• Journal of the Korean Geotechnical Society
• /
• v.26 no.8
• /
• pp.59-66
• /
• 2010

In this study, an applicability by using the FEM was investigated for the prediction of both the depth of improvement and the vibration effect when dynamic compaction method is applied. The region was modelled by the field conditions applying dynamic compaction method and the rigid body force was applied to the dynamic load model. Predicted depth of improvement calculated by the vertical peak particle acceleration was compared and analyzed with an existing empirical equation, and the effect of groundwave by deducing the peak particle velocity from vibration sources was compared and analyzed with the results of another existing empirical equation. The results showed that the prediction of the depth of improvement has similar tendency to practice, and the vibration effect has some differences in a particular section from existing equation, but it could predict the safety distance to some degree. The analyzed results are expected to be basic data for the development of reliability of dynamic compaction design with existing empirical method.

• Journal of Broadcast Engineering
• /
• v.27 no.5
• /
• pp.694-702
• /
• 2022

This paper is the UX-based technology strategy research which is a solution to how conversational AI can be ethically evolved in the Metaverse environment. Since conversational AI influences people's on-offline decision-making factors through interaction with people, the Metaverse AI ethics must be reflected. In the machine learning process of conversational AI, cultural codes along with user's personal experience data must be included and considered to reduce the error value of user experience. Through this, the super-personalized Metaverse service can evolve ethically with social values. With above hypothesis as a result of the study, a conceptual model of a forward-looking perspective was developed and proposed by adding user experience data to the machine learning (ML) process for context-based interactive AI in the Metaverse service environment.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.167-175
• /
• 2018

By conducting multiple regression analysis, we analyzed the major independent factors affecting user convenience and emotional factors, and identified the important functional elements in the design of the VR device, so that the functional elements to be developed can be grasped in advance. As a result of the study, satisfaction of handling of VR bicycle and satisfaction of speed control by paddling were considered as the most important technical factors as independent factors which have the greatest influence on user convenience and emotional factor among technical satisfaction. Also, it is possible to increase the probabilities of successful design by setting a model that predicts user convenience and the emotional part from the technical factors.

• Journal of the Korean Geotechnical Society
• /
• v.20 no.8
• /
• pp.77-87
• /
• 2004

In this paper a back-propagation neural network model is developed to estimate the preconsolidation pressure of Korean soft soils based on 176 oedometer tests and 63 piezocone test results, which were compiled from 11 sites - western and southern parts of Korea. Only 147 data were used for the training of the neural network and 29 data, which were not used during the training phase, were used for the verification of trained network. Empirical and theoretical models were compared with the developed neural network model. A simple 4-4-9-1 multi-layered neural network has been developed. The cone tip resistance $q_T$ penetration pore pressure $u_2$, total overburden pressure $\sigma_{vo}$ and effective overburden pressure $\sigma'_{vo}$ were selected as input variables. The developed neural network model was validated by comparing the prediction results of the proposed neural network model for the new data which were not used for the training of the model with the measured preconsolidation pressures. It can also predict more precise and reliable preconsolidation pressures than the analytical and empirical model. Furthermore, it can be carefully concluded that neural network model can be used as a generalized model for prediction of preconsolidation pressure throughout Korea since developed model shows good performance for the new data which were not used in both training and testing data.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.50-54
• /
• 2007

소프트웨어 개발을 위한 모델링 방법 중 대표적인 것으로 UML을 이용한 방법이 있으며, 제품계열공학에서 소프트웨어의 재사용을 위한 모델링 방법으로 feature 모델링에 관한 연구가 진행 되고 있다. feature 모델링 방법은 잘 정의된 개발 기법을 제공하여 활용되고 있으나 다소 범용 적이지 않다. 또한 그 구조물이 UML과 상이하여 UML사용자가 feature 모델을 재사용하는 데는 어려움을 가지고 있고, feature 모델에서 class모델로의 변환을 제시한 기존연구는 도메인 전문가에 의해 경험적으로 모델링을 하기 때문에 모호성과 이해의 오류, 그리고 잘못된 해석 등의 문제가 발생 된다. 그리고, feature 모델과 class모델의 모든 요소를 매핑하여 변환하지 않는다는 점에서 완전하지 못하다. 따라서 본 논문에서는 Ontology를 이용하여 의미 기반의 명확한 명세를 통한 feature모델의 class 모델로의 변환기법을 제시하고, 이를 위해 feature 모델과 class 모델의 구조물의 요소를 정의하고 이를 기반으로 feature 모델과 OWL, 그리고 class 모델 속성간의 매핑 규칙을 제시하고, 본 논문에서 제시한 변환 프로세스를 이용하여 사례연구를 하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06c
• /
• pp.139-141
• /
• 2006

