• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제4권11호
• /
• pp.521-528
• /
• 2015

도로주행 영상에서의 객체 검출에 관한 기존의 연구들은 날씨 및 조명 상태에 따른 객체 검출의 어려움 때문에 대부분 맑은 날씨의 영상을 대상으로 연구가 진행되었다. 본 논문에서는 도로주행 영상의 다양한 날씨 및 조명 상태를 먼저 판단하고, 이를 기반으로 도로 이정표에 대한 색상모델을 설정하여 이정표 객체를 찾는 방법을 제안한다. 제안한 방법은 5종류의 도로 이미지 특징을 이용하여 맑음, 흐림, 비, 야간, 역광으로 날씨 및 조명 상태를 먼저 분류하고, 각각의 상태에서 대상 이정표 색상의 픽셀값의 범위를 추출하여 GMM(Gaussian Mixture Model)을 생성하고 이를 객체 추출에 사용한다. 날씨 및 조명이 다양하게 변하는 도로주행 영상에 제안한 방법을 적용하여 이정표 영역이 안정적으로 찾아지는 것을 확인할 수 있었다.

• 응용통계연구
• /
• 제22권1호
• /
• pp.221-235
• /
• 2009

This manuscript illustrates the comparative study between ARIMA and Exponential Smoothing modeling to develop forest fire forecasting system using different weather parameters. In this paper, authors have developed the most suitable and closest forecasting models like ARIMA and Exponential Smoothing techniques using different weather parameters. Authors have considered the extremes of the Wind speed, Radiation, Maximum Temperature and Deviation Temperature of the Summer Season form March to June month for the Ranchi Region in Jharkhand. The data is taken by own resource with the help of Automatic Weather Station. This paper consists a deep study of the effect of extreme values of the different parameters on the weather fluctuations which creates forest fires in the region. In this paper, the numerical illustration has been incorporated to support the present study. Comparative study of different suitable models also incorporated and best fitted model has been tested for these parameters.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.794-797
• /
• 2024

Despite advancements in deep learning, existing semantic segmentation models exhibit suboptimal performance under adverse weather conditions, such as fog or rain, whereas they perform well in clear weather conditions. To address this issue, much of the research has focused on making image or feature-level representations weather-independent. However, disentangling the style and content of images remains a challenge. In this work, we propose a novel fine-tuning method, 'freeze-n-update.' We identify a subset of model parameters that are weather-independent and demonstrate that by freezing these parameters and fine-tuning others, segmentation performance can be significantly improved. Experiments on a test dataset confirm both the effectiveness and practicality of our approach.

• 한국태양에너지학회 논문집
• /
• 제33권5호
• /
• pp.9-17
• /
• 2013

Hourly horizontal global solar radiation has been used as one of significant parameters in a weather file for building energy simulations, which determines the quality of building thermal performance. However, as about twenty two weather stations in Korea have actually measured the horizontal global sola radiation, the weather files collected in other stations requires solar data simulation from the other meteorological parameters. Thus, finding the reliable complicated method that can be used in various weather conditions in Korea is critically important. In this paper, three solar simulation models were selected and evaluated through the reliability test with the simulated hourly horizontal global solar radiation against the actually measured solar data to find the most suitable model for the south east area of Korea. Three selected simulation models were CRM, ZHM, and MRM. The first two models are regression type models using site-fitted coefficients which are derived from the correlation between measured solar data and local meteorological parameters from the previous years, and the last model is a mechanistic type model using the meteorological data to calculate conditions of atmospheric constituents that cause absorption and scattering of the extraterrestrial radiation on the way to the surface on the Earth. The evaluation results show that ZHM is the most reliable model in this area, yet a complicated hybrid simulation methods applying the advantages of each simulation method with the monthly-based weather data is needed.

• The Plant Pathology Journal
• /
• 제36권1호
• /
• pp.54-66
• /
• 2020

This study was conducted to evaluate usefulness of numerical weather prediction data generated by the Unified Model (UM) for plant disease forecast. Using the UM06- and UM18-predicted weather data, which were released at 0600 and 1800 Universal Time Coordinated (UTC), respectively, by the Korea Meteorological Administration (KMA), disease forecast on bacterial grain rot (BGR) of rice was examined as compared with the model output based on the automated weather stations (AWS)-observed weather data. We analyzed performance of BGRcast based on the UM-predicted and the AWS-observed daily minimum temperature and average relative humidity in 2014 and 2015 from 29 locations representing major rice growing areas in Korea using regression analysis and two-way contingency table analysis. Temporal changes in weather conduciveness at two locations in 2014 were also analyzed with regard to daily weather conduciveness (C_i) and the 20-day and 7-day moving averages of C_i for the inoculum build-up phase (C_inc) prior to the panicle emergence of rice plants and the infection phase (C_inf) during the heading stage of rice plants, respectively. Based on C_inc and C_inf, we were able to obtain the same disease warnings at all locations regardless of the sources of weather data. In conclusion, the numerical weather prediction data from KMA could be reliable to apply as input data for plant disease forecast models. Weather prediction data would facilitate applications of weather-driven disease models for better disease management. Crop growers would have better options for disease control including both protective and curative measures when weather prediction data are used for disease warning.

