• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.743-758
• /
• 2005

This paper consider penalized likelihood regression with data from exponential family. The fast computation method applied to Gaussian data(Kim and Gu, 2004) is extended to non Gaussian data through asymptotically efficient low dimensional approximations and corresponding algorithm is proposed. Also smoothing parameter selection is explored for various exponential families, which extends the existing cross validation method of Xiang and Wahba evaluated only with Bernoulli data.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.612-614
• /
• 1999

In order to improve the operational reliability, it is necessary to validate the measured sensor data, isolate any failed sensor and recover the failed critical measurement. This paper describes the use of estimating equation to identify failed sensors and to recover the feedback signal for control purpose when the sensor measurement is determined to be erroneous Simulation results show that the proposed sensor validation scheme can adequately identify the failed sensor and provide reasonable estimates for control purposes.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2003년도 The Fifth Asian Computational Fluid Dynamics Conference
• /
• pp.43-45
• /
• 2003

Nonlinear relationship between Reynolds stresses and the rate of strain for nonlinear${\kappa}-{\varepsilon}$ turbulence models is validated theoretically by using the boundary layer assumptions against the turbulence­driven secondary flows in noncircular ducts and then the prediction performance for several nonlinear models is evaluated numerically through the application to the turbulent flow in a square duct.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2003년도 춘계학술대회 논문집
• /
• pp.462-467
• /
• 2003

According to the computerization of railway signalling system, necessity of communication protocol for interface between these equipments is increasing. Therefore the research on communication protocol structure that is required according to computerization trend of these signalling goes. In our research the existed protocol currently used was analyzed, and the simulation modeling for performance analysis is deduced. Based on this simulation model the performance analysis and comparison is carried out, and also validation test is executed about new suggested protocol.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.593-605
• /
• 2006

We have developed a catenary-pantograph dynamic simulation program by using the finite element method and verified the accuracy according to the EN 50319. During the validation process, we have reviewed which the time integration methods is proper for this application. among the Newmark method, Wilson theta method and alpha method. We conclude that the alpha method is the best in terms of computation time and accuracy.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.446-448
• /
• 2007

This paper presents the high frequency (HF) eigenvalue results against IEEE SSR First Benchmark Mode and validation using the simultaneous time-domain simulation program, PSCAD/EMTDC. Two results show a little difference but not much. Particularly, HF eigenvalue analysis results tends to give more conservative results compared to those of the exact time-domain simulation.

• Journal of Welding and Joining
• /
• 제22권1호
• /
• pp.50-57
• /
• 2004

This paper provides FE and experimental validation of the defect assessment method for strength mismatched welded structures, resulting from the Brite Euram SINTAP (Structural Integrity Assessment Procedures for European Industry) project. This shows that the proposed method is conservative, and that the degree of conservatism is similar to that embedded in the methods for homogeneous structures. It provides confidence in the use of the proposed SINTAP method for assessing defective weld strength mismatched structures.

• Nuclear Engineering and Technology
• /
• 제37권1호
• /
• pp.11-24
• /
• 2005

A very important feature in the development of nuclear technology has been and will continue to be the flow of information from nuclear data production to the various applications fields in nuclear technology. Both, nuclear data and this communications flow are defined in this paper. Nuclear data result from specific technical activities including their production, evaluation, processing, verification, validation and applications. These activities are described, focusing on nuclear reactor calculations. Mathematical definitions of different types of nuclear data are introduced, and international forums involved in nuclear data activities are listed. Electronic links to various sources of information available on the web are specified, whenever possible.

• 초등상담연구
• /
• 제9권1호
• /
• pp.21-39
• /
• 2010

이 연구의 목적은 Armsden과 Greenberg(1983)이 개발한 부모 및 또래 애착 검사(Inventory of Parent and Peer Attachment)에서 부모애착척도를 한국 초 중 고등학생에게 동일하게 사용할 수 있도록 수정하고 타당화 하는 것이다. 이를 위해 부와 모에 대한 애착을 각각 독립적으로 측정하는 25문항으로 구성된 한국형 부모애착척도(IPA)를 개발하여 서울과 경기도 소재의 초 중 고등학생 964명을 대상으로 실시하였다. 수정된 IPA의 신뢰도와 타당도 검증을 위해 전문가 분석을 통한 내용타당도, 확인적 요인분석을 통한 구인타당도를 검증하였고, Cronbach $\alpha$를 산출하였다. 분석 결과, 부와 모에 대한 애착 척도 모두 양호한 신뢰도를 보였으며, 기존의 IPPA에서 제안한 3요인 모형이 우리나라 초, 중, 고등학생들을 대상으로 했을 때도 비교적 양호한 적합도를 보였다. 또한 다집단 분석을 이용하여 IPA의 형태동일성, 측정동일성, 척도동일성을 검증함으로써 초, 중, 고등 학교급간 구인동등성을 확인한 결과 IPA는 한국 초 중 고등학생에게 동일하게 사용할 수 있는 척도로 확인되었다.

• 동의신경정신과학회지
• /
• 제28권3호
• /
• pp.207-216
• /
• 2017

Objectives: To simplify the mindfulness scale and to ensure reliability and validity of the scale. Methods: To develop scale items using the original scale and to identify factor structure of the scale, exploratory factor analysis was conducted based on results of factor analysis, the short-form 5-factor mindfulness scale item was selected. Internal consistency coefficient was calculated and confirmatory factor analysis was conducted to verify reliability of the short-form scale. Finally, to verify validity of the abbreviated scale, we conducted correlation analysis with the abbreviated scale and the mindfulness scale (FFMQ). Results: As with the original scales, scaled scales were composed of 5 factors and consisted of 15 items in total. Factor analysis revealed factor loadings were adequate and reliability and validity were secured. Conclusions: It provided that mindfulness shortening scale validation can be used more simply to measure mindfulness in the clinical scene.