제품계열공학에서 feature diagram(FD)은 개발자의 직관이나 도메인 전문가의 경험에 근거하여 작성되어, feature간의 공통성 및 가변성분석 기준이 불명확하며 비정형적인 feature의 공통성 및 가변성 분석으로 인한 stakeholder의 공통된 이해가 부족한 문제점을 내포하고 있다. 따라서, 본 논문에서는 이를 해결하기 위하여 공통된 feature의 이해를 위해 feature 속성리스트에 기반한 메타 feature모델과 feature간의 의미유사성관계를 이용한 온톨로지를 적용한 공통성 및 가변성 분석모델을 제안한다.

• Computational Structural Engineering
• /
• v.11 no.4
• /
• pp.219-227
• /
• 1998

실제 구조물에 있어 확률, 통계 및 이론으로 구해진 랜덤성을 갖는 객관적 불확실성뿐만 아니라 설계자의 경험이나 공학적 판단에 의해 주관적으로 평가되는 인간오차나 시공중의 과오 또는 구조설계에 미치는 사회적, 정치적 및 경제적 요청 등의 퍼지성을 갖는 주관적 불확실성이 존재하기 때문에 현실적으로 랜덤성과 퍼지성을 동시에 고려한 실뢰성평가 즉, 안전성평가에 대한 퍼지이론의 도입이 필수 불가결하다. 따라서 본 연구에서는 기존 구조물의 객관적·주관적 불확실성을 동시에 고려한 신뢰성해석방법으로 베이즈의 의사결정이론에 퍼지이론을 병합한 퍼지-베이즈 신뢰성해석 알고리즘을 개발하여 건축구조물의 신뢰성평가 및 안전성평가에 적용하여 분석하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.269-272
• /
• 2006

현재 제품계열 공학에서 feature 중심의 공통성 및 가변성 분석을 통한 재사용성에 대한 연구가 활발히 이루어지고 있다. 지금까지는 도메인 전문가의 직관 및 경험에 의해 feature가 분석되어 그 개념의 불명확함으로 재사용 측면에서 제한점을 내포하고 있다. 본 논문에서는 개별 feature 속성 List 작성을 통해 feature간의 의미관계를 중심으로 한 Pattern 분석 방법을 제시하고, 의미 유사성 관계를 적용한 feature 온톨로지 그래프를 이용하여 S/W 제품계열 도메인 공학에서 사용자와 개발자간의 동일한 해석이 가능하고 재사용성을 위한 명시적 feature를 분석 및 추출하는 모델을 제안한다.

• Korean Journal of Remote Sensing
• /
• v.22 no.2
• /
• pp.87-99
• /
• 2006

The Median Resolution Sensors (MRSs) for land observation such as Landsat-ETM+ and SPOT-HRV are more effective than Ocean Color Sensors (OCSs) for studying of detailed ecological and biogeochemical components of the coastal waters. In this study, we developed suspended sediment algorithm for Landsat TM/ETM+ by considering the spectral response curve of each band. To estimate suspended sediment concentration (SS) from satellite image data, there are two difference types of algorithms, that are derived for enhancing the accuracy of SS from Landsat imagery. Both empirical and remote sensing reflectance model (hereafter referred to as $R_{rs}$ model) are used here. This study tried to compare two algorithm, and verified using in situ SS data. It was found that the empirical SS algorithm using band 2 produced the best result. $R_{rs}$ model-based SS algorithm estimated higher values than empirical SS algorithm. In this study we used $R_{rs}$ model developed by Ahn (2000) focused on the Mediterranean coastal area. That's owing to the difference of oceanic characteristics between Mediterranean and Korean coastal area. In the future we will improve that $R_{rs}$ model for the Korean coastal area, then the result will be advanced.