• 천문학회보
• /
• 제35권1호
• /
• pp.32.1-32.1
• /
• 2010

KASI's Solar and Space Weather Research Group (SSWRG) is actively involved in solar and space weather research. Since its inception, the SSWRG has been utilizing ground-based assets for its research, such as the Solar Flare Telescope, Solar Imaging Spectrograph, and Sunspot Telescope. In 2007 SSWRG initiated the Korean Space Weather Prediction Center (KSWPC). The goal of KSWPC is to extend the current ground observation capabilities, construct space weather database and networking, develop prediction models, and expand space weather research. Beginning in 2010, SSWRG plans to expand its research activities by collaborating with new international partners, continuing the development of space weather prediction models and forecast system, and phasing into developing and launching space-based assets. In this talk, we will report on KASI's recent activities of international collaborations with NASA for STEREO (Solar Terrestrial Relations Observatory), SDO (Solar Dynamic Observatory), and Radiation Belt Storm Probe (RBSP).

• 응용통계연구
• /
• 제29권1호
• /
• pp.145-155
• /
• 2016

이 논문에서는 기상에 따른 고령 환자의 질병 발생빈도를 예측하는 방법을 비교한다. 분석을 위해 건강보험심사평가원의 고령 환자 의료 자료와 기상청 자료를 주별, 권역별로 병합한다. 기상에 영향을 받는 질병의 주별 발생 빈도를 ARMAX모형, VARMAX모형, TSCS회귀모형으로 분석하고 MSE, MAPE, MAE 기준으로 모형을 비교했다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.150-150
• /
• 2018

The Numerical Weather Prediction (NWP) models provide information for weather forecasts. The highly nonlinear and complex interactions in the atmosphere are simplified in meteorological models through approximations and parameterization. Therefore, the simplifications may lead to biases and errors in model results. Although the models have improved over time, the biased outputs of these models are still a matter of concern in meteorological and hydrological studies. Thus, bias removal is an essential step prior to using outputs of atmospheric models. The main idea of statistical bias correction methods is to develop a statistical relationship between modeled and observed variables over the same historical period. The Model Output Statistics (MOS) would be desirable to better match the real time forecast data with observation records. Statistical post-processing methods relate model outputs to the observed values at the sites of interest. In this study three methods are used to remove the possible biases of the real-time outputs of the Weather Research and Forecast (WRF) model in Imjin basin (North and South Korea). The post-processing techniques include the Linear Regression (LR), Linear Scaling (LS) and Power Scaling (PS) methods. The MOS techniques used in this study include three main steps: preprocessing of the historical data in training set, development of the equations, and application of the equations for the validation set. The expected results show the accuracy improvement of the real-time forecast data before and after bias correction. The comparison of the different methods will clarify the best method for the purpose of the forecast skill enhancement in a real-time case study.

• 응용통계연구
• /
• 제25권2호
• /
• pp.351-362
• /
• 2012

일기 산출기 모형은 가상의 일기 자료를 생성하는 통계 모형이다. 본 연구는 시공간 상관성이 고려된 다중지점에서의 일기산출 모형을 제안하고, 온실가스 배출 미래 시나리오에 따라 강수량과 평균 기온 일기산출이 가능한 알고리즘을 개발하였다. 제안된 알고리즘은 다단계 일반화 선형모형 하에서 필요한 모수들을 추정하고, 적합된 모형 하에서 일기변수들을 랜덤하게 산출하는 절차이다. 과거 30년간 관측된 우리나라 4대강 유역의 일 강수량 자료와 평균 기온 자료를 가지고 모형을 적합하고, 미래 일별 일기자료 산출에 적용하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 추계학술대회 논문집 전력기술부문
• /
• pp.35-38
• /
• 2005

This paper suggests the method that forecast Dynamic Line Rating (DLR). Thermal Overload Risk (TOR) of next time is forecasted based on current weather condition and DLR value by Monte Carlo Simulation (MCS). To model weather element of transmission line for MCS, we will propose the use of weather forecast system and statistical models that time series law is applied. Also, through case study, forecasted TOR probability confirmed can utilize by standard that decide DLR of next time. In short, proposed method may be used usefully to keep safety of transmission line and reliability of supply of electric Power by forecasting transmission capacity of next time.