• 한국경영과학회지
• /
• 제10권1호
• /
• pp.9-13
• /
• 1985

This paper develops a decomposition method for stochastic programming with a block diagonal structure. Here we assume that the right-hand side random vector of each subproblem is differente each other. We first, transform this problem into a master problem, and subproblems in a similar way to Dantizig-Wolfe's Decomposition Princeple, and then solve this master problem by solving subproblems. When we solve a subproblem, we first transform this subproblem to a Deterministic Equivalent Programming (DEF). The form of DEF depends on the type of the random vector of the subproblem. We found the subproblem with finite discrete random vector can be transformed into alinear programming, that with continuous random vector into a convex quadratic programming, and that with random vector of unknown distribution and known mean and variance into a convex nonlinear programming, but the master problem is always a linear programming.

• 대한기계학회논문집A
• /
• 제24권10호
• /
• pp.2438-2450
• /
• 2000

The Design Axioms provide a general framework for design methodologies. The axiomatic design framework has been successfully applied to various design tasks. However, the axiomatic design has been rarely utilized in the detailed design process of structures where the optimization technology is generally carried out. The relationship between the axiomatic design and the optimization is investigated and Logical Decomposition method is developed for a systematic structural optimization. The entire optimization process is decomposed to satisfy the Independence Axiom. In the decomposition process, design variables are grouped according to sensitivities. The sensitivities are evaluated by the Analysis of Variance(ANOVA) to avoid considering only local values. The developed method is verified through examples such as the twenty -five members transmission tower and the two -bay-six-story frame.

• KIEE International Transactions on Power Engineering
• /
• 제4A권1호
• /
• pp.33-41
• /
• 2004

Knowledge of partial discharge (PD) is important to accurately diagnose and predict the condition of insulation. The PD phenomenon is highly complex and seems to be random in its occurrence. This paper indicates the possible use of chaos theory for the recognition and distinction concerning PD signals. Chaos refers to a state where the predictive abilities of a systems future are lost and the system is rendered aperiodic. The analysis of PD using deterministic chaos comprises of the study of the basic system dynamics of the PD phenomenon. This involves the construction of the PD attractor in state space. The simulation results show that the variance of an orthogonal axis in an attractor of chaos theory increases according to the magnitude and the number of PDs. However, it is difficult to clearly identify the characteristics of the PDs. Thus, we calculated the magnitude on an orthogonal axis in an attractor using singular value decomposition (SVD) and principal component analysis (PCA) to extract the numerical characteristics. In this paper, we proposed the condition monitoring method for gas insulated switchgear (GIS) using SVD for efficient calculation of the variance. Thousands of simulations have proven the accuracy and effectiveness of the proposed algorithm.

• The Journal of Asian Finance, Economics and Business
• /
• 제4권4호
• /
• pp.61-66
• /
• 2017

Environmental awareness and its relation to the development of economy has garnered increased attention in recent years. Researchers, over the years, have argued that sustainable development warrants for minimizing environmental degradation since one depends on the other. This study analyzes the relationship between environmental degradation (carbon emission taken as proxy for degradation), economic growth, total energy consumption and industrial production index growth in Bangladesh from year 1998 to 2013. This study uses Vector Autoregression (VAR) Model and variance decomposition of VAR to analyze the effect of these variables on carbon emission and vice-versa. The findings of VAR model suggest that industrial production and GDP per capita has significant relationship with carbon emission. Further analysis through variance decomposition shows carbon emission has consistent impact on industrial production over time, whereas, industrial production has high impact on emission in the short run which fades in the long run which is consistent with Environmental Kuznets Curve (EKC) hypothesis. Carbon emission rising along with GDP per capita and at the same time having low impact in the long run on industrial index indicates there may be other sources of pollution introduced with the rise in income of the economy over time.

