• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.79-84
• /
• 2016

본 연구는 전문기관에서 생산되는 검증된 문서를 웹상의 수많은 검증되지 않은 문서에 자동 주석하여 신뢰도 향상 및 심화 정보를 자동으로 추가하는 시스템을 설계하는 것을 목표로 한다. 이를 위해 활용 가능한 시스템인 인공 신경 정리 증명계(neural theorem prover)가 대규모 말뭉치에 적용되지 않는다는 근본적인 문제를 해결하기 위해 내부 순환 모듈을 단어 임베딩 모듈로 교체하여 재구축 하였다. 학습 시간의 획기적인 감소를 입증하기 위해 국가암정보센터의 암 예방 및 실천에 대한 검증된 문서들에서 추출한 28,844개 명제를 위키피디아 암 관련 문서에서 추출한 7,844개 명제에 주석하는 사례를 통하여 기존의 시스템과 재구축한 시스템을 병렬 비교하였다. 동일한 환경에서 기존 시스템의 학습 시간이 553.8일로 추정된 것에 비해 재구축한 시스템은 93.1분 내로 학습이 완료되었다. 본 연구의 장점은 인공 신경 정리 증명계가 모듈화 가능한 비선형 시스템이기에 다른 선형 논리 및 자연언어 처리 모듈들과 병렬적으로 결합될 수 있음에도 현실 사례에 이를 적용 불가능하게 했던 학습 시간에 대한 문제를 해소했다는 점이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.255-258
• /
• 2002

최근에 학습 관리 시스템은 기존의 교수자 중심의 교수설계와는 달리, 학습자들이 스스로 자신의 진도를 판단하거나 관리, 동료들과 연구를 할 수 있도록 도와주는 역할을 한다. 학습 컨텐트 관리 시스템(LCMS: Learning Content Management System)는 컨텐트 관리와 학습자들의 학습 과정 관리를 한데 묶어 융통성 있게 활용할 수 있도록 도와주는 시스템이다. 즉 새로운 컨텐트 묶음을 생성하고, 학습객체(LO: Learning Object)를 통한 코스개발도 할 수 있다. 본 논문에서는 학습 객체를 통한 코스의 개발에 초점을 맞추어, 도구의 분석 및 설계 경험을 비교 분석하여 효과적인 웹 기반 CDT-L(Course Development Tool-LCMS)의 분석 및 설계를 위한 기능, 비기능 요소를 추출해 보고자 하였다. 학습 객체의 생성, 분해 조립을 통해 학습코스를 작성함으로써 수업개발의 효율성을 높일 수 있으며, 학습자리 개별적 요구에 컨텐트를 제공해 줄 수 있으며, 학습 객체를 통해 코스개발 도구의 분석 및 설계를 함으로써 비용과 효율성을 보장하며, 학습 컨텐트의 중복을 피하고 학습과정 개발의 효율성을 가지게 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.704-709
• /
• 2006

In this study, we suggest the effective storage structure and management method for XML-based electrocardiography(ECG) data to support the interoperability between medical information systems, and implement the metadata system of ECG data providing the web-based information service. ECG matadata management system include functions for storing and managing as well as reporting PDF service of ECG data. We analyzed a characteristics of the data and access patterns for XML-based ECG and then used the non-partitioning storing method and indexing the extracted metadata from the HL7 aECC for supporting the quick search. We, using the template mechanism, converts the XML-based results data into various formats in order to provide services of the ECG reporting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.269-272
• /
• 2004

