• Communications for Statistical Applications and Methods
• /
• 제9권2호
• /
• pp.491-503
• /
• 2002

In this paper, we propose a automatic document summarization method based on Principal Component Analysis(PCA) which is one of the multivariate statistical methods. After extracting thematic words using PCA, we select the statements containing the respective extracted thematic words, and make the document summary with them. Experimental results using newspaper articles show that the proposed method is superior to the method using either word frequency or information retrieval thesaurus.

• 산업경영시스템학회지
• /
• 제3권3호
• /
• pp.23-34
• /
• 1980

The method of principal component analysis is originated by K. Pearson, who considered this as geometrical method Principal component analysis is the most elementary method, and this means that the information having various type of characteristics which have been correlated among themselves, are summarized by orthogonal transformations of characteristics. I: Even though we have different result whether this method is applied to homogeneous population or not. In this research we should deal with the case of homogeneous population only. II: On the other hand, we can have different result whether we start from covariance matrix or matrix of correlation- coefficients. In this research we are studying based on covariance matrix.

• 한국안전학회지
• /
• 제29권4호
• /
• pp.73-77
• /
• 2014

In the field of fault diagnosis, the deviations from normal operating conditions are monitored to identify the type of faults and find their root causes. One of the most representative methods is the statistical approaches, due to a large amount of advantages. However, ambiguous diagnosis results can be generated according to fault magnitudes, even if the same fault occurs. To tackle this issue, this work proposes principal component analysis (PCA) based method with qualitative information. The PCA model is constructed under normal operation data and the residuals from faulty conditions are calculated. The significant changes of these residuals are recorded to make the information for identifying the types of fault. This model can be employed easily and the tasks for building are smaller than these of other common approaches. The efficacy of the proposed model is illustrated in Tennessee Eastman process.

• Nuclear Engineering and Technology
• /
• 제32권5호
• /
• pp.485-494
• /
• 2000

In this work, a fuzzy neural network is used to estimate the relevant sensor signal using other sensor signals. Noise components in input signals into the fuzzy neural network are removed through the wavelet denoising technique . Principal component analysis (PCA) is used to reduce the dimension of an input space without losing a significant amount of information. A lower dimensional input space will also usually reduce the time necessary to train a fuzzy-neural network. Also, the principal component analysis makes easy the selection of the input signals into the fuzzy neural network. The fuzzy neural network parameters are optimized by two learning methods. A genetic algorithm is used to optimize the antecedent parameters of the fuzzy neural network and a least-squares algorithm is used to solve the consequent parameters. The proposed algorithm was verified through the application to the pressurizer water level and the hot-leg flowrate measurements in pressurized water reactors.

• 대한인간공학회지
• /
• 제2권1호
• /
• pp.3-11
• /
• 1983

Anthropometric data is most basic materials in the all studies related with it. Therefore, in anthropometric data, not only consideration of the state of variance, but more various analysis is needed. This study selected the 13 parts that properly show a whole characteristics of human body and, anthropometric data were obtained through the actual measurements for male and female workers who were engaged in production factory. And, to interpret anthropometric data, principal component analysis of multivariate analysis methods was applied.

• 정보처리학회논문지B
• /
• 제13B권3호
• /
• pp.329-336
• /
• 2006

문서를 구성하는 단어들은 서로 연관이 있다는 정보를 충분히 이용할 수 있는 다변량 분석 방법 중, 주성분분석(Principal Component Analysis)을 이용하여 중요 용어를 추출하고자 한다. 본 논문에서는 주성분분석의 분석 대상을 용어 사이의 공분산행렬이 아닌 상관행렬을 이용한다. 그리고, 중요 용어를 추출하기 위해서, 보유해야 할 주성분 개수와 주성분과 용어 사이의 상관계수에 대한 최적의 임계치를 찾고자 한다. 283건의 신문기사를 대상으로, 추출된 용어에 기반한 문장 추출 실험 결과, 첫 6개까지의 주성분과 상관계수 |0.4|라는 조건에서 가장 좋은 성능을 보였다.