• 산경연구논집
• /
• 제8권1호
• /
• pp.5-13
• /
• 2017

Purpose - In this article, a dynamic model like a VAR is an appropriate choice for estimating the possible interrelationship between ownership structure and firm performance as a dynamic process. Research design, data, and methodology - Data of this work are collected from Chinese stock exchange including 350 Chinese-listed firms during the period of 1999-2012. We hypothesize that this interrelationship dynamically exists between ownership structure and firm performance. To examine the correlation, a panel Vector Auto-regression (PVAR) approach generated by GMM method is utilized to test the possible dynamic relation embedded in corporate governance. Another two dynamic analysis solutions such as orthogonalized impulse-response function and variance decomposition are also used simultaneously. Results - Findings of this study indicate the evidence that dynamically endogenous relationship exists between ownership structure and firm performance. Further, there is a dynamical correlation between investment and performance. Impulse response and variance decomposition illustrate that impact of a shock to variables themselves is the main source for their variability. Conclusions - The conclusion in this study is that there is a bidirectional and inter-temporal effect between proportion of ownership and corporate performance for a long run in accordance with impulse response function. Overall, our results suggest that corporate governance in China is more market oriented.

• 수산경영론집
• /
• 제46권1호
• /
• pp.93-107
• /
• 2015

This study aims to analyze causalities among Hairtail prices by distribution channel using a vector autoregressive model. This study applies unit-root test for stability of data, uses Granger causality test to know interaction among Hairtail Prices by distribution channel, and employes the vector autoregressive model to estimate statistical impacts among t-2 period variables used in model. Analyzing results of this study are as follows. First, ADF, PP, and KPSS tests show that the change rate of Hairtail price by distribution channel differentiated by logarithm is stable. Second, a Granger causality test presents that the producer price of Hairtail leads the wholesale price and then the wholesale price leads the consumer price. Third, the vector autoregressive model suggests that the change rate of Hairtail producer price of t-2 period variables statistically, significantly impacts change rates of own, wholesale, and consumer prices at current period. Fourth, the impulse response analysis indicates that impulse responses of the structural shocks with a respectively distribution channel of the Hairtail prices are relatively more powerful in own distribution channel than in other distribution channels. Fifth, a forecast error variance decomposition of the Hairtail prices points out that the own price has relatively more powerful influence than other prices.

• 한국산학기술학회논문지
• /
• 제16권12호
• /
• pp.8455-8461
• /
• 2015

본 논문에서는 라만 스펙트럼의 고속 탐색을 위해 특이값 분해(SVD, Singular Value Decomposition)를 이용한 새로운 탐색 알고리즘들을 제안한다. 제안 알고리즘에서는 SVD를 통해 얻은 특이벡터를 중요도에 따라 선별하여 실험에 사용함으로써 계산량 단축을 도모한다. 파일럿 테스트(Pilot test)를 수행하여 일부 데이터들을 미리 탐색 대상에서 제외시키고 부분탐색법(PDS, Partial Distance Search)을 적용하여 탐색을 수행함으로써 큰 폭으로 계산량을 감소시킨다. 실험에 사용한 데이터베이스는 총 14,032종의 화학 물질 라만 스펙트럼으로 구성하였으며, 기존의 탐색 방법인 전체탐색법(Full Search), PDS와 평균피라미드탐색법(MPS, Mean Pyramid Search)를 1차원공간상의 신호에 적용하기 적절하게 변형한 1DMPS에 PDS를 적용한 실험(1DMPS+PDS), 데이터의 분산을 내림차순 정렬하여 !DMPS와 PDS를 적용한 실험(1DMPS Sort with Variance+PDS), 데이터의 250차원 성분만 SVD 변환하여 PDS를 적용한 실험(250SVD+PDS), 그리고 제안 알고리즘 PSP(Partial SVD with PDS)와 PSSP(Partial SVD with Sorted Pilot test)을 적용한 실험을 비교 분석하였다. 각 알고리즘의 성능은 곱셈 및 덧셈의 연산량 비교를 통해 이루어졌는데, 실험 결과에 따르면 250SVD+PDS에 비해 제안알고리즘 PSP는 15.7%, PSSP에서는 64.8%의 계산량 감소를 확인하였다.

