• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.129-140
• /
• 2017

Weather acts through low visibility, precipitation, high winds, and temperature extremes to affect driver capabilities, vehicle performance (i.e., traction, stability and maneuverability), pavement friction, roadway infrastructure, crash risk, traffic flow, and agency productivity. Recently a variety of road weather big data sources such as CCTV, road sensor/systems, car sensor have been developed to solve the weather-related problems, This study identifies and defines the types and characteristics of these sources to suggest how to utilize them for car safety and efficiency as well as road management through analyzing domestic and oversea cases of road weather big data applications.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.271-272
• /
• 2017

본 논문에서는 교통사고 데이터베이스 구축을 통해 교통사교 현황과 사고 당시의 여러 정황들을 파악할 수 있는 정보를 제공한다. 이 정보들에는 사고 당시의 기상상태, 도로형태, 차종, 연령, 성별 등의 데이터들이 포함되고 이러한 정보들을 바탕으로 데이터베이스 사용자들은 각 사고 별 종합적인 정보를 얻을 수 있다. 이를 통해 정부 당국 외에 보험사 등에 교통사고 관련 정책을 위한 유용한 정보들을 제공할 수 있다. 또한 운전자 개인들에게도 정보들을 제공해 교통사고를 보다 효율적으로 예방할 수 있다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.39-44
• /
• 2023

Renewable energy such as solar and wind power is a resource that is sensitive to weather conditions and environmental changes. Since the amount of power generated by a facility can vary depending on the installation location and structure, it is important to accurately predict the amount of power generation. Using meteorological data, a data preprocessing process based on principal component analysis was conducted to monitor the relationship between features that affect energy production prediction. In addition, in this study, the prediction was tested by reconstructing the dataset according to the sensitivity and applying it to the machine learning model. Using the proposed model, the performance of energy production prediction using random forest regression was confirmed by predicting energy production according to the meteorological environment for new and renewable energy, and comparing it with the actual production value at that time.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.5
• /
• pp.480-488
• /
• 2018

The development of information and communication technology has been carried out actively in the field of agriculture to generate valuable information from large amounts of data and apply big data technology to utilize it. Crops and their varieties are determined by the influence of the natural environment such as temperature, precipitation, and sunshine hours. This paper derives the climatic factors affecting the production of crops using the garlic growth process and daily meteorological variables. A prediction model was also developed for the production of garlic per unit area. A big data analysis technique considering the growth stage of garlic was used. In the exploratory data analysis process, various agricultural production data, such as the production volume, wholesale market load, and growth data were provided from the National Statistical Office, the Rural Development Administration, and Korea Rural Economic Institute. Various meteorological data, such as AWS, ASOS, and special status data, were collected and utilized from the Korea Meteorological Agency. The correlation analysis process was designed by comparing the prediction power of the models and fitness of models derived from the variable selection, candidate model derivation, model diagnosis, and scenario prediction. Numerous weather factor variables were selected as descriptive variables by factor analysis to reduce the dimensions. Using this method, it was possible to effectively control the multicollinearity and low degree of freedom that can occur in regression analysis and improve the fitness and predictive power of regression analysis.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.429-429
• /
• 2019

최근 들어 이상기후 등 다양한 환경적 요인으로 인해 국지적이고 집중적인 호우가 빈발하고 있으며 도로상의 교통체증과 도로재해가 사회적으로 큰 문제가 되고 있다. 이러한 문제를 해결하기 위해서는 실시간, 단기간 이동성 강우정보 기술과 도로 기상정보를 활용할 수 있는 방법에 대한 연구가 필요하다. 본 연구는 차량의 AW(AutoWiping) 기능을 위해 장착된 강우센서를 이용하여 강우정보를 생산하는 기술을 개발하고자 하였다. 강우센서는 총 4개의 채널로 이루어져있고, 초당 250개의 광신호 데이터를 수집하며, 1시간이면 약 360만 개의 데이터가 생산되게 된다. 5단계의 인공강우를 재현하여 실내 인공강우실험을 실시하고 이를 통해 강우센서 데이터와 강우량과의 상관성을 W-S-R관계식으로 정의하였다. 실내실험데이터와 비교하여 외부환경 및 데이터 생성조건이 다른 실외 데이터의 누적값을 계산하기 위해 Threshold Map 방식을 개발하였다. 강우센서에서 생산되는 대량의 데이터를 이용하여 실시간으로 정확한 강우정보를 생산하기 위해 빅 데이터 처리기법을 사용하여 계산된 실내 데이터의 Threshold를 강우강도 및 채널에 따라 평균값을 계산하고 $4{\times}5$ Threshold Map(4 = 채널, 5 = 강우정보 사상)을 생성하였고 강우센서 기반의 강우정보 생산에 적합한 빅데이터 처리기법을 선정하기 위하여 빅데이터 처리기법 중 Gradient Descent와 Optima Rainfall Intensity을 적용하여 분석하고 결과를 지상 관측강우와 비교검증을 하였다. 이 결과 Optima Rainfall Intensity의 적합도를 검증하였고 실시간으로 관측한 8개 강우사상을 대상으로 강우센서 강우를 생산하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.305-306
• /
• 2015

