• 한국환경과학회지
• /
• 제26권4호
• /
• pp.521-527
• /
• 2017

Solar radiation forecasts are important for predicting the amount of ice on road and the potential solar energy. In an attempt to improve solar radiation predictability in Jeju, we conducted machine learning with various data mining techniques such as tree models, conditional inference tree, random forest, support vector machines and logistic regression. To validate machine learning models, the results from the simulation was compared with the solar radiation data observed over Jeju observation site. According to the model assesment, it can be seen that the solar radiation prediction using random forest is the most effective method. The error rate proposed by random forest data mining is 17%.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2001년도 춘계학술대회 논문집
• /
• pp.1125-1128
• /
• 2001

A 110mm diameter aspheric metal secondary mirror for a test model of an earth observation satellite camera was fabricated by ultra-precision single point diamond turning(SPDT). Aluminum alloy for mirror substrates is known to be easily machinable, but not polishable due to its ductility. A harder material, Ni, is usually electrolessly coated on an Al substrate to increase the surface hardness for optical polishing. Aspheric metal secondary mirror without a conventional polishing process, the surface roughness of Ra=10nm, and the form error of Ra=λ/12(λ=632nm) has been required. The purpose of this research is to find the optimum machining conditions for reflector cutting of electroless-Ni coated Al alloy and apply the SPDT technique to the manufacturing of ultra precision optical components of metal aspheric reflector.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1999년도 학술발표대회 논문집 제18권 1호
• /
• pp.28-31
• /
• 1999

기존의 문장종속형 화자인식 방법들은 대부분 음성인식에서 사용되는 방법을 그대로 적용하기 때문에, 화자의 개인성 정보보다 음운정보에 더 민감한 단점이 있다. 화자인식 시스템의 성능향상을 위해서는 음운정보보다는 화자의 개인성 정보가 잘 반영되도록 하는 것이 중요하다. 본 논문에서는 HMM(hidden Maxkov model)을 기반으로 한 문장종속형 화자확인 시스템의 성능향상을 위한 관측확률 가중 반법을 제안한다. 먼저 주어진 학습자료에서 화자의 개인성이 잘 반영된 프레임들을 예측한다. 임의의 입력음성에 대한 인식점수는 화자의 특징이 잘 반영된 프레임의 관측확률에 가중치를 주어 구한다. 제안한 방법을 적용한 결과 기존의 우도비(likelihood ratio) 정규화 점수를 사용하는 방법에 비해 동일오류율(EER, equal error rate)을 $2\~3\%$정도 줄여 인식율 향상을 얻을 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.35-37
• /
• 2007

Super resolution using stochastic approach which based on the Bayesian approach is to easy modeling for a priori knowledge. Generally, the Bayesian estimation is used when the posterior probability density function of the original image can be established. In this paper, we introduced the improved MAP algorithm based on Bayesian which is stochastic approach in spatial domain. And we presented the observation model between the HR images and LR images applied with MAP reconstruction method which is one of the major in the SR grid construction. Its test results, which are operation speed, chip size and output high resolution image Quality. are significantly improved.

• 한국정밀공학회지
• /
• 제17권7호
• /
• pp.63-73
• /
• 2000

Internet becomes very common tool for communication and data sharing. Virtual reality(VR) on web browser, and virtual prototyping and virtual manufacturing is widely used in many engineering folds. The reduction of overall development process and error minimization during data conversion becomes very crucial where sharing data via Internet and VR. This paper deals with the advantage and disadvantage of VRML format used in RP(Rapid Prototyping), and a software for RP data preparation is developed. If VRML format as an international standard for VR, is replaced with STL format, the weak points of STL format can be overcome and the technique related to virtual prototyping and virtual manufacturing can be addressed more systematically by sharing the data. The system developed in this work shows a good window to get access to a more realistic observation of an object fur an RP system from a long remote sites in a more systematic way.

• 환경영향평가
• /
• 제18권1호
• /
• pp.31-39
• /
• 2009

A lot of data which are used in environment analysis of air pollution have characteristics that are distributed continuously in space. In this point, the collected data value such as precipitation, temperature, altitude, pollution density, PM10 have spatial aspect. When geostatistical data analysis are needed, acquisition of the value in every point is the best way, however, it is impossible because of the costs and time. Therefore, it is necessary to estimate the unknown values at unsampled locations based on observations. In this study, spatial interpolation method such as local trend surface model, IDW(inverse distance weighted), RBF(radial basis function), Kriging were applied to PM10 annual average concentration of Seoul in 2005 and the accuracy was evaluated. For evaluation of interpolation accuracy, range of estimated value, RMSE, average error were analyzed with observation data. The Kriging and RBF methods had the higher accuracy than others.

