• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.337-337
• /
• 2023

가뭄은 가장 심각한 기상 재해 중 하나로 농업 생산, 사회경제 등 다양한 분야에 영향을 미친다. 국내의 경우 광주·전남지역이 1990년대 이후 30년 만에 제한 급수 위기에 처하는 역대 최악의 가뭄으로 지역민들은 심각한 피해가 발생하였다. 유럽의 경우 2022년 당시 500년 만에 찾아온 가뭄으로 인해 3분의 2에 해당하는 지역이 피해를 입었으며, 미국 서부 지역은 2000년부터 2021년까지 1200년 만에 가장 극심한 대가뭄을 겪은 것으로 나타났다. 지구온난화에 따른 기후변화로 인해 가뭄의 빈도와 강도가 증가함에 따라 피해도 커질 것으로 예상된다. 가뭄의 부정적인 영향으로 인해 정확하고 신뢰할 수 있는 가뭄 예측 기술이 필요하다. 본 연구에서는 가뭄예측을 위한 입력변수로서 GPM IMERG (The Integrated Multi-satellitE Retrievals for GPM) 강수량 자료와 NOAA에서 제공하는 8가지 북반구 대기패턴 자료 간의 상관성을 분석하였다. 입력변수 간의 상관성과 중장기 가뭄 예측을 위하여 딥러닝 모델 중 시계열 데이터에서 높은 예측 성능을 보이는 LSTM(Long Short Term-Memory)을 적용하여 가뭄을 예측하고자 한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.3
• /
• pp.39-47
• /
• 2016

In this study analysis the status of land cover change and land degradation of Tuul-Basin in Mongolia by using the Landsat satellite images that was taken in year of 1990, 2001 and 2011 respectively in the summer at the time of great growth of green plants. Analysis of the land cover change during time series data in Tuul-Basin, Mongolia and NDVI (Normalized Difference Vegetation Index), SAVI (Soil-Adjusted Vegetation Index) and LST (Land Surface Temperature) algorithm are used respectively. As a result shows, there was a decrease of forest and green area and increase of dry and fallow land in the study area. It was be considered as trends to be a land degradation. In addition, there was high correlation between LST and vegetation index. The land cover change or vitality of vegetation which is taken in study area can be closely related to the temperature of the surface.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1219-1230
• /
• 2022

Multi-spectral drones in agricultural observation require quantitative and reliable data based on physical quantities such as radiance or reflectance in crop yield analysis. In the case of remote sensing data for crop monitoring, images taken in the same area over time-series are required. In particular, biophysical data such as leaf area index or chlorophyll are analyzed through time-series data under the same reference, it can be directly analyzed. So, comparable reflectance data are required. Orthoimagery using drone images, the entire image pixel values are distorted or there is a difference in pixel values at the junction boundary, which limits accurate physical quantity estimation. In this study, reflectance and vegetation index based on drone images were calculated according to the correction method of drone images for time-series crop monitoring. comparing the drone reflectance and ground measured data for spectral characteristics analysis.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.117-130
• /
• 2021

The government's social distancing policy and concerns about COVID-19 are increasing restrictions on outdoor leisure activities. Based on the decrease in outdoor leisure activities and the increase in indoor leisure activities, The purpose of this study is to examine the correlation between the degree of new confirmed cases of COVID-19 and the number of VOD views. This study conducted a time series analysis for 348 days from February 18, 2020 to January 31, 2021. Data were collected from the number of daily VOD views provided by the Korean Film Council and the number of new confirmed cases of COVID-19 provided by the Korea Centers for Disease Control and Prevention. The analysis showed that the number of confirmed COVID-19 cases has a significantly positive effect on the number of daily movie VOD views at the 5% significance level. This results indicate that the more confirmed cases of COVID-10, the more people watch movie VOD as indoor leisure activities. While previous studies examined the relationship between the confirmed cases of COVID-19 and indoor leisure activities in general, this study tried to academically contribute by analyzing the impact on specific indoor leisure activities. The practical implications of this study are as follows. The results of this study show that efficient promotions are possible based on significant social issues, such as infectious diseases. According to the results, promotions that respond quickly to changes are more effective than long-term promotions considering the climate or seasons. Due to the limitations of the data, the current study was conducted based only on PPV, but future research should also consider various billing forms such as PPM and SVOD.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.720-722
• /
• 2019

