• 한국환경과학회지
• /
• 제31권9호
• /
• pp.803-813
• /
• 2022

In this study, we improved the water-based condensation particle counter in Atmospheric Research Aircraft NARA and investigated the condensation particle number concentration over the Korean peninsula. Pump and set point information were changed to improve the instrument used by aircraft for observation. Ground-based observational result showed that the error between two instruments, which are water-based condensation particle counter and butanol-based condensation particle counter, was 4.7%. Aerial observational result revealed that the number concentration before improvement indicate large variation with unstable condition, whereas the number concentration after improvement indicate a reasonable variation. After improvement, the number concentration was 706±499 particle/cm³ in the West Sea and 257±80 particle/cm³ in Gangwon-do, and these are similar to the concentration range reported in previous studies. Notably, this is the first attempt to use aerial observation with water-based condensation particle counter to investigate condensation particle number concentration.

• 한국컴퓨터정보학회논문지
• /
• 제28권5호
• /
• pp.9-15
• /
• 2023

본 연구는 신경망을 이용하여 링크 속도로부터 각 차로의 속도를 예측하는 방법을 제시하였다. 예측 정확도를 높이기 위해 학습 데이터 구성에 있어 3가지 사항을 고려하였다. 첫 번째는 링크의 시작점과 끝점이 연결된 14개의 링크를 포함하여 데이터 소스의 공간적 범위를 확장하였다. 또한 시간 간격을 07:00에서 22:00로 늘리고 특성 데이터에 데이터 생성 시각을 포함했다. 마지막으로 요일과 공휴일을 표시했다. 실험 결과 직진 차로는 속도 오차가 6.4km/h에서 5.0km/h로 21.9%, 우회전은 8.5km/h에서 7.4km/h로 12.9%, 좌회전은 8.7km/h에서 8.2km/h로 5.7% 감소한 것으로 나타났다. 두번째 결과로 교통 정체시 도심부 도로의 차선별 예측 정확도가 높은 것을 확인하였다. 제안한 방법의 특징은 도로 소통 상황을 차로 단위로 예측하여 도로 소통 상황을 보다 정확하게 예측한 것이다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.172-172
• /
• 2023

The use of low-cost IoT sensors for flow measurement in open channels has gained significant attention due to their potential to provide continuous and real-time data at a low cost. However, the accuracy and reliability of these sensors in real-world scenarios are not well understood. This study aims to compare the performance of low-cost IoT sensors in the laboratory and real-world conditions to evaluate their accuracy and reliability. Firstly, a low-cost IoT sensor was integrated with an IoT platform to acquire real-time flow rate data. The IoT sensors were calibrated in the laboratory environment to optimize their accuracy, including different types of low-cost IoT sensors (HC-SR04 ultrasonic sensor & YF-S201 sensor) using an open channel prototype. After calibration, the IoT sensors were then applied to a real-world case study in the Dorim-cheon stream, where they were compared to traditional flow measurement methods to evaluate their accuracy.The results showed that the low-cost IoT sensors provided accurate and reliable flow rate data under laboratory conditions, with an error range of less than 5%. However, when applied to the real-world case study, the accuracy of the IoT sensors decreased, which could be attributed to several factors such as the effects of water turbulence, sensor drift, and environmental factors. Overall, this study highlights the potential of low-cost IoT sensors for flow measurement in open channels and provides insights into their limitations and challenges in real-world scenarios.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• 스마트미디어저널
• /
• 제11권9호
• /
• pp.64-74
• /
• 2022

해양자원을 활용하기 위한 수중 로봇과 관련된 연구가 다수 진행되고 있다. 그러나 일반 드론과 다르게 수중 로봇은 매개체가 공기가 아닌 물이기 때문에 위치 파악이 쉽지 않은 문제점이 존재한다. 수중 위치를 확인하기 위한 기존 연구인 수중 로봇의 모니터링 및 포지셔닝 프로그램은 대규모 공간에서 활용하기 위한 목적을 가지고 있기 때문에 소규모의 공간에서 위치 파악 및 모니터링에 어려움을 가지고 있다. 이에 본 논문에서는 소규모 공간에서 지속적인 모니터링과 명령 전달을 위한 3차원 포지셔닝 프로그램을 제안한다. 제안된 프로그램은 수중 로봇의 위치에 깊이를 확인할 수 있도록 다차원 포지셔닝 모니터링 기능과 3차원 화면을 통해 이동 경로 제어할 수 있는 기능으로 구성된다. 성능평가를 통해 수중 로봇이 수조 모습과 동일하게 출력되어 3차원 화면으로 다양한 각도에서 모니터링 확인이 가능하였으며, 설정 경로와 실제 위치의 차이가 평균 6.44m 이내로써 상정 범위 내의 오차를 확인하였다.

• 대기
• /
• 제32권1호
• /
• pp.27-37
• /
• 2022

The Korean Integrated Model (KIM) forecast system was extended to assimilate Horizontal Line-Of-Sight (HLOS) wind observations from the Atmospheric Laser Doppler Instrument (ALADIN) on board the Atmospheric Dynamic Mission (ADM)-Aeolus satellite. Quality control procedures were developed to assess the HLOS wind data quality, and observation operators added to the KIM three-dimensional variational data assimilation system to support the new observed variables. In a global cycling experiment, assimilation of ALADIN observations led to reductions in average root-mean-square error of 2.1% and 1.3% for the zonal and meridional wind analyses when compared against European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecast System (IFS) analyses. Even though the observable variable is wind, the assimilation of ALADIN observation had an overall positive impact on the analyses of other variables, such as temperature and specific humidity. As a result, the KIM 72-hour wind forecast fields were improved in the Southern Hemisphere poleward of 30 degrees.

