• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2002.03b
• /
• pp.127-141
• /
• 2002

GIS환경에서 도시모형(urban model)의 적용을 목적으로 사회·경제적 데이터(socio-economic data)를 활용하는 과정은 도시현상이 갖는 복잡성과 변동성으로 인해 하나의 특정시간에서의 상황을 그대로 저장한 형태인 스냅샷 모형(snapshot model)만으로는 효율적인 공간분석의 실행이 불가능하다. 또한 도시모형을 적용하는 과정에서 GIS의 대상이 되는 공간, 속성, 시간의 정의는 분석목적에 따라 다르게 정의되어질 수 있으며 이에 따라 상이한 결과가 도출될 수 있다. 본 연구는 30년 간의 부산시 인구분포의 동적 변화과정 관측을 위해 시간개념을 결합한 Temporal GIS를 구축하고 이를 활용하여 인구밀도모형 및 접근성모형을 적용하는 과정을 통해 보다 효율적이고 다양한 결과를 제시할 수 있는 GIS 활용방안을 제시하고자 하였다. 흔히 공간현상의 계량화와 통계적 기법의 적용을 위한 데이터 처리과정은 많은 오차와 오류를 유발할 수 있다. 이러한 문제의 해결을 위해서는 우선적으로 분석목적에 맞는 데이터의 정의(Data Definition), 적용하고자 하는 모형(Model)의 유용성 검증, 적절한 분석단위의 설정, 결과해석의 객관적 접근 등이 요구된다. 이와 더불어 변동성 파악을 위한 시계열 자료의 효율적 처리를 위한 방법론이 마련되어져야 한다. 즉, GIS환경에서의 도시모형의 적용에 따른 효율성과 효과성의 극대화를 위해서는 분석목적에 맞는 데이터모델의 설정과 공간DB의 구축방법이 이루어져야 하며 분석가능한 데이터의 유형에 대한 충분한 고려와 적용과정에서 분석결과에 중대한 영향을 미칠 수 있는 요소들을 미리 검증하여 결정하는 순환적 의사결정과정이 필요하다., 표준패턴을 음표와 비음표의 두개의 그룹으로 나누어 인식함으로써 DP 매칭의 처리 속도를 개선시켰고, 국소적인 변형이 있는 패턴과 특징의 수가 다른 패턴의 경우에도 좋은 인식률을 얻었다.r interferon alfa concentrated solution can be established according to the monograph of EP suggesting the revision of Minimum requirements for biological productss of e-procurement, e-placement, e-payment are also investigated.. monocytogenes, E. coli 및 S. enteritidis에 대한 키토산의 최소저해농도는 각각 0.1461 mg/mL, 0.2419 mg/mL, 0.0980 mg/mL 및 0.0490 mg/mL로 측정되었다. 또한 2%(v/v) 초산 자체의 최소저해농도를 측정한 결과, B. cereus, L. mosocytogenes, E. eoli에 대해서는 control과 비교시 유의적인 항균효과는 나타나지 않았다. 반면에 S. enteritidis의 경우는 배양시간 4시간까지는 항균활성을 나타내었지만, 8시간 이후부터는 S. enteritidis의 성장이 control 보다 높아져 배양시간 20시간에서는 control 보다 약 2배 이상 균주의 성장을 촉진시켰다.차에 따른 개별화 학습을 가능하게 할 뿐만 아니라 능동적인 참여를 유도하여 학습효율을 높일 수 있을 것으로 기대된다.향은 패션마케팅의 정의와 적용범위를 축소시킬 수 있는 위험을 내재한 것으로 보여진다. 그런가 하면, 많이 다루어진 주제라

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.1
• /
• pp.141-148
• /
• 2018

In recent years, there has been a movement to create a learning city where people can learn and enjoy what they want whenever, wherever, and whenever, so that the self-realization of individuals and the quality of life can be enhanced to improve the competitiveness of the city as a whole, It is becoming active. Many developed countries in the world are supporting projects to build learning cities by utilizing schools and public facilities, thereby providing local residents with opportunities for self-growth and solving community problems. In Korea, too, there are various programs using idle facilities. However, there is a lack of education programs for local residents and learning programs by partnership with local communities. It is when spatial and software strategies are needed to build a successful learning city. Therefore, we want to systematically organize the spatial data of the facilities that can be learned, analyze the current problems, and explore various ways to utilize them. We also analyze the programs that residents need to implement real and efficient learning cities.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.622-624
• /
• 2021

