• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.637-637
• /
• 2015

2009년 미국에서 처음으로 스마트워터그리드의 개념이 도입된 이후로 국내외 국가 기관뿐만 아니라 민간 기업에서도 스마트워터그리드에 대한 관심이 높아지고 있다. 현재 스마트워터그리드는 IBM의 진출을 시작으로 Veolia, Suez 등 다국적 물관리 기업들이 사업을 추진 중이다. 국내의 ICT기술과 수자원시스템의 융합을 통하여 용수 수요 공급량을 실시간으로 파악하고 관리하여 수자원의 지역적 시간적 격차를 해소하는 스마트워터그리드 연구가 국내에서도 진행 중이다. 물관리 시장 주도권을 확보하기 위해 글로벌 물기업간 경쟁이 심화되고 있으며, 개별플랫폼을 구축 활용하여 신규기업의 물산업 진출을 가로막고 있는 실정이다. 이러한 상황에서 국외 물산업 시장 진출을 위하여 통합플랫폼 개발 및 체계적인 데이터 구조 설계가 필요하며, 본 연구는 스마트워터그리드를 운영하기 위해 여러 곳에 분산되어 관리 운영되어지고 있는 수자원 및 물관리 데이터의 통합을 위한 체계적인 데이터베이스 구조설계에 대한 연구를 수행하였다. 이에 본 연구에서는 스마트워터그리드 도메인 내에 주력하고 있는 통합데이터베이스 구조를 외부 데이터 마이닝과 연계하여 확장하는 구조로 현실적이고 단기적인 데이터 통합효과를 위해 ETL/데이터웨어하우스방식을 적용하여 데이터 통합을 추진하였다. 지자체간 분산되어 있는 데이터베이스간의 연동은 관련 법제도 및 지자체간 협의 등 다양한 문제가 연루되어 있어 단기적으로는 B2B 데이터 연동방식을 응용하여 구성하였다. 광역 중앙 제어를 위한 통합데이터베이스는 가상DB 방식을 고려하였으며, 이는 지자체별로 구성된 통합DB에 대한 인터페이스 및 Wrapper 플랫폼을 적용하였다. 이 플랫폼간의 연동은 WaterML2.0을 적용함으로써 단기간내 구현이 가능하도록 하고 상호운용성에 문제를 해결하며, 실시간 데이터 연계를 추구하였다. 본 연구를 통해서 궁극적으로는 수자원 및 물관리 데이터의 통합을 위해 해당플랫폼에서 스키마 맵핑, 프로토콜 변환 정합 등을 실시하며, 실시간 데이터 마이닝 및 통합이 가능하도록 구성함으로써 향후 스마트워터그리드의 빅데이터 플랫폼 개발까지 확장해나갈 수 있을 것으로 기대된다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.39-48
• /
• 2023

Because a railway bridge is designed over a long period of time and covers a large site, it involves various environmental factors and uncertainties. For this reason, design changes often occur, even if the design was thoroughly reviewed in the initial design stage. In particular, design changes of large-scale facilities, such as railway bridges, consume significant time and cost, and it is extremely inefficient to repeat all the procedures each time. In this study, a technique that can improve the efficiency of learning after design change was developed by utilizing the learning result before design change through transfer learning among deep-learning algorithms. For analysis, scenarios were created, and a database was built using a previously developed railway bridge deep-learning-based prediction system. The proposed method results in similar accuracy when learning only 1000 data points in the new domain compared with the 8000 data points used for learning in the old domain before the design change. Moreover, it was confirmed that it has a faster convergence speed.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.1
• /
• pp.51-60
• /
• 2023

This paper aims to propose a method for the systematic management of construction information using ontology. In particular, it was intended to propose a method to systematically manage the construction method information required by designers and constructors. The information used in this paper is a case of test-bed construction resulting from 10 years of modernized Hanok technology development research. The new construction methods of modernized Hanok were organized using the ontology editor, Protege. To this end, the concept of ontology and the process of constructing ontology have been summarized through a review of existing research first. A conceptual diagram for constructing a domain ontology of the modernized Hanok construction methods was then proposed, and the effectiveness of the proposed domain ontology was verified using the SPARQL Query function of Protege. Finally, the defined classes and construction method metadata were published on the web using ontology web language (OWL).

