• Management Science and Financial Engineering
• /
• 제10권2호
• /
• pp.103-118
• /
• 2004

$\epsilon$-sensitivity analysis is a kind of methods for performing sensitivity analysis for linear programming. Its main advantage is that it can be directly applied for interior-point methods with a little computation. Although $\epsilon$-sensitivity analysis was proposed several years ago, there have been no studies on its relationship with other sensitivity analysis methods. In this paper, we discuss the relationship between $\epsilon$-sensitivity analysis and sensitivity analysis using an optimal basis. First. we present a property of $\epsilon$-sensitivity analysis, from which we derive a simplified formula for finding the characteristic region of $\epsilon$-sensitivity analysis. Next, using the simplified formula, we examine the relationship between $\epsilon$-sensitivity analysis and sensitivity analysis using optimal basis when an $\epsilon$-optimal solution is sufficiently close to an optimal extreme solution. We show that under primal nondegeneracy or dual non degeneracy of an optimal extreme solution, the characteristic region of $\epsilon$-sensitivity analysis converges to that of sensitivity analysis using an optimal basis. However, for the case of both primal and dual degeneracy, we present an example in which the characteristic region of $\epsilon$-sensitivity analysis is different from that of sensitivity analysis using an optimal basis.

• Journal of Mechanical Science and Technology
• /
• 제15권7호
• /
• pp.876-888
• /
• 2001

For a large scaled optimization based on response surface methods, an efficient quadratic approximation method is presented in the context of the trust region model management strategy. If the number of design variables is η, the proposed method requires only 2η+1 design points for one approximation, which are a center point and tow additional axial points within a systematically adjusted trust region. These design points are used to uniquely determine the main effect terms such as the linear and quadratic regression coefficients. A quasi-Newton formula then uses these linear and quadratic coefficients to progressively update the two-factor interaction effect terms as the sequential approximate optimization progresses. In order to show the numerical performance of the proposed method, a typical unconstrained optimization problem and two dynamic response optimization problems with multiple objective are solved. Finally, their optimization results compared with those of the central composite designs (CCD) or the over-determined D-optimality criterion show that the proposed method gives more efficient results than others.

• 한국안전학회지
• /
• 제33권4호
• /
• pp.105-110
• /
• 2018

Korea has entered to 'aged society', which the elderly people over 65 years old is over 14% of total population. This paper aims to analyze the traffic accident by aging level. In pursuing the above, this paper focuses on modeling the traffic accident severity based on three aging levels. The main results are as follows. First, the ratio of fatal and serious injured persons (FSI) is judged to increase according to increasing aging level. Second, the null hypothesis that there is no difference in FSI among three aging levels (aging, aged, and super-aged) is rejected. Four accident severity generalized linear models which are all statistically significant have been developed. Third, the common variables are analyzed to be median age, the number of hospital beds per persons, and turn signal usage ratio. Fourth, the differentiated traffic safety policies fitted to aging levels are required. The enforcement of traffic law violation and safety enhancement of motorcycle in the region of 'aging society', improvement of traffic facilities in the region of 'aged society', and expansion of transportation facilities in the region of 'super-aged society' are evaluated to be indispensable.

• 한국동물학회:학술대회논문집
• /
• 한국동물학회 1998년도 한국생물과학협회 학술발표대회
• /
• pp.332.1-332
• /
• 1998

No Abstract, See Full Text

• 한국동물학회:학술대회논문집
• /
• 한국동물학회 1998년도 한국생물과학협회 학술발표대회
• /
• pp.334.1-334
• /
• 1998

No Abstract, See Full Text

• 한국멀티미디어학회논문지
• /
• 제13권4호
• /
• pp.504-511
• /
• 2010

본 논문에서는 인간 뇌의 내부에 존재하는 해마를 모델링한 해마 신경망을 사용하여 도시방범용 CCTV를 위한 얼굴영역 인식 시스템을 제안한다. 이 시스템은 특징추출 부분과 학습 및 인식 부분으로 구성되어 있으며, 특징 추출 부분은 PCA(Principal Component Analysis)와 LDA(Linear Discriminant Analysis) 사용하여 구성한다. 학습부분에서는 해마의 구조의 순서에 따라 입력되는 영상 데이터들의 특징을 치아 이랑 영역에서 호감도 조정에 의해 반응 패턴을 이진화 하고, 다음으로 CA3 영역에서의 자기 연상을 통해 영상에 포함되어 있는 노이즈를 제거하게 된다. 노이즈가 제거된 데이터는 CA1 영역에서 신경망을 통해 장기기억이 이루어진다. 제안한 시스템의 성능을 평가하기 위해 형태변화와 조명변화에 따른 인식률 실험을 실시하였다. 실험 결과, 본 논문에서 제안한 특징 추출 및 학습 방법을 다른 학습 방법들과 비교하였을 때, 우수한 인식률을 가짐을 확인하였다.

