• 농업과학연구
• /
• 제46권1호
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• 정보관리학회지
• /
• 제36권2호
• /
• pp.105-131
• /
• 2019

본 연구는 장서개발관리 분야의 최근 연구동향을 분석함으로써 핵심 연구주제를 파악하고 학문의 지적구조를 규명하고자 하였다. 2003년부터 2017년까지 15년간 문헌정보학 분야 4개 학회지에 등재된 논문 중 장서개발관리 분야의 키워드를 가진 연구논문을 선정하여 저자키워드를 추출하였다. 추출된 저자키워드를 가지고 NetMiner4 프로그램을 이용하여 키워드 네트워크를 구성한 뒤 빈도분석, 연결중심성 분석, 매개중심성 분석을 수행하였다. 분석은 시간의 흐름에 따른 연구 변화를 살펴보기 위하여 2003년부터 2017년까지 전 구간을 대상으로 한 분석과 5년 단위의 3구간으로 나누어 살펴보았다. 연구결과, '오픈액세스', '기관 레포지터리', '학술지' 등의 장서개발관리 분야의 핵심키워드를 파악하고, '대학도서관' 등의 계속 연구될 분야의 주제어를 파악하였다.

• Translational and Clinical Pharmacology
• /
• 제26권4호
• /
• pp.166-171
• /
• 2018

Although there are many commercially available training software programs for pharmacokinetics, they lack flexibility and convenience. In this study, we develop simulation software to facilitate pharmacokinetics education. General formulas for time courses of drug concentrations after single and multiple dosing were used to build source code that allows users to simulate situations tailored to their learning objectives. A mathematical relationship for a 1-compartment model was implemented in the form of differential equations. The concept of population pharmacokinetics was also taken into consideration for further applications. The source code was written using R. For the convenience of users, two types of software were developed: a web-based simulator and a standalone-type application. The application was built in the JAVA language. We used the JAVA/R Interface library and the 'eval()' method from JAVA for the R/JAVA interface. The final product has an input window that includes fields for parameter values, dosing regimen, and population pharmacokinetics options. When a simulation is performed, the resulting drug concentration time course is shown in the output window. The simulation results are obtained within 1 minute even if the population pharmacokinetics option is selected and many parameters are considered, and the user can therefore quickly learn a variety of situations. Such software is an excellent candidate for development as an open tool intended for wide use in Korea. Pharmacokinetics experts will be able to use this tool to teach various audiences, including undergraduates.

• 한국정보통신학회논문지
• /
• 제23권9호
• /
• pp.1160-1172
• /
• 2019

연합인증은 다수의 보안도메인 간에 적용되는 사용자 인증 및 인가체계이다. 연구 및 교육 분야에서 활용되고 있는 다수의 국외 웹 응용서비스들은 표준화된 사용자 인증방식으로 SAML(Security Assertion Markup Language) 기반의 연합인증을 채택하고 있다. 하지만 국내는 공개 SAML 소프트웨어를 이용하기 힘든 특정 웹 서버나 웹 응용 서버의 시장 점유율이 높고 전자정부 표준프레임워크 기반의 Java 웹 응용이 많기 때문에 연합인증 기술을 적용하기 어려운 상황이다. 본 논문은 Java 기반의 웹 응용개발 환경에서 연합인증 기술을 쉽고 안전하게 활용케 할 목적으로 개발된 SAML4J 소프트웨어를 소개한다. SAML4J는 개발 프레임워크에 독립적인 세션 저장소를 지원하고 API를 통해 Web SSO 플로우를 처리케 함으로써 개발자 친화적인 장점이 있다. 네트워킹 테스트베드를 구성하고 개발한 소프트웨어의 기능과 성능, 확장성 및 보안성에 대해서 검증함으로써 SAML4J의 높은 활용가능성을 확인한다.

• 농업과학연구
• /
• 제47권4호
• /
• pp.1029-1037
• /
• 2020

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제12권4호
• /
• pp.127-134
• /
• 2023

본 논문에서는 gcc 기반으로 개발된 eCos 운영체제 및 PROFINET 통신 스택을 IAR 컴파일러로 포팅하는 방법에 대해 설명한다. eCos 운영체제의 경우 PROFINET 구동을 위한 멀티 스레드, TCP/IP, 디바이스 드라이버 등의 기반 기능을 제공하고 있어, PROFINET 어플리케이션 개발시 변경할 필요가 없다. 따라서, 본 연구에서는 eCos는 gcc로 빌드된 라이브러리를 활용하고, 개발시 변경이 필요한 PROFINET 통신 스택은 IAR 로 포팅하여 함께 링킹하는 방안을 제안한다. IAR 링커와 gcc 링커의 차이로 인해 일부 섹션의 주소를 정의하는 심볼과 생성자의 주소가 정상적으로 생성되지 못하는 문제가 있어, MAP 파일을 읽어 해당 심볼 및 주소를 저장하는 외부 툴을 개발하였으며, 이 툴과 연동하여 동작할 수 있도록 부트로더의 소스 코드를 수정하였다. 제안하는 방법을 검증하기 위해 실제 지멘스 사의 PLC와 연결하여 PROFINET IRT 통신으로 실제 I/O 가 정상 동작하는지 검증하였으며, IAR 컴파일러가 컴파일 시간 및 생성된 바이너리 크기 모두 더 좋은 성능을 가지고 있음을 확인하였다. 본 연구에서 제안하는 방법은 eCos 및 PROFINET 통신 스택뿐 아니라 다양한 오픈 소스를 상용 컴파일러로 포팅하는데 도움을 줄 것으로 기대한다.