현재 BERT와 같은 대용량의 코퍼스로부터 학습된 사전 학습 언어 모델을 자연어 응용 태스크에 적용하기 위해 일반적으로 널리 사용되는 방법은 Fine-tuning으로 각 응용 태스크에 적용 시 모델의 모든 파라미터를 조정하기 때문에 모든 파라미터를 조정하는데 필요한 시간적 비용과 함께 업데이트된 파라미터를 저장하기 위한 별도의 저장공간이 요구된다. 언어 모델이 커지면 커질수록 저장 공간의 비용이 증대됨에 따라 이러한 언어모델을 효율적으로 튜닝 할 수 있는 방법들이 연구되었다. 본 연구에서는 문장의 입력 임베딩에 연속적 태스크 특화 벡터인 prefix를 추가하여 해당 prefix와 관련된 파라미터만 튜닝하는 prefix-tuning을 한국어 네이버 감성 분석 데이터 셋에 적용 후 실험결과를 보인다.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.39-49
• /
• 2021

Recently, large and diverse weather data are being collected by sensors from various sources. Efforts to predict the concentration of fine dust through machine learning are being made everywhere, and this study intends to compare PM10 and PM2.5 prediction models using data from 840 outdoor air meters installed throughout the city. Information can be provided in real time by predicting the concentration of fine dust after 5 minutes, and can be the basis for model development after 10 minutes, 30 minutes, and 1 hour. Data preprocessing was performed, such as noise removal and missing value replacement, and a derived variable that considers temporal and spatial variables was created. The parameters of the model were selected through the response surface method. XGBoost, Random Forest, and Deep Learning (Multilayer Perceptron) are used as predictive models to check the difference between fine dust concentration and predicted values, and to compare the performance between models.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.4
• /
• pp.341-353
• /
• 2022

Pipelines are buried in urban area, and the position (depth and orientation) of buried pipeline should be clearly identified before ground excavation. Although various geophysical methods can be used to detect the buried pipeline, it is not easy to identify the exact information of pipeline due to heterogeneous ground condition. Among various non-destructive geo-exploration methods, ground penetration radar (GPR) can explore the ground subsurface rapidly with relatively low cost compared to other exploration methods. However, the exploration data obtained from GPR requires considerable experiences because interpretation is not intuitive. Recently, researches on automated detection technology for GPR data using deep learning have been conducted. However, the lack of GPR data which is essential for training makes it difficult to build up the reliable detection model. To overcome this problem, we conducted a preliminary study to improve the performance of the detection model using finite difference time domain (FDTD)-based numerical analysis. Firstly, numerical analysis was performed with homogeneous soil media having single permittivity. In case of heterogeneous ground, numerical analysis was performed considering the ground heterogeneity using fractal technique. Secondly, deep learning was carried out using convolutional neural network. Detection Model-A is trained with data set obtained from homogeneous ground. And, detection Model-B is trained with data set obtained from homogeneous ground and heterogeneous ground. As a result, it is found that the detection Model-B which is trained including heterogeneous ground shows better performance than detection Model-A. It indicates the ground heterogeneity should be considered to increase the performance of automated detection model for GPR exploration.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.22 no.3
• /
• pp.239-248
• /
• 2020

Exact rock classification helps suitable support patterns to be installed. Face mapping is usually conducted to classify the rock mass using RMR (Rock Mass Ration) or Q values. There have been several attempts to predict the grade of rock mass using mechanical data of jumbo drills or probe drills and photographs of excavation surfaces by using deep learning. However, they took long time, or had a limitation that it is impossible to grasp the rock grade in ahead of the tunnel surface. In this study, a method to predict the Q value ahead of excavation surface is developed using recurrent neural network (RNN) technique and it is compared with the Q values from face mapping for verification. Among Q values from over 4,600 tunnel faces, 70% of data was used for learning, and the rests were used for verification. Repeated learnings were performed in different number of learning and number of previous excavation surfaces utilized for learning. The coincidence between the predicted and actual Q values was compared with the root mean square error (RMSE). RMSE value from 600 times repeated learning with 2 prior excavation faces gives a lowest values. The results from this study can vary with the input data sets, the results can help to understand how the past ground conditions affect the future ground conditions and to predict the Q value ahead of the tunnel excavation face.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.3
• /
• pp.45-55
• /
• 2022

