• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.206-208
• /
• 2000

Manual generation of the relay setting summary could involve fatal errors which would result in the big damage to the system. This paper reports the automatic generation system of relay setting reports. Analysing the manual reports of various relays the almost unified format has been designed. The developed system utilizes the graphics and tabular format to enhance the user understanding.

• 한국항행학회논문지
• /
• 제28권5호
• /
• pp.738-744
• /
• 2024

의료 분야에서 중요한 DICOM 이미지 데이터를 효과적으로 요약하고 시각화하는 시스템을 개발하는 것을 목표로 한다. 이 시스템은 React와 Node.js를 활용하여 DICOM 이미지를 수집하고 파싱하며, 그 과정에서 중요한 의료 정보를 추출한다. 이후 LLM (large language model)을 이용해 자동 요약 보고서를 생성하여 사용자에게 맞춤형 의료 정보를 제공한다. 이를 통해 의료 정보의 접근성을 높이고, 웹 기술을 활용하여 대용량 데이터를 신속하고 안정적으로 처리할 수 있다. 이 시스템은 환자와 의사 간의 커뮤니케이션을 강화하여 치료의 질을 높이고, 의료진이 빠르고 정확한 의사 결정을 할 수 있도록 돕는다. 이와 더불어, 환자의 의료 경험을 개선하여 전반적인 만족도를 높이는 데 기여할 것이다. 궁극적으로 이 시스템은 의료 서비스의 질적 향상을 목표로 한다.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.327-334
• /
• 2024

Bridge inspection is crucial for infrastructure maintenance. Current inspections based on computer vision primarily focus on identifying simple defects such as cracks or corrosion. These detection results can serve merely as preliminary references for bridge inspection reports. To generate detailed reports, on-site engineers must still present the structural conditions through lengthy textual descriptions. This process is time-consuming, costly, and prone to human error. To bridge this gap, we propose a deep learning-based framework to generate detailed and accurate textual descriptions, laying the foundation for automating bridge inspection reports. This framework is built around an encoder-decoder architecture, utilizing Convolutional Neural Networks (CNN) for encoding image features and Gated Recurrent Units (GRU) as the decoder, combined with a dynamically adaptive attention mechanism. The experimental results demonstrate this approach's effectiveness, proving that the introduction of the attention mechanism contributes to improved generation results. Moreover, it is worth noting that, through comparative experiments on image restoration, we found that the model requires further improvement in terms of explainability. In summary, this study demonstrates the potential and practical application of image captioning techniques for bridge defect detection, and future research can further explore the integration of domain knowledge with artificial intelligence (AI).

• 정보관리학회지
• /
• 제29권2호
• /
• pp.7-25
• /
• 2012

전자저널의 활용이 급속히 증가하면서 도서관에서는 자관에서 구입되는 전자저널이 얼마나, 어떻게 활용되고 있는지에 대한 관심이 증가하였다. 또한 전자정보 컨소시엄 주관기관에서도 컨소시엄 내에서 유통되는 학술자원의 이용통계에 대한 분석을 통해 국가 차원의 전자학술저널의 유통 현황 파악 및 수요자 중심의 정보수집 정책 개발이 필수적이다. 그러나 기존의 수작업에 의존한 이용통계 수집과 출판사에서 제공하는 저널 이용통계 보고서만으로는 이용에 대한 포괄적이고 심층적인 분석이 불가능하다. 이에 본 연구에서는 대용량 이용통계 수집 및 분석의 기반 마련을 위해 스크린 스크래핑과 SUSHI 프로토콜을 적용한 전자저널 이용통계 자동수집 시스템을 구현하였다. 또 저널 서지정보 및 컨소시엄 계약 데이터베이스를 연동하여 심층적인 이용통계 분석정보를 생성할 수 있는 방안을 제안하였다.

