• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.32 no.3
• /
• pp.191-197
• /
• 2019

As the shipbuilding and offshore plant industries grow larger and more complex, their maintenance and inspection systems become more important. Recently, maintenance and inspection systems based on augmented reality have been attracting much attention for improving worker's understanding of work and efficiency, but it is often difficult to work with because accurate matching between the augmented model and reality information is not. To solve this problem, marker based AR technology is used to attach a specific image to the model. However, the markers get damaged due to the characteristic of the shipbuilding and offshore plant industry, and the camera needs to be able to detect the entire marker clearly, and thus requires sufficient space to exist between the operator. In order to overcome the limitations of the existing AR system, in this study, a markerless AR was adopted to accurately recognize the actual model of the pipe system that occupies the most processes in the shipbuilding and offshore plant industries. The matching methodology. Through this system, it is expected that the twist phenomenon of the augmented model according to the attitude of the real worker and the limited environment can be improved.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.3
• /
• pp.37-51
• /
• 2023

Spatial information is essential for interpreting urban phenomena. Methodologies for spatializing urban information, especially when it lacks location details, have been consistently developed. Typical methods include Geocoding using structured address information or place names, spatial integration with existing geospatial data, and manual tasks utilizing reference data. However, a vast number of documents produced by administrative agencies have not been deeply dealt with due to their unstructured nature, even when there's demand for spatialization. This research utilizes the natural language processing model BERT to spatialize public documents related to urban planning. It focuses on extracting sentence elements containing addresses from documents and converting them into structured data. The study used 18 years of urban planning public announcement documents as training data to train the BERT model and enhanced its performance by manually adjusting its hyperparameters. After training, the test results showed accuracy rates of 96.6% for classifying urban planning facilities, 98.5% for address recognition, and 93.1% for address cleaning. When mapping the result data on GIS, it was possible to effectively display the change history related to specific urban planning facilities. This research provides a deep understanding of the spatial context of urban planning documents, and it is hoped that through this, stakeholders can make more effective decisions.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.151-168
• /
• 2017

Current research aimed to demonstrate a way to enhance the aesthetic experience of the general public while appreciating contemporary art via online platform. Contemporary art is highly complicated and are avoided by the general public. Meanwhile, previous research confirmed that external information can lead to better aesthetic experience and appreciation of the artwork. Therefore, current research hypothesized that provision of explicit information may enhance the appreciation of contemporary artworks and aimed to demonstrate which phase of the cognitive process from Leder et al. (2004) profits from the aid of written information. Experimental environment reproduced online curating platform to reflect the current trend on exhibition. In experiment 1, subjects were presented with written information and reported how well they understood the artwork, and their willingness to visit the artwork in real life. Results revealed that written information had a positive effect on overall appreciation. Further analysis discovered a full mediation between information comprehension, artwork comprehension, and willingness to visit. In experiment 2, ARS questions and an interactive interface were added. Results indicated that information enhanced comprehension and intention to visit the artwork. Expertise, self-reference, and artistic quality which belong to later stages of Leder et al. (2004) model, acquired higher scores on information conditions. In sum, the current research illustrated clear effects of explicit information in inducing better aesthetic experience and cognitive process of contemporary artworks in online environment.

• Journal of The Korean Association For Science Education
• /
• v.36 no.6
• /
• pp.815-833
• /
• 2016

This study investigated children's (grade 3 to 9) responses to assessment items on energy as a cross-cutting concept in order to get basic information for a learning progression. The assessment consisted of 8 ordered multiple-choice items at the contexts of electric circuit, mechanical energy of falling objects, phase change of matter, dissolution, biological phenomena of a lizard, food chain, radiative equilibrium between Sun and Earth, and the system of water cycling. Children's responses to each item were analyzed with using cross-tabulations in terms of grades and item option levels and Wright map and Differential item functioning based on Rasch modeled item response analysis. The results offered empirical evidence of children's development of understanding energy from relation between energy and its phenomena, types of energy, transfer and conversion of energy, towards conservation and equilibrium of energy for all of eight contexts. Children of each grade did not fully understand energy conservation. As grade goes up, their understandings of energy transfer and conversion were differentiated across the contexts and topics of energy. According to Rasch analysis, children had easier understanding of energy on dissolution and poorer understanding of energy on water cycling than that on other contexts. It was discussed and suggested that the results of this study help us organize science topics with regard to energy when developing new national science curriculum.

