• Computational Structural Engineering
• /
• v.4 no.2
• /
• pp.111-117
• /
• 1991

The analysis method calculating the mean and standard deviation for the eigenvalue of complicated structures in which the limit state equation is implicitly expressed is formulated and applied to the buckling analysis by combining probabilistic finite element method with direct differential method which is a kind of sensitivity analysis technique. Also, the probability of buckling failure is calculated by combining classical reliability techniques such a MVFOSM and AFOSM. As random variables external load, elastic modulus, sectional moment of inertia and member length are chosen and Parkinson's iteration algorithm in AFOSM is used. The accuracy of the results by this study is verified by comparing the results with the crude Monte Carlo simulation and Importance Sampling Method. Through the case study of some structures the important aspects of buckling reliability analysis are discussed.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.18 no.1
• /
• pp.29-42
• /
• 2005

Considering the effect by uncertainty in the structures, it is reasonable that the safety examination has to be performed by using method of reliability evaluation. Therefore, in this study, program is developed which can perform the reliability analysis or the dynamic response analysis more efficiently by formularizing the stochastic finite element analysis suitable for the existing reliability analysis about the cable stayed bridge suffering the seismic loads. Based on this program, the characteristic of dynamic responses is analyzed quantitatively by examining the average, the standard deviation and the coefficient of variance about the displacement, the resistance and the tension of cable according to the random variables. and the safety of cable stayed bridge is evaluated by examining of reliability index and failure probability

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.4C
• /
• pp.476-483
• /
• 2009

Tracking and detecting targets by the microwave seeker is affected by the clutter reflecting from the earth's surface. In order to detect retreating targets in look-down scenario, which appear in the sidelobe clutter (SLC) region, in the microwave seeker of high pulse repetition frequency (HPRF) mode, it is necessary to understand statistical characteristics of the surface SLC. Statistical analysis of SLC has been conducted for several kinds of the surface using data obtained by the captive flight test of the microwave seeker in the HPRF mode. The probability density function (PDF) fitting is conducted for several kinds and conditions of the surface. PDFs and PDF parameters, which best describe statistical distribution of the SLC power, are estimated. By using the estimated PDFs and PDF parameters, analyses for setting the target-detection thresholds, which give a desired level of target-detection false alarm probability, are made. These analysis materials for statistical characteristics of SLC power and the target-detection threshold can be used in various fields, such as development of a target-detection method, the constant false alarm rate processing.

• Computational Structural Engineering
• /
• v.4 no.4
• /
• pp.125-133
• /
• 1991

For the purpose of efficiently calculating the design sensitivity and the reliability for the complicated structures in which the structural responses or limit state functions are given by implicit form, the probabilistic finite element method is introduced to formulate the deterministic design sensitivity analysis method and incorporated with the second moment reliability methods such as MVFOSM, AFOSM and SORM. Also, the probabilistic design sensitivity analysis method needed in the reliability-based design is proposed. As numerical examples, two thin plates are analyzed for the cases of plane stress and plate bending. The initial yielding is defined as failure criterion, and applied loads, yield stress, plate thickness, Young's modulus and Poisson's ratio are treated as random variables. It is found that the response variances and the failure probabilities calculated by the proposed PFEM-based reliability method show good agreement with those by Monte Carlo simulation. The probabilistic design sensitivity evaluates explicitly the contribution of each random variable to probability of failure. Further, the design change can be evaluated without any difficulty, and their effect on reliability can be estimated quickly with high accuracy.

• Ecology and Resilient Infrastructure
• /
• v.11 no.2
• /
• pp.55-64
• /
• 2024

The disaster impact assessment system was introduced in 2005 as a disaster prevention procedure for comprehensive and systematic developmental projects. However, according to the 'Practical Guidelines for Disaster Impact Assessment', Jeju Island's unique hydrogeological features necessitate the calculation of isohyetal-based probabilistic rainfall, which can reflect altitude, when estimating probabilistic rainfall for flood volume determination, rather than using conventional methods. Despite Jeju Island being centered around Hallasan, there are three Automatic Weather Stations (AWS) located at the summit of Hallasan, making weather stations denser than in other cities and provinces. Therefore, it is judged that there would be no difficulty in applying conventional methods, such as utilizing the probabilistic rainfall data from the weather stations or employing the Thiessen method, to estimate flood volumes for small-scale project areas. Accordingly, this study conducts a comparative analysis of the impact of applying general probabilistic rainfall from weather stations and isohyetal-based probabilistic rainfall in site in the context of Jeju Island's disaster impact assessment system.

