• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.325-327
• /
• 2020

최근 비대면 원격강의의 비율이 증가하였지만 비대면 상황에서 원격으로 진행하는 강의로 인해 강의를 수강하는 학생들의 강의를 진행하는 교수와의 질문에 대한 즉각적인 상호작용과 피드백이 부족하고 교수 또한 비대면 상황에서 학생들과의 소통의 어려움으로 인해 질문에 대한 답변을 하는 것에 어려움 있다. 본 논문에서는 이러한 문제를 해결하기 위해 학생들에게 질문에 대한 즉각적인 답변을 해주고 교수에게는 질문-답변을 관리할 수 있는 인공지능 챗봇 웹 서비스를 제안한다. 웹 서비스는 강의를 수강하는 학생과 강의를 진행하는 교수로 나눠져 제공된다. 구현을 위해 Seq2Seq 모델을 활용하였고 질문-답변 데이터셋으로 학습을 하여 테스트 하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.6A
• /
• pp.765-778
• /
• 2008

Performance Profiles are essential to predict the performance variation over time for the bridge management system (BMS) based on risk management. In general, condition profiles based on experts opinion and/or visual inspection records have been used widely because obtaining profiles based on real performance is not easy. However, those condition profiles usually don't give a good consistency to the safety of bridges, causing practical problems for the effective bridge management. The accuracy of performance evaluation is directly related to the accuracy of BMS. The reliability of the evaluation is important to produce the optimal solution for distributing maintenance budget reasonably. However, conventional methods of bridge assessment are not suitable for a more sophisticated decision making procedure. In this study, a method to compute quantitative performance profiles has been proposed to overcome the limitations of those conventional models. In Bridge Management Systems, the main role of performance profiles is to compute and predict the performance of bridges subject to lifetime activities with uncertainty. Therefore, the computation time for obtaining an optimal maintenance scenario is closely related to the efficiency of the performance profile. In this study, the Response Surface Method (RSM) based on independent and important design variables is developed for the rapid computation. Steel box bridges have been investigated because the number of independent design variables can be reduced significantly due to the high dependency between design variables.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.325-338
• /
• 2022

This study was conducted to explore the acceptance behavior of undergraduate students toward telemedicine, which is temporarily allowed in the COVID-19. We applied social cognitive theory and technology acceptance model in order to reflect the convergence characteristics between medical service and digital technology of telemedicine. Based on these theoretical backgrounds, we investigated perception toward telemedicine and determinants of intention to accept telemedicine. To examine the research model and hypothesis, an online survey was conducted for college students who have not used telemedicine from September 8 to 10, 2021. A total of 184 data were collected, and multiple regression analysis was conducted using the SPSS 28.0 program. The results showed that health technology self-efficacy, usefulness and convenience benefits, social norm, and trust in telemedicine providers had positive effects on intention to accept telemedicine. This study is meaningful in that it selected undergraduate students, who are digital natives, as new targets for telemedicine, and presented the basic direction of strategies to target them.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1992.10a
• /
• pp.90-96
• /
• 1992

경계면 요소를 이용하여 철근콘크리트 구조물의 접촉면 문제를 유한 요소법으로 해석하는 기법에 대하여 연구한다. 본 연구에서는 경계면 요소의 수치해석의 이론과정을 전개하고, 실험 관찰된 부착 시험체에 적용하여 이형철근과 콘크리트 부착기구의 접촉면을 해석한다. 경계면은 특별한 연결요소를 이용하여 재현하며 Mohr-Coulomb의 마찰 이론을 응응한다. 해석의 주요점으로 하중상태에 따라 변화되는 경계면의 접촉상태, 즉 고정(stick), 미끄러짐(slide), 분리(separation)를 묘사하여 경계면 재료의 비선형 거동을 관찰한다. 부착모델의 해석결과는 실험실의 결과와 대체로 일치되며 따라서 철근콘크리트 접촉면의 응력해석을 위해 경계면 요소가 활용될 수 있음을 보여준다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.4 no.4
• /
• pp.37-51
• /
• 2000

이 연구는 지진 시 철근콘크리트 교각의 비탄성 거동 및 연성능력을 해석적으로 파악하는데 그 목적이 있다. 재료적 비선형성에 대해서는 균열 콘크리트에 대한 인장, 압축, 전단모델과 콘크리트 속에 있는 철근 모델을 조합하여 고려하였다. 이에 대한 콘크리트의 균열 모델로서의 분산균열모델을 사용하였다. 두께가 서로 다른 부재간의 접합부에 단면강성이 급변하기 때문에 생기는 국소적인 불연속변형을 고려하기 위한 경계면 요소를 도입하였다. 또한, 축방향철근의 유무 및 그 양 등에 따른 구속효과를 적절히 표현할 수 있는 해석 모델을 개발하였다. 본 연구에서는 철근콘크리트 교각의 비탄성 거동 및 연성 능력의 파악을 위해 제안한 해석기법을 신뢰성 있는 연구자의 실험결과와 비교하여 그 타당성을 검증하였다.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2010.04a
• /
• pp.488-491
• /
• 2010

