• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.125-132
• /
• 2022

The Ministry of Environment recently analyzed the output data of 10 fine dust measuring stations and, as a result, announced that about 60% had an error that the existing atmospheric measurement concentration was higher. In order to accurately predict fine dust, the wind direction and measurement position must be corrected. In this paper, in order to solve these problems, fuzzy rules are used to solve these problems. In addition, in order to calculate the fine particulate sensation index actually felt by pedestrians on the street, a computer simulation experiment was conducted to calculate the fine particulate sensation index in consideration of weather conditions, temperature conditions, humidity conditions, and wind conditions.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.315-315
• /
• 2020

기후변화로 인하여 전 세계적으로 이상기후가 진행되고 있다. 우리나라의 경우 홍수와 가뭄 등의 이상 강수가 빈번히 발생하고 있으며, 이로 인한 비점오염물질의 유출과 집적이 발생하고 있다. SWAT (Soil and Water Assessment Tool)과 HSPF (Hydrological Simulation Program)등의 다양한 모델이 비점오염의 유출을 모의하기 위하여 활용되고 있으나, 농장 단위에서 유역 단위까지 다양한 대상지역에 대한 장기 모의와 BMP적용에 따른 효율평가가 어려운 실정이다. Texas A&M Agrilife Research에서 개발한 APEX(Agricultural Policy Environmental eXtender model) 모형의 경우, 농장 단위에서 유역 단위의 대상지역에 대하여 최대 100년까지 일단위 모의가 가능한 특징이 있다. 하지만 APEX 모형은 개발된지 상당한 시간이 지났으며, 데스크탑 기반의 모형이므로 다양한 플랫폼에서의 활용이 어려운 한계점이 있다. 따라서 본 연구에서는 1. 기존 데스크탑 기반의 APEX 모형을 웹에서 구동할 수 있도록 웹 기반 시스템을 구축하였으며, 2. 양분유출에 대한 모의 평가가 가능하도록 결과를 시스템화하는 모듈을 추가하였다. 또한, 3. 웹 기반 APEX 모형의 활용도를 위하여 최적관리기법을 적용할 수 있는 모듈을 개발 및 추가하였다. 본 연구의 결과는 향후 농업비점오염원 지역의 양분유출을 확인·예측하고 관리하기 위한 기초자료로 활용될 것으로 기대하며, 최적관리기법을 활용한 저감 정책을 수립하기 위한 평가도구로 활용될 수 있을 것이다. 또한, 기존 데스크탑 기반의 모형을 웹 기반으로 이전하였으므로, APEX 모형 혹은 다른 데스크탑 기반 모형들의 웹 이전을 통한 사용자 편의성 증대를 위한 기초자료로 활용될 수 있을 것이다. 아울러 본 연구의 결과는 APEX 모형의 작물 매개변수가 국내 환경에 최적화 되어있지 않으므로 정확한 BMP 저감효과 모의에는 한계가 있으므로, 이에 대한 추가적인 연구가 필요할 것으로 판단된다.

• Journal of Korean Society of Environmental Engineers
• /
• v.34 no.12
• /
• pp.792-800
• /
• 2012

The study was performed to simulate the reduction efficiency of suspended solids (SS) for cultivated land located at riverine area at the Namhan River and the Bukhan River watershed sites (site A, B, C) under the rainfall conditions using HUFF & SCS UH-based VFS Design module of Web GIS-based VFSMOD System. The study indicates that the field 5% sloped, located at Bukhan River watershed (site A), requires at least 0.5 m width of Vegetative Filter Strip (VFS) to reduce 70% of SS while the field 10% sloped requires the at least 1.0~1.5 m width of VFS to reduce 70% SS, under the condition 106.2 mm of rainfall event and bell pepper or corn of crops. Against the conditions 95.1 mm of rainfall event and sweet potato or soy bean of crops, the field 5% sloped, located at Namhan River watershed (site B) requires at least 0.5 m width of VFS to reduce 70% of SS while the field 10% sloped requires at least 1.0 m width of VFS to reduce 50% SS. The crops sweet potato and soy bean are cultivated in the site C, located at Namhan River watershed, 1 m of VFS is capable of 64.0% and 62.0% of SS reduction against 102.6 mm and 151.2 mm rainfall conditions respectively, for the 5% sloped field. The result supports that VFS is one of most potential methods to reduce SS from cultivated area, which is environment-friendly hydrologic structure. The VFS design, however, needs to be simulated before its installation in the field, the simulation needs to consider not only various characteristics of the field but also different conditions affecting the VFS, using a model capable to consider a lot of factors.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.1
• /
• pp.1-7
• /
• 2021

