• 대한토목학회논문집
• /
• 제13권3호
• /
• pp.163-172
• /
• 1993

본 문은 Lade의 Single surface 구성모델의 변형율 예측 능력을 평가하기 위해 백마강모래를 사용, 등방압축시험과 배수삼축시험을 반복 시행하여 모델에 필요한 각 토질매개변수값을 다수 구하여 통계처리 하였다. 그리고 1계근사법을 이용하여 이 구성모델의 변형율 예측능력을 확률론적으로 평가하였다. 그 결과 변동계수와 상관계수를 효과적으로 이용하여 토질매개변수의 수를 줄일 수 있을 것으로 기대되며 변동계수가 0.51 이하로서 이 구성모델의 변형율 예측 능력은 확률론적으로 매우 안정된 구성모델임을 알았다.

• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.849-854
• /
• 2001

Bishop이 제안한 Generative Topographic Mapping(GTM)은 Kohonen이 제안한 자율 학습 신경망인 Self Organizing Maps(SOM)의 확률 버전이다. GTM은 데이터가 생성되는 확률 분포를 잠재 변수, 혹은 은닉 변수를 사용하여 모형화한다. 이것은 SOM에서는 구현될 수 없는 GTM만의 특징이며, 이러한 특징으로 인하여 SOM의 한계들을 극복할 수 있게 된다. 본 논문에서는 이러한 GTM 모형에 베이지안 학습(Bayesian learning)을 결합하여 작은 오분류율을 가지는 분류 알고리즘인 베이지안 GTM(Bayesian GTM)을 제안한다. 이 알고리즘은 기존의 GTM의 빠른 계산 처리 능력과 데이터에 대한 확률 분포, 그리고 베이지안 추론의 정확성을 이용하여 기존의 분류 알고리즘보다 우수한 결과를 얻게 된다. 본 논문에서는 기존의 분류 알고리즘에서 많이 실험하였다. 학습 데이터를 통하여 이를 확인하였다.

• Steel and Composite Structures
• /
• 제20권6호
• /
• pp.1345-1368
• /
• 2016

This paper presents the probabilistic-based assessment of composite steel-concrete structures through an innovative framework. This framework combines model identification and reliability assessment procedures. The paper starts by describing current structural assessment algorithms and the most relevant uncertainty sources. The developed model identification algorithm is then presented. During this procedure, the model parameters are automatically adjusted, so that the numerical results best fit the experimental data. Modelling and measurement errors are respectively incorporated in this algorithm. The reliability assessment procedure aims to assess the structure performance, considering randomness in model parameters. Since monitoring and characterization tests are common measures to control and acquire information about those parameters, a Bayesian inference procedure is incorporated to update the reliability assessment. The framework is then tested with a set of composite steel-concrete beams, which behavior is complex. The experimental tests, as well as the developed numerical model and the obtained results from the proposed framework, are respectively present.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2263-2275
• /
• 2023

In general, an internal fire events probabilistic safety assessment (PSA) model is quantified by modifying the pre-existing internal event PSA model. Because many pieces of equipment or cables can be damaged by a fire, a single fire event can lead to multiple internal events PSA initiating events (IEs). Consequently, when the fire events PSA model is quantified, inappropriate minimal cut sets (MCSs), such as duplicate MCSs, may be generated. This paper shows that single quantification of a hypothetical single-top fire event PSA model may generate the following four types of inappropriate MCSs: duplicate MCSs, MCSs subsumed by other MCSs, nonsense MCSs, and MCSs with over-counted fire frequencies. Among the inappropriate MCSs, the nonsense MCSs should be addressed first because they can interfere with the right interpretation of the other MCSs and prevent the resolution of the issues related to the other inappropriate MCSs. In addition, we propose a resolution process for each of the issues caused by these inappropriate MCSs and suggest an overall procedure for resolving them. The results of this study will contribute to the understanding and resolution of the inappropriate MCSs that may appear in the quantification of fire events PSA models.

• Steel and Composite Structures
• /
• 제37권2호
• /
• pp.151-173
• /
• 2020

This paper aims to probabilistically evaluate performance of two types of I beam to box column (IBBC) connection. With the objective of considering the variability of seismic loading demand, statistical features of the inter-story drift ratio corresponding to the second, fifth and eleventh story of a 12-story steel special moment resisting frames are extracted through incremental dynamic analysis at global collapse state. Variability of geometrical variables and material strength are also taken into account. All of these random variables are exported as inputs to a probabilistic finite element model which simulates the connection. At the end, cumulative distribution functions of local seismic demand for each component of each connection are provided using histogram sampling. Through a parametric study on probabilistic local seismic demand, the influence of some geometrical random variables on the performance of IBBC connections is demonstrated. Furthermore, the probabilistic study revealed that IBBC connection with widened flange has a better performance than the un-widened flange. Also, a design procedure is proposed for WF connections to achieve a same connection performance in different stories.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권1_2호
• /
• pp.81-92
• /
• 2003