• Journal of Practical Engineering Education
• /
• v.15 no.1
• /
• pp.23-29
• /
• 2023

For given the importance of elementary school students developing the ability to solve problems using artificial intelligence (AI), problem-solving abilities should be developed using AI along with education to develop problem-solving abilities. Such students need a form that allows them to understand the concepts and principles of AI and to be easily educated in a fun way to understand basic understanding of how AI works. To this end, this study planned an 8-hour AI convergence program and operated based on self-driving cars, demonstrating that it was effective in improving elementary school students' problem-solving abilities, creativity, and AI understanding. As a result of operating the camp, students' understanding of AI was 3.56 (standard deviation 0.85), 4.00 (standard deviation 0.71), and t-value was -5.412 (p<0.001), indicating statistically improved understanding of AI, and high satisfaction and interest of students. In the future, it will be necessary to develop an educational program that allows elementary school students to devise their own ideas and create products to which AI models can be applied.

• Fire Science and Engineering
• /
• v.18 no.1
• /
• pp.42-48
• /
• 2004

The deterministic modeling techniques like Zone model and Field model are mainly used for thermal distribution and smoke flow at fire case in multi use facilities. While Zone model analyse fire simulation by dividing spaces by 2 section, the Field model dividing many cells. However, the difficultly follows to prove efficiency between the two models when it applys. Therefore new modeling development is required which in closes to real situation by verify number algorithm and related data for fire modeling. The paper analyses the efficiency of two different fire modeling at interior spaces of multiplex cinema theater. It is found that the zone model for average distribution and the field model for detail space phenomenon are relevant to apply. Also, Filed model is useful to the result that fire analysis and position of detector and review for smoke control system.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2022

Recent deep learning-based research shows excellent performance in most natural language processing (NLP) fields with pre-trained language models. In particular, the auto-encoder-based language model proves its excellent performance and usefulness in various fields of Korean language understanding. However, the decoder-based Korean generative model even suffers from generating simple sentences. Also, there is few detailed research and data for the field of conversation where generative models are most commonly utilized. Therefore, this paper constructs multi-turn dialogue data for a Korean generative model. In addition, we compare and analyze the performance by improving the dialogue ability of the generative model through transfer learning. In addition, we propose a method of supplementing the insufficient dialogue generation ability of the model by extracting recommended response candidates from external knowledge information through a retrival model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.254-254
• /
• 2021

기후변화로 인한 자연재해는 해마다 크게 증가하고있으며, 홍수 및 가뭄의 강도와 빈도 증가, 지구온난화로 인한 하천 건천화 등 많은 문제들이 대두되고 있다. 특히, 물 순환과정의 핵심요소로 설명되는 유출량의 변동은 용수 공급과 홍수 대응 및 관리, 하천생태계 유지를 위한 환경에 영향을 미치고 있다. 따라서, 갈수량, 풍수량 등을 산정하여 하천별 유황특성을 결정하는 방법을 사용하고 있으나, 이와같은 지표는 계측자료가 과소한 경우 하천의 유황특성을 세부적으로 이해하고 정량적으로 제시하는데에 한계가있다. 따라서, 미계측 유역에서 Soil and Water Assessment Tool (SWAT)과 같은 수리해석모델이 광범위하게 이용되고있으며, SWAT 모델은 유역의 수치표고모형, 토양 특성, 토지이용 현황, 기상 현황, 유역의 매개변수 등을 반영하여 모델이 구동되고 있다. 하지만, 광범위하게 이용되고 적용성이 입증된 모델임에도 불구하고 입력자료의 불확실성 및 조사되지 않은 영농활동 등으로 인해 결과에 불확실성이 내포되어있으며, 불확실성을 줄이기 위해 실측된 하천의 유량 자료를 이용하여 검정 및 보정작업을 거치고 있다. 모델의 보정 방법으로는 SWAT-CUP과 같은 프로그램 이용되고 있지만, 모델에서 이용되는 매개변수로는 보정할수 있는 범위가 한정적이기 때문에 모델의 정확성을 높이는데에 한계가 있다. 따라서, 본 연구에서는 선암천 유역을 대상으로 모델의 매개변수를 보정하지 않고도 머신러닝 기법을 이용하여 모델의 결과를 향상시켰다. 보정 결과, 유량의 경우 R²가 0.42에서 0.91으로 향상되었으며, 특히 고유량 구간에서의 정확성이 매우 향상되었다. 본 연구에서 평가된 SWAT+머신러닝 결합 모형은 향후 모델 구동에 필요한 입력자료가 부족한 경우와 빠른 검정 및 보정 작업이 필요할 경우 활용될수 있을것으로 판단된다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.3-6
• /
• 2007