• Journal of Educational Research in Mathematics
• /
• v.20 no.2
• /
• pp.163-183
• /
• 2010

It has long been of controversy what the meanings of probability is. And a century has past after the mathematical probability has been at the center of the school curriculum of it. Recently statistical meaning of probability becomes important for various reasons. However the simple modification of its definition is not enough. The computational reasoning of the probability and its practical application needs didactical changes and new instructional transformations along with the modification of it. Most of the current text books introduce probability as a limit of the relative frequencies, a statistical probability. But when the probability computation of the union of two events, or of the simultaneous events is faced on, they use mathematical probability for explanation and practices. Accordingly there is a gap for students in understanding those. Probability is an intuitive concept as far as it belongs to the domain of the experiential frequency. And frequency distribution must be the instructional bases for the (statistical) probability novices. This is what we mean by the probability in accordance with the distribution concepts. First of all, in order to explain the probability of the complementary event we should explain the empirical relative frequency of it first. These are the case for the union of two events and for the simultaneous events. Moreover we need to provide a logic of probabilistic guesses, inferences and decision, which we introduce with the name “the likelihood principle”, the most famous statistical principle. We emphasized this be done through the problems of practical decision making.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.10a
• /
• pp.164-166
• /
• 2010

선박의 안전운항을 위하여 AIS를 탑재하는 선박은 지속적으로 증가하고 있으나 이에 따른 기지국 환경은 변하지 않고 있다. 현재의 AIS 기지국은 초기에 광역의 통신권을 확보하기 위한 최적지에 설치되어 있으나, 기지국 통신권의 과다 확보, AIS 통신 용량의 한계, AIS 탑재 선박의 증가 등으로 인하여 AIS 슬롯 간 충돌이 발생할 가능성이 높아지고 있다. 본 연구에서는 AIS 기지국의 광역 통신환경에 따른 슬롯 간 간섭에 의한 AIS 메시지의 오류 확률에 대하여 분석하였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.514-519
• /
• 2002

우리는 유머문서의 추천을 위해서 문서 정보, 사용자 정보, 공통 등급매김 정보 등을 모두 이용하는 4 개의 관찰 변수와 이들간 관계의 학습을 위한 은닉변수를 사용한 확률모델을 구축하였다. 이 모델은 학습된 은닉 변수와 가시 변수 간의 관계를 통해 누락 관찰 데이터에 대해서도 추정값을 유도해 낼 수 있으므로 등급매김 정보가 부족하거나 새로운 사용자와 문서의 도입시에 안정적인 추천 성능을 보여 줄 수가 있다. 또한 확률 모델의 학습을 위해서 EMl 알고리즘을 이용하였는데 저평가된 데이터의 이용도를 높이기 위해서 추천을 반대하는 확률 모델을 따로 두고 이들간에 분류모델(classification model)을 두어서 추정값을 분류해내는 방식을 취한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.538-541
• /
• 2000

본 논문에서는 인터넷과 같은 가상 공간에서 사용자의 신분을 확인하기 위해서 길함-허용기법을 이용해 본인의 신분을 확인하는 인증 기법을 제안한다. 제안 기법은 기존 패스워드 기법에 의존하는 신분 확인 기법을 다수의 질문-응답 기법으로 전환하므로써 인간의 기억력 한계와 패스워드 강도 사이의 trade-off를 고려한 방안으로 다양한 질문의 형태에 따라 확률에 근거하여 신분을 확인하는 방안으로 가상 공간에서의 인터넷 뱅킹 및 다양한 전자상거래 응용 등에 직·간접적으로 활용될 수 있다. 또한 실용적인 측면의 응용을 위해 다양한 종류의 질문을 구성하여 이에 대한 경험적 정답 확률을 고려한 신분 확인 확률도 산출하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.301-303
• /
• 2001

최근 DNA 칩 또는 마이크로어레이 기술의 발전으로 인해 한 세포 내의 수천 개의 유전자의 발현 정도를 동시에 측정할 수 있게 되었다. 이러한 마이크로어레이 데이터를 분석해서 암의 경과나 세포의 주기적 변화 등에 영향을 미치는 유전자들을 알아낼 수 있다. 본 논문에서는 베이지안망을 이용해서 마이크로어레이 데이터를 분석, 백혈병의 경과를 예측한다. 베이지안망은 다수의 변수들간의 확률적 관계를 표현하는 그래프 모델로 각 유전자들간의 확률적 관계를 표현하는 그래프 모델로 각 유전자들간의 확률적 관계를 사람이 알아보기 쉬운 형태로 학습할 수 있다는 장점이 있다. 마이크로어레이 데이터에 대해서 학습된 베이지안망은 백혈병 경과 예측에 대해서 기존의 방법보다 뛰어난 성능을 보였다.