• Convergence Security Journal
• /
• v.23 no.3
• /
• pp.29-36
• /
• 2023

With the recent surge in exposure to fake advertising phishing sites in search engines, the damage caused by poor search quality and personal information leakage is increasing. In particular, the seriousness of the problem is worsening faster as the possibility of automating the creation of advertising phishing sites through tools such as ChatGPT increases. In this paper, the source code of fake advertising phishing sites was statically analyzed to derive structural commonalities, and among them, a detection crawler that filters sites step by step based on foreign domains and redirection was developed to confirm that fake advertising posts were finally detected. In addition, we demonstrate the need for new guide lines by verifying that the redirection page of fake advertising sites is divided into three types and returns different sites according to each situation. Furthermore, we propose new detection guidelines for fake advertising phishing sites that cannot be detected by existing detection methods.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.1
• /
• pp.182-196
• /
• 2024

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.434-437
• /
• 1999

트래픽 공학(Traffic Engineering)의 목적은 서비스에 대한 QoS의 보장과 네트워크 자원의 사용을 최대화함으로써 가능한 한 많은 데이터 스트림을 처리하고자 하는 것이다. 이를 위한 경로 배정은 MPLS 도메인을 구성하는 네트워크 자원의 가용성 여부를 바탕으로 결정되어야 하므로 네트워크 자원의 운용 상태에 대한 정보들이 경로결정이 일어나는 노드로 전달되어야 한다 또한 경로 결정에 있어서 원하는 바에 맞게 다양한 라우팅 알고리즘이 복합적으로 적용되어야 한다. 본 논문에서는 트래픽 공학을 위하여 네트워크 자원의 운용 상태를 수집하는 방법과 이를 바탕으로 적용되어야 할 여러 라우팅 메커니즘을 제시하고 트래픽 공학을 위하여 이들이 어떻게 상호 연관성을 갖고 협력하여야 할 것인가를 제시한다

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.941-943
• /
• 2013

본 눈문은 스토리지 클라우드 서비스와 소셜 네트워크 서비스가 결합된 시스템을 설계하려고 한다. 최근에 다양한 스토리지 클라우드의 등장과 SNS 인기가 급상승 하고 있지만, 서로 자료를 공유하며 의견을 주고 받는 시스템은 거의 없는 수준이다. 본 논문에서는 학교 및 기업과 같은 인적 네트워크가 필요한 곳에서 원활한 자료 공유와 SNS와 같은 자유로운 의견공유가 효율적으로 되도록 하는 시스템을 설계하려고 한다. 본 시스템을 통해 개인적인 스토리지 클라우드와 SNS를 접목해 사용자 저장 공간을 통해 언제 어디서든 SNS을 통해서 관계된 사용자간의 자유로운 자료 공유를 사용하여 추후 다양한 도메인에서 실용화가 이루어지리라 기대한다.

• Journal of Broadcast Engineering
• /
• v.18 no.1
• /
• pp.88-97
• /
• 2013

Collaborative filtering(CF) for the personalized recommendation is a successful and popular method in recommender systems. But the mainly researched and implemented cases focus on dealing with independent items with explicit feedback by users. For the domain of TV program recommendation in VOD service platform, we need to consider the unique characteristic and constraints of the domain. In this paper, we studied on the way to convert the viewing history of each TV program episodes to the TV program preference by considering the series structure of TV program. The former is implicit for personalized preference, but the latter tells quite explicitly about the persistent preference. Collaborative filtering is done by the unit of series while data gathering and final recommendation is done by the unit of episodes. As a result, we modified CF to make it more suitable for the domain of TV program VOD recommendation. Our experimental study shows that it is more precise in performance, yet more compact in calculation compared to the plain CF approaches. It can be combined with other existing CF techniques as an algorithm module.

• Journal of KIISE:Software and Applications
• /
• v.36 no.7
• /
• pp.539-547
• /
• 2009

Software product line (SPL) engineering is an emerging paradigm for successful software reuse and has been adopted for various industrial and consumer products to improve their productivity and quality. However, most SPL methods require high initial costs and long development time, which makes many companies hesitate to adopt the SPL paradigm. In this paper we introduce a method to construct an SPL by extracting core assets from legacy components based on the feature model, which requires less initial time and effort. We also present a case study on cable set-top box software to illustrate the applicability of this method, and lessons learned that will provide guidelines for many companies to adopt the SPL paradigm.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.243-250
• /
• 2020

Knowledge graph-based question answering not only requires deep understanding of the given natural language questions, but it also needs effective reasoning to find the correct answers on a large knowledge graph. In this paper, we propose a deep neural network model for effective reasoning on a knowledge graph, which can find correct answers to complex questions requiring multi-hop inference. The proposed model makes use of highly expressive bilinear graph neural network (BGNN), which can utilize context information between a pair of neighboring nodes, as well as allows bidirectional feature propagation between each entity node and one of its neighboring nodes on a knowledge graph. Performing experiments with an open-domain knowledge base (Freebase) and two natural-language question answering benchmark datasets(WebQuestionsSP and MetaQA), we demonstrate the effectiveness and performance of the proposed model.