BIM models allow building spaces to be instantiated and recognized as unique objects independently of model elements. These instantiated spaces provide the required semantics that can be leveraged for building code checking, energy analysis, and evacuation route analysis. However, theses spaces or rooms need to be designated manually, which in practice, lead to errors and omissions. Thus, most BIM models today does not guarantee the semantic integrity of space designations, limiting their potential applicability. Recent studies have explored ways to automate space allocation in BIM models using artificial intelligence algorithms, but they are limited in their scope and relatively low classification accuracy. This study explored the use of Graph Convolutional Networks, an algorithm exclusively tailored for graph data structures. The goal was to utilize not only geometry information but also the semantic relational data between spaces and elements in the BIM model. Results of the study confirmed that the accuracy was improved by about 8% compared to algorithms that only used geometric distinctions of the individual spaces.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.279-284
• /
• 2022

As a study of the blended learning method on design education through the blended learning method, I would like to propose that more advanced learner-led customized design education is possible. Understanding in face-to-face classes and advantages in non-face-to-face classes can be supplemented in an appropriate way in remote classes. Advanced artificial intelligence and big data technology can provide personalized and subdivided learning materials and effective learning methods tailored to learners' levels and interests based on quantified data in design classes. In this paper, it was proposed to maximize the efficiency of the class by applying a method that exceeds the limitations of time and space through the proposal of the A La Carte model (A La Carte). It is a remote class that can be heard anytime, anywhere, and it is also possible to bridge the educational quality and educational gap provided to students living in underprivileged areas. As the goal of fostering creative convergence-type future talents, it is changing with a rapid technological development speed. It is necessary to adapt to the change in learning methods in line with this. An analysis of the infographic virtual space design and construction process through the A La Carte model (A La Carte) proposal was presented. Rather than simply acquiring knowledge, it is expected that knowledge can be sorted, distinguished, learned, and easily reborn with its own knowledge.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.772-775
• /
• 2002

초고속 인터넷의 확산으로 인해 교육시스템이 서서히 바뀌어가고 있다. 칠판과 책, 노트, 펜을 이용한 수업이 빔 프로젝트와 컴퓨터를 통한 수업으로 대체되어가고 있고, 나아가 인터넷을 이용한 사이버 교육시스템이 점차 확산되고 있다. 사이버 교육을 통해 공간의 제약성을 무너뜨리고, 교통비와 이동 시간 등을 절약할 수 있을 뿐만 아니라 다운로드한 강의 자료를 Off-Line 상에서 반복 학습 할 수 있다는 커다란 장점이 있다. 이런 사이버 원격 교육에는 크게 3가지의 데이터, 즉 음성, 화상 및 판서 데이터가 있는데, 본 논문에서는 이 데이터들을 어떻게 하여 효율적으로 데이터를 관리할 수 있는 지, 그리고 강의 자료를 제작시 어떻게 하여 강의 제작 및 수정이 용이할지에 대해 그 구현 방안을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.413-415
• /
• 2022

Since human joints can be used as useful information for analyzing human behavior as a component of the human body, many studies have been conducted on human action recognition using joint information. However, it is a very complex problem to recognize human action that changes every moment using only each independent joint information. Therefore, an additional information extraction method to be used for learning and an algorithm that considers the current state based on the past state are needed. In this paper, we propose a human action recognition technique considering the positional relationship of connected joints and the change of the position of each joint over time. Using the pre-trained joint extraction model, position information of each joint is obtained, and bone information is extracted using the difference vector between the connected joints. In addition, a simplified neural network is constructed according to the two types of inputs, and spatio-temporal features are extracted by adding LSTM. As a result of the experiment using a dataset consisting of 9 behaviors, it was confirmed that when the action recognition accuracy was measured considering the temporal and spatial relationship features of each joint, it showed superior performance compared to the result using only single joint information.