• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2006년도 PROCEEDINGS OF JOINT CONFERENCEOF KDISS AND KDAS
• /
• pp.63-76
• /
• 2006

유전자 발현 자료(gene expression data)를 분석하기 위한 여러 가지 군집 알고리즘(clustering algorithm)과 군집 결과들을 검증하는 척도, 즉 군집 타당성분석 기법(cluster validation technique)이 제안되고 있지만, 이틀 군집 타당성을 분석하는 기법들에 대한 성능의 비교 평가는 매우 드물다. 본 논문에서는 모의 생성 자료로 몇 가지 특정 상황을 연출하여 군집 타당성 분석 기법들을 비교해 보고, 실제 유전자 발현 자료 두 가지에 대해서도 이들 기법의 성능을 비교 평가해 보았다.

• Communications for Statistical Applications and Methods
• /
• 제13권1호
• /
• pp.151-165
• /
• 2006

It is important to estimate the true misclassification rate of a given classifier when an independent set of test data is not available. Cross-validation and bootstrap are two possible approaches in this case. In related literature bootstrap estimators of the true misclassification rate were asserted to have better performance for small samples than cross-validation estimators. We compare the two estimators empirically when the classification rule is so adaptive to training data that its apparent misclassification rate is close to zero. We confirm that bootstrap estimators have better performance for small samples because of small variance, and we have found a new fact that their bias tends to be significant even for moderate to large samples, in which case cross-validation estimators have better performance with less computation.

• Toxicological Research
• /
• 제32권1호
• /
• pp.9-14
• /
• 2016

The National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods (NICEATM) provides validation support for US Federal agencies and the US Tox21 interagency consortium, an interagency collaboration that is using high throughput screening (HTS) and other advanced approaches to better understand and predict chemical hazards to humans and the environment. The use of HTS data from assays relevant to the estrogen receptor signaling data pathway is used as an example of how HTS data can be combined with computational modeling to meet the needs of US agencies. As brief summary of US efforts in the areas of biologics testing, acute toxicity, and skin sensitization will also be provided.

• International Journal of Aeronautical and Space Sciences
• /
• 제18권3호
• /
• pp.498-511
• /
• 2017

This work conducts a validation study for loads analysis of the UH-60A slowed rotor at high advance ratios. The nonlinear flexible multibody dynamics analysis code, DYMORE II, is used with a freewake model for the rotorcraft comprehensive analysis. Wind tunnel test data of airloads and structural loads of a full-scale UH-60A slowed rotor are used for this validation study. This analysis predicts well the thrust reversal phenomenon at the advance ratio of 1.0. The section airloads such as normal forces and pitching moments and the oscillatory blade structural moments in this analysis are compared well or moderately with the measured data, although the higher harmonics components of blade torsion moments are not captured well. This validation study assesses the prediction accuracy and investigates the unique aeromechanics characteristics of a slowed rotor at high advance ratio.

• Nuclear Engineering and Technology
• /
• 제54권4호
• /
• pp.1230-1244
• /
• 2022

This paper proposes an algorithm for signal validation using unsupervised methods in emergency situations at nuclear power plants (NPPs) when signals are rapidly changing. The algorithm aims to determine the stuck failures of signals in real time based on a variational auto-encoder (VAE), which employs unsupervised learning, and long short-term memory (LSTM). The application of unsupervised learning enables the algorithm to detect a wide range of stuck failures, even those that are not trained. First, this paper discusses the potential failure modes of signals in NPPs and reviews previous studies conducted on signal validation. Then, an algorithm for detecting signal failures is proposed by applying LSTM and VAE. To overcome the typical problems of unsupervised learning processes, such as trainability and performance issues, several optimizations are carried out to select the inputs, determine the hyper-parameters of the network, and establish the thresholds to identify signal failures. Finally, the proposed algorithm is validated and demonstrated using a compact nuclear simulator.