학령인구의 감소에 따른 대학 구조개혁에 대한 경쟁력 강화 방안의 일환으로 각 대학에서는 다양한 설문조사 및 만족도 조사를 시행하고 있다. 그러나, 대부분의 대학은 설문조사의 통합 관리체계 및 운영 방법의 효율성 그리고 활용 방법에 대한 고려 없이 업무별, 시스템별, 다양한 인터넷 무료 설문조사 시스템을 사용하고 있어 체계적이고 효율적인 설문 관리가 어렵다. 본 논문에서는 대학 내에서 운영되는 모든 설문조사 업무를 통합 관리할 수 있는 권한 모델을 설계하고, 자료를 체계적으로 저장할 수 있는 구조를 만들어, 축적된 데이터에 대한 시계열분석, 상관분석, 회귀분석이 가능한 시스템을 제안한다. 제안된 시스템은 학교의 설문조사 업무를 효율화하고, 대학에 필요한 다양한 분석 방법을 제공하여 대학의 발전에 기여 할 수 있을 것으로 사료된다.

• The Journal of the Korea Contents Association
• /
• v.7 no.3
• /
• pp.176-186
• /
• 2007

As SAR data have the strong point that is not influenced by weather or light amount in comparison with optical sensor data, they are highly useful for temporary analysis and can be collected in time of unforeseen circumstances like disaster. This study is to extract DEM from L-band data of JERS-1 SAR imagery using InSAR and DInSAR processing techniques. As a result of analyzing the extracted coherence and interferogram images, it was shown that the DInSAR 3-pass method produces more suitable coherence values than the InSAR method. The accuracies of DEM extracted from the SAR data were evaluated by employing the DEM derived from the digital topographic maps of 1:5000 scale as reference data. And it was ascertained that baselines between antenna locations largely affect the accuracy of extracted DEM.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.533-535
• /
• 2021

The differences between this study and previous studies are as follows. First, by building a cloud-based system using IoT technology, the system was built to monitor the status of buildings in real time from anywhere with an internet connection. Second, a model for predicting the future was developed using artificial intelligence (LSTM) and statistical (ARIMA) methods for the measured time series sensor data, and the effectiveness of the proposed prediction model was experimentally verified using a scaled-down building model. Third, a method to analyze the condition of a building more three-dimensionally by visualizing the structural deformation of a building by convergence of multiple sensor data was proposed, and the effectiveness of the proposed method was demonstrated through the case of an actual earthquake-damaged building.

• Journal of Korea Water Resources Association
• /
• v.53 no.2
• /
• pp.97-105
• /
• 2020

Recently, Artificial Neural Network receives attention as a data prediction method. Among these, a Long Shot-term Memory (LSTM) model specialized for time-series data prediction was utilized as a prediction method of hydrological time series data. In this study, the LSTM model was constructed utilizing deep running open source library TensorFlow which provided by Google, to predict inflows of multipurpose dams. We predicted the inflow of the Yongdam Multipurpose Dam which is located in the upper stream of the Geumgang. The hourly flow data of Yongdam Dam from 2006 to 2018 provided by WAMIS was used as the analysis data. Predictive analysis was performed under various of variable condition in order to compare and analyze the prediction accuracy according to four learning parameters of the LSTM model. Root mean square error (RMSE), Mean absolute error (MAE) and Volume error (VE) were calculated and evaluated its accuracy through comparing the predicted and observed inflows. We found that all the models had lower accuracy at high inflow rate and hourly precipitation data (2006~2018) of Yongdam Dam utilized as additional input variables to solve this problem. When the data of rainfall and inflow were utilized together, it was found that the accuracy of the prediction for the high flow rate is improved.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.57-66
• /
• 2023

Currently, a new energy system is emerging that implements consumption reduction by improving energy efficiency. Accordingly, as smart grids spread, the rate system by timing is expanding. The rate system by timing is a rate system that applies different rates by season/hour to pay according to usage. In this study, external factors such as temperature/day/time/season are considered and the time series prediction model, LSTM, is used to predict energy power usage data. Based on this energy usage prediction model, energy usage charges are reduced by analyzing usage patterns for each device and transferring power energy from the maximum load time to the light load time. In order to analyze the usage pattern for each device, a clustering technique is used to learn and classify the usage pattern of the device by time. In summary, this study predicts usage and usage fees based on the user's power data usage, analyzes usage patterns by device, and provides customized demand transfer services based on analysis, resulting in cost reduction for users.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.7
• /
• pp.1410-1417
• /
• 2004

In this paper, we propose that the chaotic behavior analysis in the chaotic mobile robot embedding Arnold, equation, Chua's equation and hyper-chaos equation. In order to analysis of chaotic behavior in the mobile robot, we apply not only qualitative analysis such as time-series, embedding phase plane, but also quantitative analysis such as Lyapunov exponent in the mobile robot with obstacle.