• 전기학회논문지
• /
• 제58권10호
• /
• pp.2038-2040
• /
• 2009

This paper studies the state estimation problem for the current of DC/DC boost converters with parasitic inductor resistance. The parasitic resistance increases the system uncertainty when the output load variation occurs. In order to enhance the observation performance of the Luenberger observer this paper includes the integral of the estimation error signal to the estimation algorithm. By using the proposed PI observer the converter current signal is successfully reconstructed with the voltage measurement regardless of the load uncertainty. Computer simulation has been carried out by using Simulink/Sim Power System. Simulation results show the proposed method maintains robust estimation performance against the model uncertainty.

• 대기
• /
• 제29권4호
• /
• pp.417-427
• /
• 2019

The purpose of this study is to build urban canopy model (Met Office Reading Urban Surface Exchange Scheme, MORUSES) based to Unified Model (UM) by using urban building information data in Seoul, and then to compare the improving urban canopy model simulation result with that of Seoul Automatic Weather Station (AWS) observation site data. UM-MORUSES is based on building information database in London, we performed a sensitivity experiment of UM-MOURSES model using urban building information database in Seoul. Geographic Information System (GIS) analysis of 1.5 km resolution Seoul building data is applied instead of London building information data. Frontal-area index and planar-area index of Seoul are used to calculate building height. The height of the highest building in Seoul is 40m, showing high in Yeoido-gu, Gangnam-gu and Jamsil-gu areas. The street aspect ratio is high in Gangnam-gu, and the repetition rate of buildings is lower in Eunpyeong-gu and Gangbuk-gu. UM-MORUSES model is improved to consider the building geometry parameter in Seoul. It is noticed that the Root Mean Square Error (RMSE) of wind speed is decreases from 0.8 to 0.6 m s^-1 by 25 number AWS in Seoul. The surface air temperature forecast tends to underestimate in pre-improvement model, while it is improved at night time by UM-MORUSES model. This study shows that the post-improvement UM-MORUSES model can provide detailed Seoul building information data and accurate surface air temperature and wind speed in urban region.

• 한국해양공학회지
• /
• 제35권4호
• /
• pp.273-286
• /
• 2021

In recent years, as human casualties and property damage caused by hazardous waves have increased in the East Sea, precise wave prediction skills have become necessary. In this study, the Simulating WAves Nearshore (SWAN) third-generation numerical wave model was calibrated and optimized to enhance the accuracy of winter storm wave prediction in the East Sea. We used Source Term 6 (ST6) and physical observations from a large-scale experiment conducted in Australia and compared its results to Komen's formula, a default in SWAN. As input wind data, we used Korean Meteorological Agency's (KMA's) operational meteorological model called Regional Data Assimilation and Prediction System (RDAPS), the European Centre for Medium Range Weather Forecasts' newest 5th generation re-analysis data (ERA5), and Japanese Meteorological Agency's (JMA's) meso-scale forecasting data. We analyzed the accuracy of each model's results by comparing them to observation data. For quantitative analysis and assessment, the observed wave data for 6 locations from KMA and Korea Hydrographic and Oceanographic Agency (KHOA) were used, and statistical analysis was conducted to assess model accuracy. As a result, ST6 models had a smaller root mean square error and higher correlation coefficient than the default model in significant wave height prediction. However, for peak wave period simulation, the results were incoherent among each model and location. In simulations with different wind data, the simulation using ERA5 for input wind datashowed the most accurate results overall but underestimated the wave height in predicting high wave events compared to the simulation using RDAPS and JMA meso-scale model. In addition, it showed that the spatial resolution of wind plays a more significant role in predicting high wave events. Nevertheless, the numerical model optimized in this study highlighted some limitations in predicting high waves that rise rapidly in time caused by meteorological events. This suggests that further research is necessary to enhance the accuracy of wave prediction in various climate conditions, such as extreme weather.

• 한국농림기상학회지
• /
• 제25권4호
• /
• pp.368-375
• /
• 2023

본 연구에서는 농촌진흥청과 홍콩과학기술대학교의 공동 개발로 생산된 1개월 예측 자료의 오차를 분석하고, 통계적 보정 기법을 활용한 오차 개선 효과를 살펴보고자 하였다. 이를 위해 2013년부터 2021년까지의 과거 예측(hindcast) 자료, 기상관측자료, 다양한 환경정보들을 수집하고 다양한 환경 조건에서의 오차 특성을 분석하였다. 최고기온과 최저기온의 경우, 해발고도와 위도가 높을 수록 예측 오차가 더 크게 나타났다. 평균적으로, 선형회귀모형과 XGBoost로 보정한 예측자료는 보정 전 예측자료보다 각각 0.203, 0.438(최고기온) 및 0.069, 0.390(최저기온) 정도의 RMSE가 감소했으며, 높은 고도와 위도에서의 오차 개선이 더 크게 나타났다. 모든 분석 조건에서 XGBoost가 선형회귀모형보다 우수한 오차 개선 효과를 나타냈다. 본 연구를 통해 예측 자료의 오차가 지형적 조건에 영향을 받는다는 사실을 확인하였고, XGBoost와 같은 기계학습법이 다양한 환경인자들을 고려하여 효과적으로 오차를 개선할 수 있다는 것을 확인하였다.