1950년대 동란을 거쳐 1960년대 초반부터 시작된 경제개발계획에 의해 급격한 경제성장으로 인해 산업 인구의 대도시 집중화에 의하여 전기의 공급력 부족 현상은 지속되었다. 따라서, 이때부터 성장한 경제배전계통은 수적으로도 많고 광범위하게 산재되어 있어 인력에 의해서는 더 이상 효과적인 관리가 어렵게 되었고, 사회가 고도 정보화로 진전되면서 수용가는 한층 더 높은 공급 신뢰도와 고품질의 전력공급을 요구하고 있다. 이러한 변화에 따라 전력공급자는 전력계통에 대한 감시와 제어를 통하여 항시 안정적이고 신뢰성있는 운용을 하여야한다. 이에 따라 배전계통에 설치된 배전설비를 컴퓨터와 통신수단을 이용하여 원격지에서 감시 제어할 수 있는 배전자동화 시스템에 대한 연구가 오래 전부터 이루어져 왔으며 효과적으로 양질의 전력을 공급하고자 배전자동화 시스템(DAS)이 도입되었다. 본 연구에서는 능동적인 감시 및 제어기능을 제공하는 객체지향형 능동데이터베이스 알고리즘을 사용하여 배전계통 제어에 적용하였고 기존의 인터넷 통신망을 통한 감시 및 제어가 가능하게 하였으며 이러한 효과에 의해 배전계통이 여러개의 다른 전력회사로 분할될 경우 각기 존재하는 다른 시스템에 대하여 인터넷을 통한 연계가 가능하도록 하여 통합적인 데이터베이스를 구축하는데 용이하게 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.527-530
• /
• 2008

SOA는 최근 급부상한 기술로 발전된 웹서비스 기술과 접목되면서 특히 실시간 기업에게 각광받고 있다. 이에 따라 SOA를 위한 민첩성과 빠른 적응력이 충족되는 구체적인 기법 연구가 많은 진행 중에 있다. 이는 SOA에서의 테스트 역시 마찬가지이며, 본 논문에서는 민첩성과 적응력을 높일 수 있는 SOA를 위한 테스트케이스 생성 기법을 제안한다. SOA는 기존의 컴포넌트 기반의 개발과는 관점의 차이 때문에 절차나 기법의 접근 방법이 다를 수 있다. 따라서 본 논문에서는 SOA의 서비스를 하부 계층인 컴포넌트로 분할하여 기존의 연구를 활용한 후, 다시 서비스 단위로 합성하여 서비스의 테스트케이스를 생성한다. 그리고 제시한 기법을 인터넷 뱅킹 시스템의 계좌잔액조회 서비스에 적용함으로써 서비스 단위의 테스트케이스 생성 사례를 보인다. 제안 기법을 통해 서비스 단위의 테스트를 체계적으로 할 수 있으며, 빠른 릴리즈를 실현하여 SOA의 민첩성과 적응력을 높일 수 있다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.87-92
• /
• 2024

In this paper, a RAG system was implemented using an existing Large Language Model (LLM) and Langchain library to develop a dental consultation chatbot. For this purpose, we collected contents from the webpage bulletin boards of domestic dental university hospitals and constructed consultation data with the advice and supervision of dental specialists. In order to divide the input consultation data into appropriate sizes, the chunk size and the size of the overlapping text in each chunk were set to 1001 and 100, respectively. As a result of the simulation, the Retrieval Augmented LLM searched for and output the consultation content that was most similar to the user input. It was confirmed that the accessibility of dental consultation and the accuracy of consultation content could be improved through the built chatbot.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.287-292
• /
• 2002

In general cases, the conventional internet connected to a terrestrial network is transmit too large medical images. To overcome this low speed transmitting rate problem of the interned, we have studied about an image division communication system as a fast telemedicine system. The image division communication system was 5-10 times faster than the conventional terrestrial internet link. Also we have developed a Web-based telemedicine system that can access every permitted server of hospitals via the internet. Studied image division communication corrected problem of other reflex quality decline in erratic transmission of reflex by transmission speed imbalance that is problem of single communication techniques that used in existing reflex transmission. Also, could keep quality state of fixed reflex gouge abnormal transmission speed. Visual Basic and C++, ASP programming techniques were used to make our system and it can access and retrieve medical information and image through only public web browse such as internet explorer without additional specific tools. To increase the transmitting speed of our telemedicine system, JPEG method was used. In conclusion, we were able to develop a fast and public telemedicine system using the proposed image division communication system and Web technology. Image division communication system technology increased the speed of the conventional internet and Web technology extended the scope of use for telemedicine system from intrahospital to public use.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.895-907
• /
• 2020

With the recent increasing influence of multimedia content other than the text-based content, services that help to process information in content brings us great convenience. These services' representative features are searching and masking the sensitive data. It is not difficult to find the solutions that provide searching and masking function for text information and image. However, even though we recognize the necessity of the technology for searching and masking a part of the audio data, it is not easy to find the solution because of the difficulty of the technology. In this study, we propose web application that provides searching and masking functions for audio data using audio partitioning method. While we are achieving the research goal, we evaluated several speech to text conversion APIs to choose a proper API for our purpose and developed regular expressions for searching sensitive information. Lastly we evaluated the accuracy of the developed searching and masking feature. The contribution of this work is in design and implementation of searching and masking a sensitive information from the audio data by the various functionality proving experiments.