• 서비스연구
• /
• 제6권1호
• /
• pp.83-95
• /
• 2016

본 논문은 한국은행 경제통계시스템에서 제공한 서비스업생산지수와 서비스업도소매지수를 가지고 상호간의 연관성을 분석하였다. 분석을 위한 통계분석 기간은 2000년 1월부터 2015년 9월까지 15년 9개월간의 월별자료 189개를 사용하였고, 분석도구로는 E-Views 6을 이용하여 VAR 모형을 통한 그랜저 인과관계분석(Granger Causality test)과 충격반응분석(Impulse Response Function) 및 분산분해(Variance Decomposition)를 실시하였다. 주요 분석결과는 다음과 같다. 첫째, 그랜저 인과관계 분석결과(Granger Causality test) 상승률과 변동성에 있어서 서비스업생산지수와 서비스업도소매지수 상호간에 예측력이 있음을 알 수 있었다. 둘째, 충격반응함수(Impulse Response Function)분석결과 서비스업생산지수와 서비스업도도소매지수에 사이에 충격이 존재하여 일정시차까지 영향을 미치다가 사라짐을 알 수 있었다. 이는 다른 산업뿐만 아니라 서비스업산업에 있어서도 생산량은 어느 정도 도소매업체의 판매량을 예측할 수 있다는 것으로 해석할 수 있다. 마지막으로 분산분해(Variance Decomposition) 분석결과 서비스업도소매지수는 일정시차동안 73.65%~65.59%의 서비스업생산지수에 의하여 영향을 받는 것으로 나타났다. 하지만 서비스업생산지수는 일정시차동안 0.97%~1.92%의 서비스업도소매지수에 영향을 받는 것으로 나타나 영향력이 미미함을 알 수 있었다. 본 연구는 다양한 지수를 대상으로한 상호간의 가격발견을 통한 상호연관성을 분석한 기존의 연구방법을 확장하여 서비스업생산지수와 서비스업도소매지수와의 가격발견 기능을 파악하는데 기여하였다고 사료된다. 이와 같은 연구결과는 물가지수를 관리하고 있는 정부에게 물가정책을 수립하는데 의미를 부여하고, 각종 지수를 관리하고 있는 한국은행 및 통계청에게 의미 있는 시사점을 제공할 것으로 판단된다. 본 연구에 대한 한계점으로는 물가지수를 이용한 선행연구가 많지 않아서 좀 더 체계적인 분석이 부족하다는 점과 구조변화 시점을 구분하여 분석하지 못했다는 점이다. 따라서 다양한 물가지수를 활용한 후속연구와 구조변화를 전후를 대상으로 한 추가연구가 필요하다고 사료된다.

• 정보처리학회논문지B
• /
• 제13B권6호
• /
• pp.625-632
• /
• 2006

협력적 여과는 사용자 선호도를 예측하기 위해 그 사용자의 유형을 학습하는 데 목적을 둔 기술이다. 협력적 여과 시스템이 전자상거래에서 성공적인 기술일지라도 그들은 데이터의 고차원성과 희박성이라는 문제점을 갖는다. 본 논문에서는 이와 같은 문제점을 해결하기 위하여 비부정 행렬 인수분해(NNMF, Non-negative Matrix Factorization) 방법을 이용한 최근 인접 협력적 여과 방법을 제안한다. 행렬을 분해하기 위한 전처리로서 사용자 변동 계수를 이용하여 사용자-아이템 행렬의 결측치를 채우고, 이를 대상으로 비부정 분해 방식을 적용하여 행렬을 인수분해 한다. 비부정 분해 방식을 적용한 긍정 분해는 사용자들을 의미를 갖는 벡터로써 표현함으로써 사용자들을 의미 관계를 갖는 그룹으로 표현한다. 이와 같이 벡터로 표현된 사용자들은 벡터 유사도에 의해 그들간의 유사도를 계산한다. 계산된 유사도의 정도에 의해 이웃을 결정하고, 이웃들이 평가한 아이템에 대한 흥미도를 기반으로 새로운 사용자가 평가하지 않은 아이템에 대한 결측치를 예측한다.

• ETRI Journal
• /
• 제34권5호
• /
• pp.684-689
• /
• 2012

A mode-singular-value-decomposition (SVD) maximum likelihood (ML) estimation procedure is proposed for the source localization problem under an additive measurement error model. In a practical situation, the noise variance is usually unknown. In this paper, we propose an algorithm that does not require the noise covariance matrix as a priori knowledge. In the proposed method, the weight is derived by the inverse of the noise magnitude square in the ML criterion. The performance of the proposed method outperforms that of the existing methods and approximates the Taylor-series ML and Cram$\acute{e}$r-Rao lower bound.