사람들이 어떠한 행동을 할 때는 특정 의도를 가지고 있기 때문에 상황에 맞는 적합한 서비스를 제공하기 위해서는 사용자가 현재 하고 있는 행동에 대한 의도를 파악해야한다. 이를 위해 의도와 행동사이의 연관성을 이용하여 사용자의 의도에 따른 행동의 모델을 만든다. 일상생활에서 사람들이 하는 행동은 작은 단위 행동들의 연속(sequence)으로 이루어지므로, 사용자의 단위행동의 순서를 분석한다면 의도에 따른 행동 모델을 만들기가 용이해진다. 하지만, 이런 단위 행동 분석 방법의 문제점은 같은 의도를 가진 행동이 완벽하게 동일한 단위 행동의 순서로 일어나지는 않는다는 점이다. 시스템은 동일한 동작 순서로 일어나지 않는 행동들을 서로 다른 의도를 가진 행동으로 이해하게 된다. 따라서 이 문제점을 해결할 수 있는 사용자 의도 파악 기법이 필요하다. 본 논문에서는 과거의 사용자의 행동 정보를 기반으로 행동들의 유사성을 판별하였고, 그 결과를 이용하여 행동의 의도를 파악하는 방법을 사용한다. 이를 위해, 과거 사용자가 한 행동들을 단위 시간 별로 나누어 단위 행동의 순서로 만들고, 이를 K-평균 군집화 방법(K-means)으로 군집들의 순서로 나타내었다. 이 변경된 사용자 행동 정보를 사용하여 은닉 마코프 모델을 학습 시키고, 이렇게 만들어진 은닉 마코프 모델은 현재 사용자가 행한 행동이 어떤 행동인지를 예측하여 사용자의 의도를 파악한다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.376-380
• /
• 2009

본 논문에서는 하천정비에 있어 구상, 계획, 설계, 사업, 운용 유지관리의 각 단계에 따른 대응에서 의사 합의 형성의 목적과 논의의 대상을 정하고, 객관적이며 합리적인 합의 형성 방법을 선택하는 모델로서 "안전", "이용", "환경" 이라고 하는 3요소 모델을 제안하고자 한다. 종래의 제도로써 계획의 절차, 환경평가, 행정소송, 의회제도에 새로운 대응으로써 공공사업의 구상 단계에 있어서 주민 참가 절차 등을 고려하고, 다양한 이해관계자의 의향을 조정하고, 원할한 합의 형성을 추진하면서, 대상 사업 등을 사회적으로 바람직하게 끌어가기 위한 합의 형성에 관한 종합적인 producer의 필요성을 논한다. 끝으로 이 모델에 의거한 4대강 정비사업에 대한 예비 전문가 그룹의 의사결정의 관점을 합의 형성 이론과 테크닉으로써 분석결과, 4대강 정비사업에 대하여는 3요소간의 우선순위가 "안전", "환경", "이용" 의 순으로 나타나고 있어, "이용" 에 우선순위를 둔 경부대운하 사업에 대한 시민들의 우려를 뒷받침하고 있다. 또, 전통적인 유역하천에 대하여는 "환경" 이 큰 비중을 차지하고 있어 시민의 환경에 대한 높은 관심을 표현하고 있다. 끝으로 이러한 새로운 패러다임을 파악하기 위한 3요소 모델의 의사합의 형성내용을 하천정비사업이나 관리에 적용하여 실현시키기 위하여 하천정비사업에도 "유니버설디자인" 수법의 도입을 제언한다.