최근에 WIFI를 사용하여 무선 인터넷을 접속하는 기기들의 증가로 인터넷을 사용하는 기기는 갈수록 증가하고 있다. 이에 맞춰 유무선 공유기의 수도 증가하고 있다. 본 논문에서는 핸드폰 사용자들이 WiFi 환경하에서 최적의 AP에 접속할 수 있도록 WiFi 기상도를 설계하고 구현하였다. 구현된 앱을 활용하여 사용자들은 주변의 AP 정보를 서버에 전달하는 센서 역할을 하며 다수의 사용자들에 의해 수집된 정보는 빅데이터 분석을 통해 최적의 AP를 선정할수 있는 정보로 분석되어 사용자들이 최적의 AP에 접속할 수 있도록 활용될 수 있다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.107-117
• /
• 2020

With the recent development of autonomous vehicles, various sensors installed in vehicles have become common, and big data generated from those sensors is increasingly being used in the transportation field. In this study, we proposed a grid index method to efficiently process real-time vehicle sensing big data and public data such as road weather. The applicability and effect of the proposed grid space division method and grid ID generation method were analyzed. We created virtual data based on DTG data and mapped to the road link based on coordinates. As a result of analyzing the data processing speed in grid index method, the data processing performance improved by more than 2,400 times compared to the existing link unit processing method. In addition, in order to analyze the efficiency of the proposed technology, the virtually generated data was mapped and visualized.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.133-146
• /
• 2021

Providing weather information on roads today means that the road weather conditions near weather observation points are presented to road managers and road users. These weather observation points are managed by the Korea Meteorological Administration. However, it is difficult to provide accurate weather information due to physical limitations such as the presence of precipitation collection points, distance to weather information provision roads, and the presence of mountains. Therefore, this study intends to perform a comparative analysis by time zone and administrative dong provided by the Meteorological Administration using the wiper information among the information contained in the PVD(Probe Vehicle Data) collected from the highway C-ITS project. As a result of the analysis it was possible to detect rainfall even in the event of local rainfall and rainfall over a long period of time and the higher the cumulative precipitation per hour, the higher the probability of coincidence. This study is meaningful because it used PVD to solve the limitations of the existing road weather information provision method and suggested utilization plan for PVD.

• The Journal of Engineering Geology
• /
• v.30 no.4
• /
• pp.663-671
• /
• 2020

Recently, there have been many natural disasters in Korea, not only in forest areas but also in urban areas, and the national requirements for them are increasing. In particular, there is no pre-disaster information system that can systematically manage the collapse of the slope of the national highway. In this study, big data analysis was conducted on the factors causing slope collapse based on the detailed investigation report on the slope collapse of national roads in Gangwon-do and Gyeongsang-do areas managed by the Cut Slope Management System (CSMS) and the basic survey of slope failures. Based on the analysis results, a slope collapse risk prediction model was established through Adaboost, a classification-based machine learning model, reflecting the collapse slope location and weather information. It also developed a visualization map for the risk of slope collapse, which is a visualization program, to show that it can be used for preemptive disaster prevention measures by identifying the risk of slope due to changes in weather conditions.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.3
• /
• pp.135-143
• /
• 2020

Shortwave radiation and sunshine hours (SHOUR) are important variables having many applications, including crop growth. However, observational data for these variables have low horizontal resolution, rendering its application to related research and decision making on f arming practices challenging. In the present study, hourly solar radiation data were physically generated using the Land-Atmosphere Modeling Package (LAMP) at the National Center f or Agro-Meteorology, and then daily SHOUR fields were calculated through statistical downscaling. After data quality evaluation, including case studies, the SHOUR data were added to the existing publically accessible LAMP daily database. The LAMP daily dataset, newly updated with SHOUR, has been provided operationally as input data to the "Gyeonggi-do Agricultural Drought Prediction System," which predicts agricultural weather disasters and field crop growth status.