• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.1169-1175
• /
• 2008

The validation technique is classified with two methods whether to demand of additional experimental points. The method which requires additional experimental points such as RSME is actually impossible in engineering field. Therefore, the method which only use experimented points such as the cross validation technique is only available. But the cross validation not only requires considerable computational costs for generating metamodel each iterations, but also cannot measure quantitatively the fidelity of metamodel. In this research we propose a new validation technique for representative metamodels using an variance of metamodel and confidence interval information. The proposed validation technique computes confidence intervals using a variance information from the metamodel. This technique will have influence on choosing the accurate metamodel, constructing ensemble of each metamodels and advancing effectively sequential sampling technique.

• 대한기계학회논문집A
• /
• 제34권5호
• /
• pp.541-547
• /
• 2010

메타모델의 정확도를 엄밀하게 검증하는 것은 메타모델링에서 중요한 연구주제이다. k 점 선택교차검증기법이 많은 계산시간을 요구하면서도 메타모델의 정확도를 정략적으로 측정하지 못한다. 최근들어, 평균 $_0$ 기준이 메타모델의 정확도를 정량적으로 제공하기 위하여 제안되었다. 그러나 평균 $_0$ 검증 기준은 크리깅 메타모델이 부정확함에도 불구하고 일찍 수렴하는 경향이 있다. 따라서 본 연구에서는 최대엔트로피를 이용한 순차적 실험계획에서 크리깅모델의 평균과 분산을 이용한 정확도 평가기법을 제안한다. 이 제안한 기법은 평균 및 분산을 계산할 때 수치해석으로 구하는 것이 아니라 크리깅메타모델을 직접 적분하여 구하기 때문에 k 점 선택교차검증기법보다 효율적이며 정확하다. 제안한 기준은 실제 응답의 평균제곱오차의 경향과 매우 유사하여 순차적 실험계획의 수렴기준으로 사용할 수 있다.

• Wind and Structures
• /
• 제18권4호
• /
• pp.375-389
• /
• 2014

The high-frequency force-balance (HFFB) technique and its subsequent improvements are reviewed in this paper, including a discussion about nonlinear mode shape corrections, multi-force balance measurements, and using HFFB model to identify aeroelastic parameters. To apply the HFFB technique in engineering practice, various validation studies have been conducted. This paper presents the results from an analytical validation study for a simple building with nonlinear mode shapes, three experimental validation studies for more complicated buildings, and a field measurement comparison for a super-tall building in Hong Kong. The results of these validations confirm that the improved HFFB technique is generally adequate for engineering applications. Some technical limitations of HFFB are also discussed in this paper, especially for higher-order mode response that could be considerable for super tall buildings.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.920-923
• /
• 2002

In this paper, we propose Class Diagram With Constraints (CDWC) as an object oriented modeling technique which makes validation possible in software development. CDWC is a simple and basic model for the object oriented analysis, and has a reasonable strictness for software developers. CDWC consists of class diagrams and constraints (invariant and pre/post conditions), using UML and a subset of OCL.. We introduce a method of validation of CDWC using the verification technique of algebraic formal specification language CafeOBJ.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2004년도 학술발표논문집
• /
• pp.195-198
• /
• 2004

One Important problem in a cancer microarray study is to identify a set of genes from which a molecular prognostic indicator can be developed. In parallel with this problem is to validate the chosen set of genes. We develop in this note a K-fold cross validation procedure by combining a 'pre-validation' technique and a bootstrap resampling procedure in the Cox regression . The pre-validation technique predicts the microarray predictor of a case without having seen the true class level of the case. It was suggested by Tibshirani and Efron (2002) to avoid the possible over-fitting in the regression in which a microarray based predictor is employed. The bootstrap resampling procedure for the Cox regression was proposed by Sauerbrei and Schumacher (1992) as a means of overcoming the instability of a stepwise selection procedure. We apply this K-fold cross validation to the microarray data of 92 gastric cancers of which the experiment was conducted at Cancer Metastasis Research Center, Yonsei University. We also share some of our experience on the 'false positive' result due to the information leak.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.48-54
• /
• 2019

This paper proposed a method of validation data augmentation for improving the grading accuracy of diabetic macular edema (DME) using deep learning. The data augmentation technique is basically applied in order to secure diversity of data by transforming one image to several images through random translation, rotation, scaling and reflection in preparation of input data of the deep neural network (DNN). In this paper, we apply this technique in the validation process of the trained DNN, and improve the grading accuracy by combining the classification results of the augmented images. To verify the effectiveness, 1,200 retinal images of Messidor dataset was divided into training and validation data at the ratio 7:3. By applying random augmentation to 359 validation data, $1.61{\pm}0.55%$ accuracy improvement was achieved in the case of six times augmentation (N=6). This simple method has shown that the accuracy can be improved in the N range from 2 to 6 with the correlation coefficient of 0.5667. Therefore, it is expected to help improve the diagnostic accuracy of DME with the grading information provided by the proposed DNN.