• 사물인터넷융복합논문지
• /
• 제9권3호
• /
• pp.61-67
• /
• 2023

구리의 전기주조 공정을 최적화하기 위하여 이중 비밀 다층구조의 역전파 뉴럴 네트워크가 구성된다. 샘플 학습을 통하여, 구리 전기주조 공정 조건과 목표 특성 간의 함수관계가 정확히 성취되고, 구리 전기주조 공정 내에서 다층구조의 미세강도와 장력에 대한 예측이 이루어진다. 예측된 결과는 펄스 전원공급기를 장착한 구리 피로인산염 솔루션 시스템 내에서 구리의 전해석출 시험에 의하여 증명된다. 그 결과는 다음과 같이 나타난다. "3-4-3-2" 구조의 이중비밀 다층구조 뉴럴 네트워크에 의하여 예측된 구리 다층구조의 미세강도와 장력은 실험값에 매우 근접하며 그 상대적 오차는 2.32%보다 작다. 주어진 파라미터의 범위 내에서, 구리의 미세강도는 100.3~205.6MPa이며, 장력은 112~485MPa 정도로 측정된다. 미세강도와 장력이 최적인 조건에서 그에 대응하는 공정 조건은 다음과 같다: 전류밀도는 2A·dm-2, 펄스 주파수는 2KHz, 펄스의 듀티싸이클은 10%이다.

• 한국재료학회지
• /
• 제33권5호
• /
• pp.175-188
• /
• 2023

Water electrolysis holds great potential as a method for producing renewable hydrogen fuel at large-scale, and to replace the fossil fuels responsible for greenhouse gases emissions and global climate change. To reduce the cost of hydrogen and make it competitive against fossil fuels, the efficiency of green hydrogen production should be maximized. This requires superior electrocatalysts to reduce the reaction energy barriers. The development of catalytic materials has mostly relied on empirical, trial-and-error methods because of the complicated, multidimensional, and dynamic nature of catalysis, requiring significant time and effort to find optimized multicomponent catalysts under a variety of reaction conditions. The ultimate goal for all researchers in the materials science and engineering field is the rational and efficient design of materials with desired performance. Discovering and understanding new catalysts with desired properties is at the heart of materials science research. This process can benefit from machine learning (ML), given the complex nature of catalytic reactions and vast range of candidate materials. This review summarizes recent achievements in catalysts discovery for the hydrogen evolution reaction (HER) and oxygen evolution reaction (OER). The basic concepts of ML algorithms and practical guides for materials scientists are also demonstrated. The challenges and strategies of applying ML are discussed, which should be collaboratively addressed by materials scientists and ML communities. The ultimate integration of ML in catalyst development is expected to accelerate the design, discovery, optimization, and interpretation of superior electrocatalysts, to realize a carbon-free ecosystem based on green hydrogen.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2021년도 학술발표회
• /
• pp.161-161
• /
• 2021

본 연구에서는 금강 상류의 용담댐 유역(930.0 km²)을 대상으로 Sentinel-1 SAR(Synthetic Aperture Radar) 및 Sentinel-2 MultiSpectral Instrument(MSI) 위성영상을 활용한 토양수분 산출연구를 수행하였다. 연구에 사용된 자료는 10 m 해상도의 Sentinel-1 IW(Interferometric Wide swath) mode GRD(Ground Range Detected) product의 VV(Vertical transmit-Vertical receive) 및 VH(Vertical transmit-Horizontal receive) 편파자료와 Sentinel-2 Level-2A Bottom of Atmosphere(BOA) reflectance 자료를 2019년에 대해 각 6일 및 5일 간격으로 구축하였다. 위성영상의 Image processing은 SNAP(SentiNel Application Platform)을 활용하여 Sentinel-1 영상의 편파 별(VV, VH) 후방산란계수와 Sentinel-2의 적색(Band-4) 및 근적외(Band-8) 영상을 생성하였다. 토양수분 산출 모형은 다중선형회귀모형(Multiple Linear Regression Model)을 활용하였으며, 각 지점에 해당하는 토양 속성별로 모형을 생성하였다. 모형의 입력자료는 Sentinel-1 위성의 편파별 후방산란계수, Sentinel-1 위성에서 산출된 식생지수 RVI(Radar Vegetation Index)와 Sentinel-2 위성에서 산출된 NDVI(Normalized Difference Vegetation Index)를 활용하여 식생의 영향을 반영하고자 하였다. 모의 된 토양수분을 검증하기 위해 6개 지점의 TDR(Time Domain Reflectometry) 기반 실측 토양수분 자료를 수집하고, 상관계수(Correlation Coefficient, R), 평균제곱근오차(Root Mean Square Error, RMSE) 및 IOA(Index of Agreement)를 활용하여 전체 기간 및 계절별로 나누어 검증할 예정이다.