• 비파괴검사학회지
• /
• 제24권6호
• /
• pp.590-596
• /
• 2004

신경망 기반의 신호 분류 시스템은 비파괴 검사 시 추출되는 많은 양의 데이터를 처리하기 위한 방법으로 꾸준히 이용되고 있다. 비파괴검사 방법 중, 초음파 탐상법은 용접 지역에서 결함들을 찾기 위하여 비파괴 검사에서 일반적으로 사용되고 있는 추세다. 초음파 탐상법의 중요한 특징은 특정 신호에서 발생하는 불연속성을 판별해내는 능력이다. 지금까지의 보편화되어 있는 기술은 신호를 분류하기 위해 각각의 A-scan 신호를 처리하는 반면 본 논문에서는 이웃하는 A-scan 신호의 정보를 기반으로 하는 2차원 푸리에 변환(Fourier transform)과 주성분 분석(principal component analysis) 기법을 이용하여 특징 벡터를 추출, 분류하는 방법을 제시하고자 한다.

• 한국빅데이터학회지
• /
• 제5권2호
• /
• pp.135-143
• /
• 2020

본 논문은 농식품 소비자패널 데이터에서 소비자의 유형을 나눌 때에 변수간 연관성이 많은 장바구니 분석에서 전처리 방법과 차원축소의 방법을 제안한다. 군집분석은 다변량 자료에서 관측 개체를 몇 개의 군집으로 나눌 때 널리 사용되는 분석기법이다. 하지만 여러 개의 변수가 연관성을 가진 경우에는 차원축소를 통한 군집분석이 더 효과적일 수 있다. 본 논문은 1,987 가구를 대상으로 조사한 식품소비 데이터를 K-means 방법을 사용하여 군집화하였으며, 군집을 나누기 위해 17개의 변수를 선정하였고, 17개의 다중공선성 문제와 군집을 나누기 위한 차원축소의 방법 중 주성분 분석과 요인분석을 비교하였다. 본 연구에서는 주성분분석과 요인분석 모두 2개의 차원으로 축소하였으며 주성분분석에서는 3개의 군집으로 나뉘었지만 분석하고자 하였던 소비 패턴에 대한 군집의 특성이 잘 나타나지 않았으며 요인분석에서는 분석가가 보고자 하는 소비 패턴의 특징이 잘 나타났다.

• Communications for Statistical Applications and Methods
• /
• 제24권2호
• /
• pp.143-154
• /
• 2017

A variable selection method based on probabilistic principal component analysis (PCA) using penalized likelihood method is proposed. The proposed method is a two-step variable reduction method. The first step is based on the probabilistic principal component idea to identify principle components. The penalty function is used to identify important variables in each component. We then build a model on the original data space instead of building on the rotated data space through latent variables (principal components) because the proposed method achieves the goal of dimension reduction through identifying important observed variables. Consequently, the proposed method is of more practical use. The proposed estimators perform as the oracle procedure and are root-n consistent with a proper choice of regularization parameters. The proposed method can be successfully applied to high-dimensional PCA problems with a relatively large portion of irrelevant variables included in the data set. It is straightforward to extend our likelihood method in handling problems with missing observations using EM algorithms. Further, it could be effectively applied in cases where some data vectors exhibit one or more missing values at random.

• 대한가정학회지
• /
• 제36권12호
• /
• pp.43-54
• /
• 1998

From the viewpoint of clothing construction, it is necessary to grasp exactly the shapes of the neck and the shouder, such as the line of the neck base, the neck gradient, the shoulder gradient, the shape of the scapular, and the shape of the breast. In this report, factor analysis was applied to 39 items of neck & shoulder level measurements, including stature, weight, but grith, waist girth, to demonstrate the most relevant measurements for collar and bodice pattern designing, and to classify the neck and shoulder level shapes. The subjects investigated were 126 women of the age 20-29. The main results are follows : 1. For factors of body form were extracted by the factor analysis. The 1st principal component can be interpreted as "size" component, the 2nd-3th principal component is "shape" component relating to neck and shoulder level, and the 4th principal component is "shoulder shape" component. 2. With regard to factor loadings, we were able to extract the most relevant measurements for collar and bodice pattern designing. M16, M22, S26, S30, S34, S35, S36, C37, C38, C39.