도 값이 가장 큰 영상의 대표 아바타가 결과영상으로 나오게 된다. 실험결과 기존의 아바타 추출방법에서 드러난 입력영상과 2진화된 아바타 영상과의 속성 차이로 인한 문제점을 보안하고 좀 더 정확하고 자동화된 방법으로 아바타를 추출 할 수 있다는 것을 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.718-720
• /
• 2004

얼굴 인증에서 가장 보편적으로 사용되고 있는 주성분 분석(PCA . Principal Component Analysis)은 정면 얼굴과 같은 특징 패턴에 대해서 비교적 높은 성능을 보인다. 인식률을 떨어뜨리지 않으면서 데이터량을 줄일 수 있는 효과가 있어 클래스를 잘 축약하여 표현하기에 유용하다. 하지만 조명이나 표정의 변화에 대해서는 성능을 보장할 수 없다 이를 보완하기 위해 성분이 다른 클래스간의 분리가 수월하도록 선형판별분석(LDA Linear Discriminant Analysis)을 사용한다 LDA는 데이터의 양이 적을 때는 성능이 떨어지는 단점이 있다 그래서 PCA와 LDA를 융합한 기술을 사용하면 더 나은 성능을 얻을 수 있는데 Min, Max, Mean, Append, Majority voting방법 등이 이에 해당된다. 하지만 기존 연구에서는 제한적 데이터베이스에 대한 실험에 그쳐 실험 결과의 객관성이 부족했다. 본 논문에서는 정형화된 환경에서 여러 가지 데이터베이스를 사용해 실험함으로써 Min, Max, Mean 융합 알고리즘의 성능을 비교 분석한다. 융합 알고리즘이 언제나 좋은 성능을 내는 것은 아니지만 얼굴영상에서 조명이나 표정 등이 변화함에 상관없이 일정 수준의 인증율을 보장하고 있다.