• 전력전자학회논문지
• /
• 제14권6호
• /
• pp.472-480
• /
• 2009

본 논문은 3상 NPC형 3레벨 인버터의 과변조 SVPWM 기법과 변조비에 대한 출력전압의 고조파를 분석하였다. 3상 NPC형 3레벨 인버터는 SVPWM을 적용하여 선형영역을 0.907까지 확장하였고 과변조 영역에서는 푸리에 급수에 의한 추종전압의 보상기법을 적용하여 6 스텝영역까지 운전할 수 있도록 하였다. PWM 형태인 출력전압의 고조파 특성분석에는 PD방식의 멀티 캐리어 기법에 대하여 이중 푸리에 급수를 적용하여 해석하였다. 시뮬레이션은 PSIM을 사용하여 구현하였고 3레벨 인버터의 영역도의 각 영역에 대해서 고조파의 특성을 확인하였다. NPC형 3레벨 인버터의 고조파 분포는 선형영역에서는 캐리어 주파수의 측대 고조파가 분포되고, 과변조 영역으로 넘어가면서 기본파에 의한 고조파 성분이 점차 증가하고 캐리어 주파주의 사이드 밴드의 고조파 성분은 감소함을 확인하였다. 본 논문에서의 고조파 해석을 검증하기 위하여 동일한 조건에서 시뮬레이션과 실험을 수행하였다.

• 전기전자학회논문지
• /
• 제6권1호
• /
• pp.72-79
• /
• 2002

본 논문에서는 복잡한 배경의 영상에서 얼굴을 검출하는 효과적인 알고리즘을 제안한다. 제안된 알고리즘은 색상정보와 PCA-LDA(Principal Component Analysis - Linear Discriminant Analysis)에 의하여 구해진 고유얼굴 (eigenface)을 이용한다. 색상정보는 다른 어떤 방법보다 얼굴을 검출하는데 유용하게 사용된다. 고유얼굴은 전체학습 얼굴들의 평균정보를 포함하고 있기 때문에 얼굴 후보영역에 대하여 얼굴인지를 판별할 수 있는 기능을 갖는다. 전체적인 과정은 두 단계로 이루어진다. 첫 번째 단계는 영상내에서 색상정보를 이용하여 살색영역의 1차 얼굴 후보영역을 찾아 후보영역의 위치와 기를 결정한다. 두 번째 단계는 1차 얼굴 후보영역에 대하여 PCA-LDA에 의한 얼굴의 유사성을 측정하여 얼굴인지 아닌지를 판별한다. 제안한 검출 방법을 사용한 실험 결과, 색상정보를 사용하여 1차 얼굴 후보영역의 크기와 위치를 결정함으로써 검출속도의 향상을 가져올 수 있었다. 또한 PCA-LDA에 의한 고유얼굴과의 비교를 통해 복잡한 매경이 있는 영상에서도 97%의 검출률을 얻을 수 있었다.

• Journal of Periodontal and Implant Science
• /
• 제37권1호
• /
• pp.137-150
• /
• 2007

CADIA(Computer-assisted densitometric image analysis) method is used to analyze bone density changes around the implants. The usefullness and reproducibility of the method was assessed. We tried to find out if there is any possibility to quantitiate and qualitify peri-implant bone density change as time passes. And we concluded that this newly developed linear analysis is efficient for analyzing peri-implant bone density change non-Invasively. In this study, 2152 machined $Br{\aa}nemark$ fixtures installed from 1994 to 2002 in the department of Periodontics, Dental hospital of College of Dentistry, Yonsei University were included. Of these fixtures 22 radiographically analyzable failed fixtures were used as experimental group, and 22 successful implants placed in the same patient were used as control group. 1. 57 out of 1635 machined $Br{\aa}nemark$ standard and Mk II implants system failed, the survival rate was 96.5%. And 11 out of 517 machined $Br{\aa}nemark$ Mk III and Mk IV implants system failed, the survival rate was 97.9%. Total survival rate was 96.8%. 2. 22 failed implants were used for the analysis, 10 of which failed before prosthetic treatment due to infection and overheating. 12 failed due to overload after prosthetic treatment, 63.6% of which failed during the early phase of functional loading, i, e. before 1 year of loading. 3. Bone density change values around coronal region of the failed implants were $-6.54{\pm}6.35$, middle region were $-3.53{\pm}5.78$, apical region were $-0.75{\pm}10.33$, resulting in average of $-3.71{\pm}8.03$. 4. Bone density change values around coronal region of the successful implants were $4.25{\pm}4.66$, middle region were $6.33{\pm}5.02$, apical region were $9.89{\pm}4.67$, resulting in average of $6.27{\pm}5.29$. 5. There was a statistically significant difference between two groups (p<0.01). In conclusion, the linear analysis method using computer-assisted densitometric image analysis could be a useful method for the analysis of implants, and could be used for future implant researchs.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1625-1625
• /
• 2001

The calibration equations for Brix value determination of intact mango were developed using the NIR spectra in a short wavelength region from 700 to 1100 nm. Multiple linear regression (MLR) and partial least square regression (PLS) was used for the calibration. It was found that the best wavelength region for PLS calibration from 900 to 1000 nm was similar to the wavelength region selected by MLR from 906 nm to 996 nm. Both MLR and selected region PLS provided sufficiently accurate prediction equations for Brix determination of intact mango. For MLR, the prediction results were SEP = 0.45 Brix and Bias = -0.04 Brix while PLS prediction results were SEP : 0.46 Brix and Bias = -0.2 Brix. It was concluded that MLR and PLS would have similar abilities in making calibration equation for Brix determination of intact mango if the appropriate wavelengths or wavelength region were selected. The appropriate wavelength region for PLS regression could be assumed by using the wavelength region selected by MLR in place of random selection, The relationship between calibration results of MLR and PLS regression is discussed.