• Journal of the Korean Data and Information Science Society
• /
• 제23권1호
• /
• pp.199-207
• /
• 2012

Recently, variable selection methods using penalized likelihood with a shrink penalty function have been widely studied in various statistical models including generalized linear models and survival models. In particular, they select important variables and estimate coefficients of covariates simultaneously. In this paper, we develop a penalize h-likelihood method for variable selection in gamma frailty models. For this we use the smoothly clipped absolute deviation (SCAD) penalty function, which satisfies a good property in variable selection. The proposed method is illustrated using simulation study and a practical data set.

• 한국지능시스템학회논문지
• /
• 제24권6호
• /
• pp.646-650
• /
• 2014

본 논문에서는 다차원 문제로 인하여 발생하는 패턴 분류 성능의 저하를 방지 하여 퍼지 패턴 분류기의 성능을 개선하기 위하여 다수의 Feature들 중에서 패턴 분류 성능 향상에 기여하는 Feature를 선택하기 위한 새로운 Feature Selection 방법을 제안 한다. 새로운 Feature Selection 방법은 각각의 Feature 들을 퍼지 클러스터링 기법을 이용하여 클러스터링 한 후 각 클러스터가 임의의 class에 속하는 정도를 계산하고 얻어진 값을 이용하여 해당 feature 가 fuzzy pattern classifier에 적용될 경우 패턴 분류 성능 개선 가능성을 평가한다. 평가된 성능 개선 가능성을 기반으로 이미 정해진 개수만큼의 Feature를 선택하는 Feature Selection을 수행한다. 본 논문에서는 제안된 방법의 성능을 평가, 비교하기 위하여 다수의 머신 러닝 데이터 집합에 적용한다.

• Journal of the Korean Statistical Society
• /
• 제22권2호
• /
• pp.325-337
• /
• 1993

This paper propose two test statistics which enable us to proceed the variable selection in Fisher's linear discriminant function for the case of heterogeneous discrimination with equal training sample size. Simultaneous confidence intervals associated with the test are also given. These are exact and approximate results. The latter is based upon an approximation of a linear sum of Wishart distributions with unequal scale matrices. Using simulated sampling experiments, powers of the two tests have been tabulated, and power comparisons have been made between them.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 춘계 학술발표회 논문집
• /
• pp.151-156
• /
• 2003

Variable selection algorithm for principal component analysis using penalized likelihood method is proposed. We will adopt a probabilistic principal component idea to utilize likelihood function for the problem and use HARD penalty function to force coefficients of any irrelevant variables for each component to zero. Consistency and sparsity of coefficient estimates will be provided with results of small simulated and illustrative real examples.

• 한국도서관정보학회지
• /
• 제30권4호
• /
• pp.1-26
• /
• 1999

This study purposes to identify how the 'selection' of library materials shold be changed in the electronic environment to improve library services fundamentally. The study scrutinized the essence of selection, the relationship between selection and collection management, and the results of various studies to define the selection. The study implies: 1) the selection must be changed to the function providing users with assessment information of library materials, which helps the users access to entire scholarly information. 2) the assessment information could be input from different libraries and used by all users connected to the library network.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.349-352
• /
• 2004

In this literature, the selection of data set among the universe set is carried out with the fuzzy entropy function. By the definition of fuzzy entropy, we have proposed the fuzzy entropy function and the proposed fuzzy entropy function is proved through the definition. The proposed fuzzy entropy function calculate the certainty or uncertainty value of data set, hence we can choose the data set that satisfying certain bound or reference. Therefore the reliable data set can be obtained by the proposed fuzzy entropy function. With the simple example we verify that the proposed fuzzy entropy function select reliable data set.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.655-659
• /
• 2004

In this literature, the selection of data set among the universe set is carried out with the fuzzy entropy function. By the definition of fuzzy entropy, the fuzzy entropy function is proposed and the proposed fuzzy entropy function is proved through the definition. The proposed fuzzy entropy function calculate the certainty or uncertainty value of data set, hence we can choose the data set that satisfying certain bound or reference. Therefore the reliable data set can be obtained by the proposed fuzzy entropy function. With the simple example we verify that the proposed fuzzy entropy function select reliable data set.

• ETRI Journal
• /
• 제30권3호
• /
• pp.355-364
• /
• 2008

Multiple-input multiple-output (MIMO) systems can provide significant increments in capacity; however, the capacity of MIMO systems degrades severely when spatial correlation among multipath channels is present. This paper demonstrates that the influence of shadowing on the channel capacity is more substantial than that of multipath fading; therefore, the shadowing effect is actually the dominant impairment. To overcome the composite fading effects, we propose combining macroscopic selection diversity (MSD) schemes with MIMO technology. To analyze the system performance, the capacity outage expression of MIMO-based MSD (MSD-MIMO) systems using a characteristic function is applied. The analytic results show that there are significant improvements when MSD schemes are applied, even for the two-base-station diversity case. It is also observed that the effect of spatial correlation due to multipath fading is almost negligible when multiple base stations cooperatively participate in the mobile communication topology.

• Communications for Statistical Applications and Methods
• /
• 제15권4호
• /
• pp.633-642
• /
• 2008

본 논문에서는 반응변수가 하나 이상이고 설명변수들의 수가 관측치에 비하여 상대적으로 많은 경우에 널리 사용되는 부분최소제곱회귀모형에 벌점함수를 적용하여 모형에 필요한 설명변수들을 선택하는 문제를 고려하였다. 모형에 필요한 설명변수들은 각각의 잠재변수들에 대한 최적해 문제에 벌점함수를 추가한 후 모의담금질을 이용하여 선택하였다. 실제 자료에 대한 적용 결과 모형의 설명력 및 예측력을 크게 떨어뜨리지 않으면서 필요없는 변수들을 효과적으로 제거하는 것으로 나타나 부분최소제곱회귀모형에서 최적인 설명변수들의 부분집합을 선택하는데 적용될 수 있을 것이다.

• 한국정밀공학회지
• /
• 제16권5호통권98호
• /
• pp.48-57
• /
• 1999

Applications of thresholding technique are based on the assumption that object and background pixels in a digital image can be distinguished by their gray level values. For the segmentation of more complex images, it is necessary to resort to multiple threshold selection techniques. This paper describes a new method for multiple threshold selection of gray level images which are not clearly distinguishable from the background. The proposed method consists of three main stages. In the first stage, a probability distribution function for a gray level histogram of an image is derived. Cluster points are defined according to the probability distribution function. In the second stage, fuzzy partition matrix of the probability distribution function is generated through the fuzzy clustering process. Finally, elements of the fuzzy partition matrix are classified as clusters according to gray level values by using max-membership method. Boundary values of classified clusters are selected as multiple threshold. In order to verify the performance of the developed algorithm, automatic inspection process of ball grid array is presented.