http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
GIS와 GPS를 연계한 무선 실시간 하천수질관리시스템 개발
이재응,하상민,이종국,Yi,Jae-Eung,Ha,Sang-Min,Lee,Jong-Kook 한국방재학회 2002 한국방재학회논문집 Vol.2 No.4
본 연구에서는 하천수질자료를 현장계측하고 무선으로 실시간 전송하여, GIS 상에서 자료를 분석하여 하천수질의 이상을 신속, 정확하게 파악하여 하천의 수질관리를 효율적으로 관리할 수 있는 GIS에 기반한 하천수질 관리시스템을 개발하였다. 시스템을 성능을 테스트할 목적으로 한강의 제1지류인 탄천을 시범유역으로 선정하여 개발된 시스템을 테스트하였다. 하천관리시스템은 크게 GPS 수신기가 탑재된 무선 실시간 계측시스템, 서버컴퓨터, GIS 시스템의 세 부분으로 나뉘어지며 각각의 시스템을 통합, 연계하여 최종 시스템을 개발하였다. 개발된 하천관리시스템을 시험유역에 적용한 결과 탄천 수질자료의 측정이 실시간으로 이루어짐과 동시에 서버컴퓨터에 저장되는 자료를 GIS 시스템 상에서 즉시 표출하고 가공할 있게 됨으로서 하천 수질을 실시간으로 관리할 수 있는 가능성을 제고하였으며 수질오염확산예측 및 수질방재등의 목적으로 활용할 수 있는 가능성을 확인하였다. In this paper the development of a real time river water quality management system is described. This system can manage a river water quality fluctuation by finding out abnormal conditions quickly and exactly. The GIS based monitoring system collects various properties of river water quality through the wireless real time network. Tanchun, the first branch of the Han River was selected as the target basin of the system development. This system is composed of three parts - wireless real time field measuring system with a GPS receiver, a server computer and a GIS platform. After the first field test in Tanchun basin, the result showed the many possibilities of measuring various water quality properties in real time and storing the data and analyzing them within the GIS environment in real time in very efficient manners. It is expected that the developed system will contribute to the efficient management of a river water quality control and water quality related disaster prevention purposes.
설명 가능한 KOSPI 증감 예측 딥러닝 모델을 위한 Layer-wise Relevance Propagation (LRP) 기반 기술적 지표 및 거시경제 지표 영향 분석
이재응(Jae-Eung Lee),한지형(Ji-Hyeong Han) Korean Institute of Information Scientists and Eng 2021 정보과학회논문지 Vol.48 No.12
Most of the research on stock prediction using artificial intelligence has focused on improving the accuracy. However, reliability, transparency, and equity of decision-making should be secured in the field of finance. This study proposes a layer-wise relevance propagation (LRP) approach to create an explainable stock prediction deep learning model, which is trained using macroeconomic and technical indicators as the input features. Also, the definition of the problem is simplified by prediction of an increase or decrease in the KOSPI closing price from the previous day instead of prediction of the KOSPI value itself. To show how the proposed method works, experiments are conducted. The results show that the model trained with data by the selected features via LRP is more accurate than the vanilla model. Moreover, we show that LRP results are meaningful by analyzing the tendency of the positive effect of each feature for the prediction results.
박재혁(Jae Hyeok Park),김규민(Kyu Min Kim),이재응(Jae Eung Lee) 대한기계학회 2018 대한기계학회 춘추학술대회 Vol.2018 No.12
Particle damper is a device that acts as an attenuator by filling the particles inside the enclosure and generating energy dissipation due to collision and friction between the particle and the enclosure. Many studies are performed to investigate the effect of variables, such as particle size, mass ratio, gap size, etc. to the damping performance of a single chamber particle damper. In this paper, a dual chamber is proposed to improve the damping performance, and an experimental study is carried out to confirm the damping performance in a low frequency band by installing a particle damper on a cantilever beam.