• Journal of Korean Home Economics Education Association
• /
• v.32 no.2
• /
• pp.59-76
• /
• 2020

The purpose of this study was to develop and evaluate the teaching/learning process plan of 'housing culture and practical space use' for home economics in middle school according to the problem based learning(PBL) model. The plan consisting of 4-lessons has been developed and implemented following the steps of ADDIE model. Various activity materials (4 scenarios, 6 individual activity sheets, 10 reading texts, and 5 working resources) and visual materials (4 sets of ppt and 4 moving pictures) as well as questionnaire were developed for the 4-session lessons. The plans were implemented to a single class of 21 junior students at H middle school in rural area, Kyeongnam, from 1^st to 12^th of April, 2019. Students highly enjoyed and were satisfied with the whole 4-lessons in aspects such as understanding of the contents, adequacy of materials and activities, and usefulness in one's own daily life. Additionally, they have more actively participated in the lessons than usual and even interested in learning more of such lessons. Students also reported that they highly accomplished the goal of each lesson as well as overall objectives. They showed interest in the major part of PBL lesson such as scenario and group activities. And they engaged themselves in drawing the share housing space plan with '5D planner' web program which they described as the best part of the lessons. The teaching/learning process plan developed in this study may be used as a theme of maker education, which is emerging these days. It can be concluded that the PBL teaching/learning process plans for 'housing values and practical space use' would contribute to improving students' attitude on living with others and ability to manage one's individual life.

• Progress in Medical Physics
• /
• v.14 no.1
• /
• pp.34-42
• /
• 2003

In medical imaging, three-dimensional (3D) display using Virtual Reality Modeling Language (VRML) as a portable file format can give intuitive information more efficiently on the World Wide Web (WWW). The web-based 3D visualization of functional images combined with anatomical images has not studied much in systematic ways. The goal of this study was to achieve a simultaneous observation of 3D anatomic and functional models with planar images on the WWW, providing their locational information in 3D space with a measuring implement using VRML. MRI and ictal-interictal SPECT images were obtained from one epileptic patient. Subtraction ictal SPECT co-registered to MRI (SISCOM) was performed to improve identification of a seizure focus. SISCOM image volumes were held by thresholds above one standard deviation (1-SD) and two standard deviations (2-SD). SISCOM foci and boundaries of gray matter, white matter, and cerebrospinal fluid (CSF) in the MRI volume were segmented and rendered to VRML polygonal surfaces by marching cube algorithm. Line profiles of x and y-axis that represent real lengths on an image were acquired and their maximum lengths were the same as 211.67 mm. The real size vs. the rendered VRML surface size was approximately the ratio of 1 to 605.9. A VRML measuring tool was made and merged with previous VRML surfaces. User interface tools were embedded with Java Script routines to display MRI planar images as cross sections of 3D surface models and to set transparencies of 3D surface models. When transparencies of 3D surface models were properly controlled, a fused display of the brain geometry with 3D distributions of focal activated regions provided intuitively spatial correlations among three 3D surface models. The epileptic seizure focus was in the right temporal lobe of the brain. The real position of the seizure focus could be verified by the VRML measuring tool and the anatomy corresponding to the seizure focus could be confirmed by MRI planar images crossing 3D surface models. The VRML application developed in this study may have several advantages. Firstly, 3D fused display and control of anatomic and functional image were achieved on the m. Secondly, the vector analysis of a 3D surface model was defined by the VRML measuring tool based on the real size. Finally, the anatomy corresponding to the seizure focus was intuitively detected by correlations with MRI images. Our web based visualization of 3-D fusion image and its localization will be a help to online research and education in diagnostic radiology, therapeutic radiology, and surgery applications.