• 대한기계학회논문집A
• /
• 제31권1호
• /
• pp.55-61
• /
• 2007

Recently simulation model becomes an essential tool for analysis and design of a system but it is often expensive and time consuming as it becomes complicate to achieve reliable results. Therefore, high-fidelity simulation model needs to be replaced by an approximate model, the so-called metamodel. Metamodeling techniques include 3 components of sampling, metamodel and validation. Cross-validation approach has been proposed to provide sequnatially new sample point based on cross-validation error but it is very expensive because cross-validation must be evaluated at each stage. To enhance the cross-validation of metamodel, sequential sampling method using candidate points and representative cross-validation is proposed in this paper. The candidate and representative cross-validation approach of sequential sampling is illustrated for two-dimensional domain. To verify the performance of the suggested sampling technique, we compare the accuracy of the metamodels for various mathematical functions with that obtained by conventional sequential sampling strategies such as maximum distance, mean squared error, and maximum entropy sequential samplings. Through this research we team that the proposed approach is computationally inexpensive and provides good prediction performance.

• 대한기계학회논문집A
• /
• 제36권8호
• /
• pp.873-879
• /
• 2012

메타모델은 설계 프레임워크 안에서 높은 효율성과 우수한 예측 능력, 타 프로그램과 쉬운 연동성 때문에 공학분야에서 지난 10 년간 최적설계 기법들과 함께 발전해왔다. 메타모델을 구성하기 위해서는 실험계획법, 메타모델링 기법, 검증법과 같은 절차가 요구된다. 검증법은 메타모델의 정확성을 판단하기 때문에 순차적 크리깅 메타모델에서 정확한 크리깅 메타모델을 구성하기 위한 표본점의 개수를 결정한다. 크리깅 메타모델과 같은 보간모델은 표본점에서의 응답을 항상 지나기 때문에 기존 방법으로 메타모델의 정확성을 판단하기 위해서는 추가적인 해석이나 메타모델의 재구성이 요구된다. 본 연구에서는 이러한 추가적인 해석과 메타모델의 재구성을 요구하지 않는 메타모델의 해석적 민감도를 이용하는 민감도 검증법을 제안한다. 14 개의 2 차원 수학예제와 공학예제를 이용하여 이 방법의 타당성을 검증한다.

• 한국시뮬레이션학회논문지
• /
• 제18권4호
• /
• pp.185-195
• /
• 2009

최근 시스템들이 복잡해지면서 시뮬레이션을 통한 시스템의 분석이 주목을 받고 있다. 시뮬레이션 분석에서 가장 핵심적인 부분 중의 하나가 시뮬레이션 모델의 검증이며, 이 과정을 통하여 시뮬레이션 모델이 얼마나 실제 시스템을 대변할 수 있는지를 판단한다. 모델의 검증에서 시뮬레이션 모델과 실제시스템의 데이터를 비교할 때 발생하는 차이는 입력 데이터의 차이에 의한 영향도 있으며, 이를 통한 모델의 검증 결과는 높은 신뢰성을 보장하지 못한다. 따라서 이 논문에서는 실제와 동일한 입력 데이터를 바탕으로 하는 Trace-Driven 시뮬레이션을 기반으로 모델을 설계하였다. 한편, 출력데이터들을 하나의 통계량을 통한 검증이 아닌 클래스 별 검증을 하기 위해 데이터마이닝 분야에서 분류기의 성능을 판단하는 F 척도를 응용하여 시뮬레이션 모델의 검증을 수행하였다. 그 결과, 제안된 검증 방법은 정밀한 모델의 검증을 가능하게 하고, 검증 시에 피드백을 제공함으로써 용이한 수정 작업을 가능하게 한다.

• Journal of Mechanical Science and Technology
• /
• 제17권7호
• /
• pp.1083-1094
• /
• 2003

This study represents an assessment of the phase-Doppler technique to the measurements of dense droplet laden jet. High-pressure injection fuel sprays have been investigated to evaluate the use of the Phase-Doppler anemometry (PDA) technique. The critical issue is the stability of the phase-Doppler anemometry technique for dense droplet laden jet such as Diesel fuel spray in order to insure the results from the drop size and velocity measurements are repeatable, consistent, and physically realistic because the validation rate of experimental data is very low due to the thick optical density. The effect of shift frequency is minor, however, the photomultiplier tube (PMT) voltage setting is very sensitive to the data acquisition and noise in dense droplet laden jet. The optimum PMT voltage and shift frequency should be chosen so that the data such as volume flux and drop diameter do not change rapidly.