http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
안성진,정연선 한국자료분석학회 2006 Journal of the Korean Data Analysis Society Vol.8 No.4
Although many problems of interest in various fields are related with compositional data on the simplex space, there has been little effort to develop basic operations and norms on the space itself. The widely used logratio analysis converts, by the logarithms of ratios of compositions, the compositional data on the simplex space to the unconstrained data on the Eucleadian space, reformulate the underlying problem in terms of these logratio compositions, and make use, wherever possible, of standard multivariate statistical procedures. Jung and Ahn(2005a, 2005b), in an effort to understand and analyze the compositional data directly on the simplex space, proposed some basic operations and norms on the simplex space. Jung and Ahn(2006) investigated the sampling distributions of the norms above mentioned. This study proposes two regression models on the Simplex space for compositional data and compares, by numerical illustrations, the applicability with Aitchison's methods. 구성성분들의 합이 항상 '1'이 되는 제약조건을 가지는 심플렉스 공간의 구성비 데이터는 분산-공분산 구조를 이용한 분석기법들을 적용하는데 많은 문제점을 가진다. 이러한 문제점을 해결하기 위해서 Aitchison의 logratio 변환에 의한 분석기법이 널리 이용되고 있다. 그러나 변환에 의한 데이터분석은 그 분석결과를 해석하기가 용이하지 않다는 단점을 가진다. 이에 '정연선·안성진(2005a,b)'은 구성비 데이터의 특수성을 살리고자 심플렉스 공간상의 기본연산자들을 이용하여 s-노옴(SN), 심플렉스 차이측도, 중심화 s-노옴(SCN) 등 몇 가지 심플렉스 공간상의 측도들을 제안하였다. 그리고 '정연선·안성진 (2006)'은 s-노옴의 표집분포를 밝혔다. 이 연구에서는 이전의 연구들에서 제안된 측도들을 이용하여 구성비 데이터에 대한 회귀분석모형을 제안하였다. 그리고 기존의 구성비 데이터의 회귀분석모형과 이 연구에서 제안한 모형을 실제 데이터에 적용한 뒤 그 결과를 비교하였다.주요용어 : 구성비 데이터, logratio 변환, s-노옴, 중심화 s-노옴, 심플렉스 차이측도.
중요지역 보안을 위한조명환경 적응형 실시간 영상 감시 시스템
안성진,이관희,권구락,김남형,고성제 대한전자공학회 2007 電子工學會論文誌-SP (Signal processing) Vol.44 No.2
In this paper, we propose a illumination environment adaptive real-time surveillance system for security of important area such as military bases, prisons, and strategic infra structures. The proposed system recognizes movement of objects on the bright environments as well as in dark illumination. The procedure of proposed system may be summarized as follows. First, the system discriminates between bright and dark with input image distribution. Then, if the input image is dark, the system has a pre-processing. The Multi-scale Retinex Color Restoration(MSRCR) is processed to enhance the contrast of image captured in dark environments. Secondly, the enhanced input image is subtracted with the revised background image. And then, we take a morphology image processing to obtain objects correctly. Finally, each bounding box enclosing each objects are tracked. The center point of each bounding box obtained by the proposed algorithm provides more accurate tracking information. Experimental results show that the proposed system provides good performance even though an object moves very fast and the background is quite dark. 본 논문에서는 군대 주둔지, 교도소, 전략적 산업구조물 등 중요한 지역의 보안을 위한 조명환경 적응적인 실시간 영상 감시 시스템을 제안한다. 제안하는 시스템은 밝은 환경에서 뿐만 아니라 객체 판별이 어려운 어두운 환경에서도 객체 추출이 추적이 가능하도록 구현하며 그 절차는 다음과 같다. 첫 번째 단계에서는 입력 영상의 분포를 판별하여 전처리 여부를 판단하고 입력 영상이 어두워 객체 탐지가 어렵다고 판단되는 경우에는 Multi-scale Reinex Color Restoration (MSRCR) 과정을 거처 보정된 입력 영상을 얻는다. 두 번째 단계인 객체 정보 획득 과정에서는 정확한 객체의 추출을 위해 보정된 배경영상과 입력영상과의 차영상을 이용하여 객체를 탐지하고 이진화 및 모폴로지 등 기본적인 영상처리 작업을 통하여 정확하게 객체를 추출한다. 마지막 단계에서는 추출된 객체의 중심점을 이용하여 좀 더 정확하게 객체를 추적할 수 있도록 한다. 실험 결과에서 제안하는 시스템은 어두운 환경에서 객체의 빠른 움직임에도 불구하고 효율적인 객체 탐지 및 추적을 수행한다.
Optimal Partitioning for Classification Trees
안성진 한국자료분석학회 2005 Journal of the Korean Data Analysis Society Vol.7 No.3
This paper introduces a unified method of choosing the most explanatory and significant multiway partitions for classification tree design and analysis. The method is derived based on the proportional-reduction-in-impurity(PRI) measure of association, which is proposed to extend the proportional-reduction-in-error(PRE) measure in the decision-theory context. For the method derivation, the PRI measure is analyzed to characterize its statistical distribution and association properties which are used to consistently handle the subjects of feature formation, feature selection, and feature deletion required in the associated classification tree construction. The PRI criterion is applied to a numerical problem for illustration.
The Usefulness of Radial Column Plate in Distal Radius Fracture: Indications and Results
안성진,이상현,김동희,장효석,홍성민,김학상 대한수부외과학회 2021 대한수부외과학회지 Vol.26 No.2
Purpose: The most common surgical treatment for distal radius fracture is internal fixation using volar locking plates, but it is sometimes difficult to maintain reduction with them. Therefore, this research reports the results of surgical treatment with additional radial column plates. Methods: We analyzed 12-month follow-up results in 100 cases. The patients had the B or C types of distal radius fractures, in accordance with AO classification, and underwent surgical treatment at our hospital from May 2013 to December 2019. There were 16 cases of B-type and 84 cases of C-type fractures. Out of these, 87 were treated with volar locking plates (V group) and 13 had additional radial column plates (VR group). The results of surgical treatment were examined clinically by measuring the disabilities of the arm, shoulder and hand (DASH) and Mayo wrist score, and radiologically by measuring the radial length, radial inclination, and volar tilt, before and after surgery. Results: After treatment, the radiographic average in the V group showed a radial length of 12.3 mm, radial inclination of 20.2°, and volar tilt of 5.8°, while the VR group showed 11.6 mm, 22.3°, and 9.0° respectively. A statistically significant difference was found in the DASH score, and the DASH score showed good results in the VR group. Conclusion: Additional radial column plate fixation is worth considering because it provides clinically and radiologically satisfactory results in treatment of B and C types distal radius fracture involving articular surface.