본 논문에서는 돌풍응답경감제어 효과 검증을 위한 풍동시험에 사용될 유연날개에 대해 공탄성 모델, 조종면 작동기 모델, 돌풍 모델 등으로 구성되는 서보공탄성 모델링을 수행하였으며, 이에 대한 연속돌풍 응답해석을 수행하여 상용 Solver를 이용한 해석결과와 비교하여 구성된 서보공탄성 모델을 검증하였다. 또한, 유연날개의 돌풍응답을 경감하는 조종면 제어기를 설계하고, 이에 대한 수치 시뮬레이션을 수행하여 돌풍응답 경감효과를 검증하였다.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.2
• /
• pp.131-139
• /
• 2022

This study aimed to evaluate the effectiveness of deep convolutional neural networks (CNNs) for diagnosis of interproximal caries in pediatric intraoral radiographs. A total of 500 intraoral radiographic images of first and second primary molars were used for the study. A CNN model (Resnet 50) was applied for the detection of proximal caries. The diagnostic accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and area under ROC curve (AUC) were calculated on the test dataset. The diagnostic accuracy was 0.84, sensitivity was 0.74, and specificity was 0.94. The trained CNN algorithm achieved AUC of 0.86. The diagnostic CNN model for pediatric intraoral radiographs showed good performance with high accuracy. Deep learning can assist dentists in diagnosis of proximal caries lesions in pediatric intraoral radiographs.

• Tunnel and Underground Space
• /
• v.33 no.6
• /
• pp.508-518
• /
• 2023

This paper presents a new approach for the automatic mapping of discontinuities in a tunnel face based on its 3D digital model reconstructed by LiDAR scan or photogrammetry techniques. The main idea revolves around the identification of discontinuity areas in the 3D digital model of a tunnel face by segmenting its 2D projected images using a deep-learning semantic segmentation model called U-Net. The proposed deep learning model integrates various features including the projected RGB image, depth map image, and local surface properties-based images i.e., normal vector and curvature images to effectively segment areas of discontinuity in the images. Subsequently, the segmentation results are projected back onto the 3D model using depth maps and projection matrices to obtain an accurate representation of the location and extent of discontinuities within the 3D space. The performance of the segmentation model is evaluated by comparing the segmented results with their corresponding ground truths, which demonstrates the high accuracy of segmentation results with the intersection-over-union metric of approximately 0.8. Despite still being limited in training data, this method exhibits promising potential to address the limitations of conventional approaches, which only rely on normal vectors and unsupervised machine learning algorithms for grouping points in the 3D model into distinct sets of discontinuities.

• The Journal of Engineering Geology
• /
• v.27 no.1
• /
• pp.81-90
• /
• 2017

Preceding displacements in tunnel are difficult to predict since the measurements of displacements after excavation can not be performed immediately. In the present study, The longitudinal displacements which can be measured immediately after excavation are used to predict the crown settlements occurring before excavation only if fault is located at the tunnel crown. Three-dimensional finite element analysis was conducted using 28 numerical models with various fault attitudes to analyze the correlation between the longitudinal displacements on tunnel face and preceding crown settlements. The results, $L_{face}/C$ ratio show 2~12% in the drives with dip models and 2~13% in the drives against dip models individually. In addition, each model has a certain $L_{face}/C$ ratio. The result of the regression analysis show that the coefficient of determination is over 0.8 in most models. Therefore, crown settlements occurring before excavation can be predicted by analyzing the longitudinal displacements occurring on tunnel faces.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.6
• /
• pp.106-112
• /
• 2017

This paper presents a mathematical model derived from the upper-bound theorem of concrete plasticity to rationally evaluate the shear friction strength of concrete interfaces with a construction joint. The upper limit of the shear friction strength was formulated from the limit state of concrete crushing failure on the strut-and-tie action along the construction joints to avoid overestimating the shear transfer capacity of a transverse reinforcement with a high clamping force. The present model approach proposed that the cohesion and coefficient of friction of concrete can be set to be $0.27(f_{ck})^{0.65}$ and 0.95, respectively, for rough construction joints and $0.11(f_{ck})^{0.65}$ and 0.64, respectively, for smooth ones, where $f_{ck}$ is the compressive strength of concrete. From the comparisons with 155 data compiled from the available literature, the proposed model gave lower values of standard deviation and coefficient of variation of the ratios between predictions and experiments than AASHTO and fib 2010 equations, indicating that the proposed model has consistent trends with test results, unlike the significant underestimation results of such code equations in evaluating the shear friction strength.