• 자동차안전학회지
• /
• 제10권1호
• /
• pp.27-31
• /
• 2018

This paper reports an analysis of cyclist accident cases with respect to passenger vehicles on Korean roads. A typology based on Initiative for the Global Harmonization of Accident Data (iGLAD) code book is applied to a traffic accident analysis system(TAAS), which has the real-world crash data on Korea roads, to understand the accident scenarios in more detail and efficiently. Similarly this typology has been used for Germany In-Depth Accidents Study (GIDAS) as well. The accident data analysis with consideration of the typology of Korean road conditions may prioritize traffic safety issues regarding cyclists and is aimed to develop an Automatic Emergency Braking (AEB) system for cyclist. In summary, this paper characterizes and analyzes the scenarios of cyclist crashes with passenger car. The most common accident scenarios on Korean roads are Car-to-Bicyclist Nearside Adult (CBNA) and Car-to-Bicyclist Longitudinal Adult (CBLA), which are more than 86% of total accidents cases. Therefore, it is inferred that AEB cyclist system should include these accident types in the operational design domain to reduce more fatality in Korea.

• 스마트미디어저널
• /
• 제12권5호
• /
• pp.17-27
• /
• 2023

최근 사용자에게 의미있는 정보만을 자동으로 간추리는 텍스트 자동 요약이 꾸준히 연구되고 있으며, 특히 인공신경망 모델인 트랜스포머를 활용한 텍스트 요약 연구가 주로 수행되고 있다. 다양한 연구 중 특히 문장 단위 마스킹을 통해 모델을 학습시키는 GSG 방식이 가장 주목을 받고 있지만, 전통적인 GSG는 문장의 의미가 아닌 토큰의 중복 정도에 기반을 두어 마스킹 대상 문장을 선정한다는 한계를 갖는다. 따라서 본 연구에서는 텍스트 요약의 품질을 향상시키기 위해, 문장의 의미를 고려하여 GSG의 마스킹 대상 문장을 선정하는 SbGSG(Semantic-based GSG) 방법론을 제안한다. 뉴스기사 370,000건과 요약문 및 레포트 21,600건을 사용하여 실험을 수행한 결과, ROUGE와 BERT Score 측면에서 제안 방법론인 SbGSG가 전통적인 GSG에 비해 우수한 성능을 보임을 확인하였다.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.30-31
• /
• 2009

Early detection of schedule delay in field construction activities is vital to project management. It provides the opportunity to initiate remedial actions and increases the chance of controlling such overruns or minimizing their impacts. This entails project managers to design, implement, and maintain a systematic approach for progress monitoring to promptly identify, process and communicate discrepancies between actual and as-planned performances as early as possible. Despite importance, systematic implementation of progress monitoring is challenging: (1) Current progress monitoring is time-consuming as it needs extensive as-planned and as-built data collection; (2) The excessive amount of work required to be performed may cause human-errors and reduce the quality of manually collected data and since only an approximate visual inspection is usually performed, makes the collected data subjective; (3) Existing methods of progress monitoring are also non-systematic and may also create a time-lag between the time progress is reported and the time progress is actually accomplished; (4) Progress reports are visually complex, and do not reflect spatial aspects of construction; and (5) Current reporting methods increase the time required to describe and explain progress in coordination meetings and in turn could delay the decision making process. In summary, with current methods, it may be not be easy to understand the progress situation clearly and quickly. To overcome such inefficiencies, this research focuses on exploring application of unsorted daily progress photograph logs - available on any construction site - as well as IFC-based 4D models for progress monitoring. Our approach is based on computing, from the images themselves, the photographer's locations and orientations, along with a sparse 3D geometric representation of the as-built scene using daily progress photographs and superimposition of the reconstructed scene over the as-planned 4D model. Within such an environment, progress photographs are registered in the virtual as-planned environment, allowing a large unstructured collection of daily construction images to be interactively explored. In addition, sparse reconstructed scenes superimposed over 4D models allow site images to be geo-registered with the as-planned components and consequently, a location-based image processing technique to be implemented and progress data to be extracted automatically. The result of progress comparison study between as-planned and as-built performances can subsequently be visualized in the D4AR - 4D Augmented Reality - environment using a traffic light metaphor. In such an environment, project participants would be able to: 1) use the 4D as-planned model as a baseline for progress monitoring, compare it to daily construction photographs and study workspace logistics; 2) interactively and remotely explore registered construction photographs in a 3D environment; 3) analyze registered images and quantify as-built progress; 4) measure discrepancies between as-planned and as-built performances; and 5) visually represent progress discrepancies through superimposition of 4D as-planned models over progress photographs, make control decisions and effectively communicate those with project participants. We present our preliminary results on two ongoing construction projects and discuss implementation, perceived benefits and future potential enhancement of this new technology in construction, in all fronts of automatic data collection, processing and communication.