• 품질경영학회지
• /
• 제50권4호
• /
• pp.831-842
• /
• 2022

Purpose: This study carried out the Quality by Design (QbD)6σ process to verify the effectiveness and equivalence of the finished D-antigen quantitative test method, and compared the OFAT-based method validation and test result acceptance criteria with the Analytical Quality by Design (AQbD)-based method validation and test method. This is a study on how to reduce the risk of delay in permit change by increasing the reliability of permit data in the existing method by statistically analyzing the results. Methods: With the QbD6σ process, the effectiveness and equivalence of the D-antigen quantitative test method were verified with the data of the existing test method and the new test method. Results: Method validation tests are performed based on AQbD. Critical Method Parameters are identified through risk assessment, and single/combined actions are verified by designing and performing tests for Critical Method Parameters (analysis of variance, full factorial design method). Method validation can be effectively accomplished with the QbD6σ process. Conclusion: The use of QbD6σ can be used to achieve satisfactory results for both pharmaceutical companies and regulators by using appropriate statistical analytical methods for method validation as required by regulatory agencies.

• Korean Journal of Radiology
• /
• 제24권7호
• /
• pp.626-639
• /
• 2023

Objective: To investigate the association of clinical, pathologic, and magnetic resonance imaging (MRI) variables with progressive disease (PD) during neoadjuvant chemotherapy (NAC) and distant metastasis-free survival (DMFS) in patients with triple-negative breast cancer (TNBC). Materials and Methods: This single-center retrospective study included 252 women with TNBC who underwent NAC between 2010 and 2019. Clinical, pathologic, and treatment data were collected. Two radiologists analyzed the pre-NAC MRI. After random allocation to the development and validation sets in a 2:1 ratio, we developed models to predict PD and DMFS using logistic regression and Cox proportional hazard regression, respectively, and validated them. Results: Among the 252 patients (age, 48.3 ± 10.7 years; 168 in the development set; 84 in the validation set), PD was occurred in 17 patients and 9 patients in the development and validation sets, respectively. In the clinical-pathologic-MRI model, the metaplastic histology (odds ratio [OR], 8.0; P = 0.032), Ki-67 index (OR, 1.02; P = 0.044), and subcutaneous edema (OR, 30.6; P = 0.004) were independently associated with PD in the development set. The clinical-pathologic-MRI model showed a higher area under the receiver-operating characteristic curve (AUC) than the clinical-pathologic model (AUC: 0.69 vs. 0.54; P = 0.017) for predicting PD in the validation set. Distant metastases occurred in 49 patients and 18 patients in the development and validation sets, respectively. Residual disease in both the breast and lymph nodes (hazard ratio [HR], 6.0; P = 0.005) and the presence of lymphovascular invasion (HR, 3.3; P < 0.001) were independently associated with DMFS. The model consisting of these pathologic variables showed a Harrell's C-index of 0.86 in the validation set. Conclusion: The clinical-pathologic-MRI model, which considered subcutaneous edema observed using MRI, performed better than the clinical-pathologic model for predicting PD. However, MRI did not independently contribute to the prediction of DMFS.

• 대한지구과학교육학회지
• /
• 제17권1호
• /
• pp.1-19
• /
• 2024

이 연구는 테크놀로지 활용 과학 수업을 위한 분산 인지 이론 기반 수업 전략을 신뢰도와 타당도가 확보된 절차에 따라 개발한 설계·개발 연구이다. 수업 전략 개발을 위해 설계·개발 연구 방법론 절차에 따라 개발 연구와 타당화 연구를 진행하였다. 개발 연구에서는 선행 문헌 검토와 사전 전문가 검토 방법으로 초기 수업 전략을 개발하였다. 타당화 연구에서는 내적 타당화(전문가 타당화, 사용성 평가)와 외적 타당화(현장 적용 평가) 방법으로 수업 전략을 타당화하고 최종 수업 전략을 개발하였다. 최종 수업 전략은 3개의 수업 원리와 9개의 수업 전략, 38개의 세부 지침으로 구성하였다. 이 연구를 통해 연구자는 테크놀로지 활용 과학 수업을 위한 수업 전략의 적합성, 블록과 교수·학습 과정안의 유용성, 인지적 도구로서 테크놀로지의 활용 가능성, 테크놀로지 활용 교수 역량 함양을 위한 교사의 노력 필요, 수업 전략 적용에 영향을 미치는 조건을 고려한 수업 설계를 제안하였다.

• Journal of the Korean Statistical Society
• /
• 제29권1호
• /
• pp.109-122
• /
• 2000

An adaptive estimator of the efficient score function for censored and truncated regression models is developed by using $\beta$-splines to estimate the score function and a relatively simple cross validation method to determine the number of knots.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2007년도 추계학술대회 논문집
• /
• pp.163-164
• /
• 2007