In this paper, We focused the issue of creating a socially problematic nurse schedule. The nurse schedule should be prepared in consideration of three shifts, appropriate placement of experienced workers, the fairness of work assignment, and legal work standards. Because of the complex structure of the nurse schedule, which must reflect various requirements, in most hospitals, the nurse in charge writes it by hand with a lot of time and effort. This study attempted to automatically create an optimized nurse schedule based on legal labor standards and fairness. We developed an I/O Q-Learning algorithm-based model based on Python and Web Application for automatic nurse schedule. The model was trained to converge to 100 by creating an Fairness Indicator Score(FIS) that considers Labor Standards Act, Work equity, Work preference. Manual nurse schedules and this model are compared with FIS. This model showed a higher work equity index of 13.31 points, work preference index of 1.52 points, and FIS of 16.38 points. This study was able to automatically generate nurse schedule based on reinforcement Learning. In addition, as a result of creating the nurse schedule of E hospital using this model, it was possible to reduce the time required from 88 hours to 3 hours. If additional supplementation of FIS and reinforcement Learning techniques such as DQN, CNN, Monte Carlo Simulation and AlphaZero additionally utilize a more an optimized model can be developed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.580-581
• /
• 2021

There are various Location-Based Services(LBS) that apply GPS technology in mobile devices such as smart-phone and tablet. In this paper, we designed non-face-to-face oriented LBS software in the reality that non-face-to-face services are increasing due to COVID-19. The proposed model searches location information for trading goods or services and utilizes information identified in real time. The proposed scheduling and priority control algorithm provides efficient service allocations and simulation was performed based on web/app to verify this. While commercialized LBS platforms focus on used goods transactions, the designed method is different in that it provides non-face-to-face services and not-direct transactions between individuals. It provides a wide range of transactions and services to users such as small business owners and franchises.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.5
• /
• pp.46-54
• /
• 2011

There have been research and developments for effective and efficient logistics and progress management in a construction project. Among them, RFID+4D has been developed for the supply chain management of long-lead item materials such as steel component, precast concrete component and curtain wall by integrating RFID with 4D CAD. And the feasibility of RFID+4D has been verified and validated and the benefits in terms of time and cost were shown in several case studies. However, the previous development of RFID+4D has not been adapted widely because of additional modeling cost, non-real time data update, additional labor for data update, and so forth. Therefore, this research has proposed a framework and process for solving these problems. And the web based simulation system has been developed and verified based on the proposed framework. The proposed framework and process can improve the existing RFID+4D system in a construction project by saving its operation cost and utilizing project information more efficiently and effectively. Also it is expected that the proposed framework could be applied to a method transferring design RIM data to construction BIM data.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1187-1190
• /
• 2004

This paper presents a traveler guidance system that offers 3D street information such as road types, signal light systems, street trees, buildings, etc. We consider 5x4 road system of Gangnam(in Seoul, Korea) as a test area and reflect the traveler's car-driving situation. A web server is constructed to serve traveler's driving path by switching 3D animation scenes automatically. To do batch processing of geometric data for the 3D graphical streets construction, we have extracted major street information from present GIS database and created new GIS file formats (SMF files), which contain data sessions for links, nodes, and facilities. With these files, we can render 3D navigation scenes. A number of vector calculations were performed for the geometrical consistence and texture-mapping method was used for the realistic scene generation. Finally, we have verified the effectiveness of the service by operating a test scenario. We have checked whether traveler's 2D path and 3D navigation are exactly reported after setting specific departure and destination. This system offers us well awareness of streets and takes useful role of traveler guidance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.12
• /
• pp.1833-1840
• /
• 2013

A golf ball collecting robot in a golf ball driving range has been recently required because it is safer and more economic than a human being. In this paper, the golf ball recognition and distance estimation system based on a neural network and OpenCV is developed for the robot. The simulation results show that the recognition ratio is over 87% for the distance of less than 120cm and accurate rate for distance estimation is over 85% for golf balls in 30-180cm from a webcam.

• Journal of Advanced Navigation Technology
• /
• v.20 no.2
• /
• pp.116-126
• /
• 2016

In this study, has designed the ship application system for efficient data integration management of onboard ship and shore application/service utilizing data collected onboard ship, and has implemented the module. In order to supports onboard ship and shore service utilizing onboard ship collected data and provide a easy to access among individual devices, the ship application system applied the XML structure of ISO 16425 and the data sharing system model discussed in IALA, and the common module for system operation, a windows service for data collection/integral management, and web service module for management has been implemented.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.56 no.1
• /
• pp.81-88
• /
• 2014

Accurate wind data is essential for predicting airborne spread of virus. OpenFOAM was used for computational fluid dynamics (CFD) simulation procedure which is under GNU GPL (General Public License). Using complex terrain, DEM (Digital Elevation Map) that was prepared from GIS information covering a research site is converted to a three dimensional surface mesh that is composed by quad and full hexahedral space meshes. Around this surface mesh, an extended computational domain volume was designed. Atmospheric flow boundary conditions were used at inlet and roughness height and was considered at terrain by using rough wall function. Two different wind conditions that was relatively stable during certain periods were compared in 3 different locations for validating the accuracy of the CFD computed solution. The result shows about 10 % of difference between the calculated result and measured data. This procedure can simulate a prediction of time-series data for airborne virus spread that can be used to make a web-based forecasting system of airborne virus spread.