• 간호행정학회지
• /
• 제3권1호
• /
• pp.93-106
• /
• 1997

By the increase of the rate of existence of the hemodialyzing patients, they were required the long run treatment. Regardless of medical insurance expansion, hemodialyzing cost much expenses so that hospital has been considering the reuse of hemodialyzer and flowing euqipments along with the diverse study and progress of the ways of hemodialyzing and medical instruments. This study was aimed to provide the basic materials regarding the reuse of hemodialyzer which is used for the patients of chronic renal disease. The reusing program in the artificial kidney center of K hospital has been used for this study from 50 patients aften one year result from Sep. 1995 through Aug. 1996. Automatic equipment of DRS-4 made by Seratronic Co., was used as the equipment and it was retreated with the function test simultaneously. Compliaction and confirmation of the infection were by the records of the hemodialysis of the patients. SPSS was used for the analysis of the materials by computerization. The character of the patients and the rate of removal was by mistake and percentage, function test and rate of complication by Ftest(ANOVA) and the rate of complication per items by ${\chi}^2$ and Ftest. As the post test the Duncan's test was used for the statistically significant different variables in the standard of p<.05 after Ftest. The followings are the summary of the result : 1) In the function test of the new hemodialyzer and the reused one, and in all of CA110 and CF15.11, the dialyzer ultrafiltration coeffient(KUf) was appeared to have been higher in the reusing groups than the first use ones. This has been the normal limit showing no troubles with them. 2) In the function test of the new and reused hemodialyzer, in all of CA110 and CF15.11, the total blood volume was appeared to have been the less value in the reuse groups than the new ones. This was the price within 80% of the first price that both showed possible for use. 3) The result of reuse hemodialyzer of CA110 was $29.48{\pm}7.83$ in average in the test of leak test while $17.3{\pm}7.96$ in reuse of CF15.11. The normal limit of <60 was the leak test result. So both of the hemodialyzer was normal for reuse. 4) The rate of removal of Blood Urea Nitrogen(BUN) was 72.25% in CA110 hemodialyzer by reusing 16-20 times as the highest rate showing the better result in the reuse hemodialyzer, while in CF15.11 hemodialyzer showed 71.16% by highest rate in the first use by the highest rate with no difference from the reuse. 5) The rate of removal of serum creatinine of CA110 was 64.08% by highest rate in reuse of 1-5 times by showing better result in reuse hemodialyzer. While in CF15.11 66.47% the highest by reuse of 16-20 times showing no difference from each other. 6) No patients were admitted or precribed by antibiotics in relation with reuse dialyzer and no reports were shown about hepatitis $B{\cdot}C$. AIDS in fection. 7) Of the total 248 episods of complication due to the hemodialyzing, 86 by first use, 73 by 1-5 times, 35 by 6-10 times, 35 by 11-15 times and 19 by 16-20 times have been shown which have had no significant difference between the groups. 8) In the comparison of the expense for the hemodialyzer, there was the effect of saving 11,597.6 Won between the first and reuse hemodialyzer. And by decreasing the extracted materials, they did the great role of disposing the waste matters.