일반화 LR(Generalized LR, 이하 GLR) 파싱은 선형 스택을 사용하는 전통적인 LR 파싱 방식의 한계를 극복하도록 만들어진 LR 파싱 기법의 하나로서, LR 기법에 여러 가지 매커니즘을 통합하여 자연어 파싱에 응용하는 작업의 토대가 되어 왔다. 본 논문에서는 기존의 확률적 LR 파싱 기법이 가지고 있는 문제를 개선한 조건부 연산 모델(Conditional Action Model)을 제안한다. 기존의 확률적 LR 파싱 기법은 그래프 구조 스택의 복잡성으로 인해 상대적으로 제한된 문맥 정보만을 사용하여 왔다. 제안된 모델은 부분 생성 파스의 표현을 위하여 표층 구문 타입(Surface Phrasal Type)을 사용하여 그래프 구조 스택에 들어 있는 구문 구조를 기술함으로써 좀 더 세분된 구조적 선호도를 파서에 반영시킬 수 있다. 실험 결과, 어휘를 고려하지 않고 학습한 조건부 연산 모델로 구현된 본 GLR 파서는 기존의 방식보다 약 6-7%의 정확도 향상을 보였으며, 본 모델을 통해 풍부한 스택 정보를 확률적 LR 파서의 구조적 중의성 해결에 효과적으로 사용할 수 있음을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2005-2010
• /
• 2004

As robots become more prevalent in human daily life, situations requiring interaction between humans and robots will occur more frequently. Therefore, human-robot interaction (HRI) is becoming increasingly important. Although robotics researchers have made many technical developments in their field, intuitive and easy ways for most common users to interact with robots are still lacking. This paper introduces a new approach to enhance human-robot interaction using a semantic symbol language and proposes a method to acquire the intentions of robot users. In the proposed approach, each semantic symbol represents knowledge about either the environment or an action that a robot can perform. Users'intentions are expressed by symbolized multimodal information. To interpret a users'command, a probabilistic approach is used, which is appropriate for interpreting a freestyle user expression or insufficient input information. Therefore, a first-order Markov model is constructed as a probabilistic model, and a questionnaire is conducted to obtain state transition probabilities for this Markov model. Finally, we evaluated our model to show how well it interprets users'commands.

• Smart Structures and Systems
• /
• 제21권5호
• /
• pp.601-609
• /
• 2018

The estimated probabilistic model of wind data based on the conventional approach may have high discrepancy compared with the true distribution because of the uncertainty caused by the instrument error and limited monitoring data. A sequential quadratic programming (SQP) algorithm-based finite mixture modeling method has been developed in the companion paper and is conducted to formulate the joint probability density function (PDF) of wind speed and direction using the wind monitoring data of the investigated bridge. The established bivariate model of wind speed and direction only represents the features of available wind monitoring data. To characterize the stochastic properties of the wind parameters with the subsequent wind monitoring data, in this study, Bayesian inference approach considering the uncertainty is proposed to update the wind parameters in the bivariate probabilistic model. The slice sampling algorithm of Markov chain Monte Carlo (MCMC) method is applied to establish the multi-dimensional and complex posterior distribution which is analytically intractable. The numerical simulation examples for univariate and bivariate models are carried out to verify the effectiveness of the proposed method. In addition, the proposed Bayesian inference approach is used to update and optimize the parameters in the bivariate model using the wind monitoring data from the investigated bridge. The results indicate that the proposed Bayesian inference approach is feasible and can be employed to predict the bivariate distribution of wind speed and direction with limited monitoring data.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2008년도 추계학술대회
• /
• pp.90-93
• /
• 2008

In natural language, it is common that repetitive constituents in an expression are to be left out and it is necessary to figure out the constituents omitted at analyzing the meaning of the sentence. This paper is on recognition of boundaries of parallel noun phrases by figuring out constituents omitted. Recognition of parallel noun phrases can greatly reduce complexity at the phase of sentence parsing. Moreover, in natural language information retrieval, recognition of noun with modifiers can play an important role in making indexes. We propose an unsupervised probabilistic model that identifies parallel cores as well as boundaries of parallel noun phrases conjoined by a conjunctive particle. It is based on the idea of swapping constituents, utilizing symmetry (two or more identical constituents are repeated) and reversibility (the order of constituents is changeable) in parallel structure. Semantic features of the modifiers around parallel noun phrase, are also used the probabilistic swapping model. The model is language-independent and in this paper presented on parallel noun phrases in Korean language. Experiment shows that our probabilistic model outperforms symmetry-based model and supervised machine learning based approaches.

• 한국건설관리학회논문집
• /
• 제8권5호
• /
• pp.191-200
• /
• 2007

This paper introduces a tool for predicting potential cost overrun during project execution and for quantifying the uncertainty on the expected project cost, which is occasionally changed by the unknown effects resulted from project's complications and unforeseen environments. The model proposed in this stuff is useful in diagnosing cost performance as a project progresses and in monitoring the changes of the uncertainty as indicators for a warning signal. This model is intended for the use by project managers who forecast the change of the uncertainty and its magnitude. The paper presents a mathematical approach for modifying the costs of incomplete work packages and project cost, and quantifying reduced uncertainties at a consistent confidence level as actual cost information of an ongoing project is obtained. Furthermore, this approach addresses the effects of actual informed data of completed work packages on the re-estimates of incomplete work packages and describes the impacts on the variation of the uncertainty for the expected project cost incorporating Multivariate Probabilistic Analysis (MPA) and Bayes' Theorem. For the illustration purpose, the Introduced model has employed an example construction project. The results are analyzed to demonstrate the use of the model and illustrate its capabilities.