• 한국컴퓨터정보학회논문지
• /
• 제14권4호
• /
• pp.1-8
• /
• 2009

이 논문에서는 철근 절단 작업의 계획 문제를 동적 계획법으로 해결하여 근사 최적의 절단 계획을 생성하도록 하는 소프트웨어의 구현을 다룬다. 일반적으로 실제 절단 작업에 요구되는 제약사항을 반영하여 최적의 자재 절단문제의 해를 얻는 알고리듬의 설계가 필요하다. 하지만, 이것은 다중 규격의 1차원 자재 절단 문제를 풀어야 하는 것으로, 최적의 해를 얻는 선형계획법은 폭발적인 계산량과 기억용량의 한계로 적용하기 어렵다. 이러한 한계를 해결하기 위하여, 동적계획법에 근거하며 자재 절단 문제를 재구성하고, 휴리스틱을 적용하여 유한 범위의 조합 열에서도 근사 최적의 해를 찾을 수 있는 탐색 기법을 사용한 자재 절단 계획 알고리듬을 제시하였다. 그리고, 자동화된 철근 가공 산업용 소프트웨어는 작업 환경에 맞게 사용이 편리한 그래픽 화면과 사용자 인터페이스가 요구되는데, 공개 소프트웨어를 활용한 GUI 라이브러리 툴킷인 GTK+를 활용하여 이를 구현하였다. 개발된 소프트웨어는 철근 가공의 현장 지식을 바탕으로 휴리스틱 지식을 획득하여 동적계획법에 적용시킨 것으로, 지역 전통 산업과 첨단 IT 산업이 접목된 융합 IT를 시도한 사례 연구이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• 한국농공학회논문집
• /
• 제66권4호
• /
• pp.27-39
• /
• 2024

Soil texture is determined by the proportions of sand, silt, and clay within the soil, which influence characteristics such as porosity, water retention capacity, electrical conductivity (EC), and pH. Traditional classification of soil texture requires significant sample preparation including oven drying to remove organic matter and moisture, a process that is both time-consuming and costly. This study aims to explore an alternative method by developing an AI model capable of predicting soil texture from images of pre-sorted soil samples using computer vision and deep learning technologies. Soil samples collected from agricultural fields were pre-processed using sieve analysis and the images of each sample were acquired in a controlled studio environment using a smartphone camera. Color distribution ratios based on RGB values of the images were analyzed using the OpenCV library in Python. A convolutional neural network (CNN) model, built on PyTorch, was enhanced using Digital Image Processing (DIP) techniques and then trained across nine distinct conditions to evaluate its robustness and accuracy. The model has achieved an accuracy of over 80% in classifying the images of pre-sorted soil samples, as validated by the components of the confusion matrix and measurements of the F1 score, demonstrating its potential to replace traditional experimental methods for soil texture classification. By utilizing an easily accessible tool, significant time and cost savings can be expected compared to traditional methods.

• Nuclear Engineering and Technology
• /
• 제56권3호
• /
• pp.993-1001
• /
• 2024

The TANDEM project is a European initiative funded under the EURATOM program. The project started on September 2022 and has a duration of 36 months. TANDEM stands for Small Modular ReacTor for a European sAfe aNd Decarbonized Energy Mix. Small Modular Reactors (SMRs) can be hybridized with other energy sources, storage systems and energy conversion applications to provide electricity, heat and hydrogen. Hybrid energy systems have the potential to strongly contribute to the energy decarbonization targeting carbon-neutrality in Europe by 2050. However, the integration of nuclear reactors, particularly SMRs, in hybrid energy systems, is a new R&D topic to be investigated. In this context, the TANDEM project aims to develop assessments and tools to facilitate the safe and efficient integration of SMRs into low-carbon hybrid energy systems. An open-source "TANDEM" model library of hybrid system components will be developed in Modelica language which, by coupling, will extend the capabilities of existing tools implemented in the project. The project proposes to specifically address the safety issues of SMRs related to their integration into hybrid energy systems, involving specific interactions between SMRs and the rest of the hybrid systems; new initiating events may have to be considered in the safety approach. TANDEM will study two hybrid systems covering the main trends of the European energy policy and market evolution at 2035's horizon: a district heating network and power supply in a large urban area, and an energy hub serving energy conversion systems, including hydrogen production; the energy hub is inspired from a harbor-like infrastructure. TANDEM will provide assessments on SMR safety, hybrid system operationality and techno-economics. Societal considerations will also be encased by analyzing European citizen engagement in SMR technology safety.