• Journal of Korean Society on Water Environment
• /
• v.27 no.3
• /
• pp.273-285
• /
• 2011

This study describes the modeling of climate change impact on runoff across southeast Korea using a conceptual rainfall-runoff model TANK and assesses the results using the concept of environmental flows developed by International Water Management Institute. The future climate time series is obtained by scaling the historical series, informed by 4 global climate models and 3 greenhouse gas emission scenarios, to reflect a $4.0^{\circ}C$ increase at most in average surface air temperature and 31.7% increase at most in annual precipitation, using the spatio-temporal changing factor method that considers changes in the future mean seasonal rainfall and potential evapotranspiration as well as in the daily rainfall distribution. Although the simulation results from different global circulation models and greenhouse emission scenarios indicate different responses in flows to the climate change, the majority of the modeling results show that there will be more runoff in southeast Korea in the future. However, there is substantial uncertainty, with the results ranging from a 5.82% decrease to a 48.15% increase in the mean annual runoff averaged across the study area according to the corresponding climate change scenarios. We then assess the hydrologic perturbations based on the comparison between present and future flow duration curves suggested by IMWI. As a result, the effect of hydrologic perturbation on aquatic ecosystems may be significant at several locations of the Nakdong river main stream in dry season.

• The Journal of Engineering Geology
• /
• v.30 no.4
• /
• pp.447-456
• /
• 2020

The study area is a slope in Dogye-eup, Samcheok-si, Gangwon-do. The cutting method was applied to this slope for stabilization in 2009 due to the influence of the waste-rock dump located at the top of slope. Recently, soil cracks and creep have occurred on this slope, and the drainage channel was damaged. Therefore, it was analyzed the topography change through photogrammetry using a UAV. Orthophotos were taken in April and October 2019 respectively. From the Orthophots, Digital Surface Model (DSM) was extracted. Time series analysis was performed by comparing each DSM. The topography of October was pushed forward while maintaining the topography of April. Through these features, it is judged that the soil creep is occurring in this study area.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.73-82
• /
• 2020

Most process date such as semiconductor and petrochemical processes, autocorrelation often exists between observed data, but when the existing SPC(Statistical process control) is applied to these processes, it is not possible to effectively detect the average change of the process. In this paper, when the average change of a certain size occurs in the process data following a specific time series model, the average of the residuals changes according to the passage of time, and the change pattern of the average is introduced around the ARMA(1,1) process. Based on this result, the reference value required in the design process of the CUSUM (Cumulative sum) control chart is appropriately considered by considering the type of the time series model of the process data of the CUSUM control chart that can detect small mean changes in the process and the width of the process mean change of interest. It was confirmed through simulation that it should be selected and used.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.7-13
• /
• 2021

This study develops an artificial intelligence prediction system for Fine particulate Matter(PM2.5) based on the deep learning algorithm GAN model. The experimental data are closely related to the changes in temperature, humidity, wind speed, and atmospheric pressure generated by the time series axis and the concentration of air pollutants such as SO2, CO, O3, NO2, and PM10. Due to the characteristics of the data, since the concentration at the current time is affected by the concentration at the previous time, a predictive model for recursive supervised learning was applied. For comparative analysis of the accuracy of the existing models, CNN and LSTM, the difference between observation value and prediction value was analyzed and visualized. As a result of performance analysis, it was confirmed that the proposed GAN improved to 15.8%, 10.9%, and 5.5% in the evaluation items RMSE, MAPE, and IOA compared to LSTM, respectively.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.58-73
• /
• 2022

The purpose of this study is to construct a predictable estimation model that reflects the relationship between the variables of mobile app performance and to verify how app reviews affect app performance. In study 1 and 2, the relationship between app performance indicators was derived using correlation analysis and random forest regression estimation of machine learning, and app performance estimation modeling was performed. In study 3, sentiment scores for app reviews were by using sentiment analysis of text mining, and it was found that app review sentiment scores have an effect one lag ahead of the number of daily installations of apps when using multivariate time series analysis. By analyzing the dissatisfaction and needs raised by app performance indicators and reviews of apps, companies can improve their apps in a timely manner and derive the timing and direction of marketing promotions.

• Geophysics and Geophysical Exploration
• /
• v.24 no.4
• /
• pp.171-179
• /
• 2021

We outline a process for estimating Cole-Cole parameters from time-domain induced polarization (IP) data. The IP transients are all inverted to 2D Cole-Cole earth models that include resistivity, chargeability, relaxation time, and the frequency exponent. Our inversion algorithm consists of two stages. We first convert the measured voltage decay curves into time series of current-on time apparent resistivity to circumvent the negative chargeability problem. As a first step, a 4D inversion recovers the resistivity model at each time channel that increases monotonically with time. The desired intrinsic Cole-Cole parameters are then recovered by inverting the resistivity time series of each inversion block. In the second step, the Cole-Cole parameters can be estimated readily by setting the initial model close to the true value through a grid search method. Finally, through inversion procedures applied to synthetic data sets, we demonstrate that our algorithm can image the Cole-Cole earth models effectively.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.493-510
• /
• 2021

Mineral wool is an insulation material commonly used in passive fire protection (PFP) systems on offshore installations. Insulation materials have only been considered functional materials for thermal analysis in the conventional offshore PFP system design method. Hence, the structural performance of insulation has yet to be considered in the design of PFP systems. However, the structural elements of offshore PFP systems are often designed with excessive dimensions to satisfy structural requirements under external loads such as wind, fire and explosive pressure. To verify the structural contribution of insulation material, it was considered a structural material in this study. A series of material tensile tests was undertaken with two types of mineral wool at room temperature and at elevated temperatures for fire conditions. The mechanical properties were then verified with modified methods, and a database was constructed for application in a series of nonlinear structural and thermal finite-element analyses of an offshore bulkhead-type PFP system. Numerical analyses were performed with a conventional model without insulation and with a new suggested model with insulation. These analyses showed the structural contribution of the insulation in the structural behaviour of the PFP panel. The results suggest the need to consider the structural strength of the insulation material in PFP systems during the structural design step for offshore installations.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.1
• /
• pp.35-48
• /
• 2023

In this study, we introduced the development status and the government policy of the Chinese automobile industry under the rapidly changing global economic environment. We conducted a consumer trend survey on automobile purchases by consumers in China. Despite the Chinese government's strong national emission control policy and stricter standards for manufacturing and selling internal combustion engine vehicles, 59.6% of respondents saying they would choose an internal combustion engine vehicle when purchasing a vehicle in the future for various reasons. It was confirmed that there is a significant gap between government policies and consumer perceptions. In addition, we have discovered the recent declining trend of automobile sales in China, and used the monthly sales volume from January 2010 to December 2020 as training set, and the sales volume from January 2021 to November 2022 as a test set. We proposed and evaluated a time-series model for predicting future automobile demand in China. Then, we showed the monthly sales forecast for 2023 when each model was applied.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.23-30
• /
• 2022

Deep learning analyzes data to discover a series of rules and anticipates the future, helping us in various ways in our lives. For example, prediction of stock prices and agricultural prices. In this research, the results of solar photovoltaic power generation accompanied by weather are analyzed through deep learning in situations where the importance of solar energy use increases, and the amount of power generation is predicted. In this research, we propose a model using LSTM(Long Short Term Memory network) that stand out in time series data prediction. And we compare LSTM's performance with CNN(Convolutional Neural Network), which is used to analyze various dimensions of data, including images, and CNN-LSTM, which combines the two models. The performance of the three models was compared by calculating the MSE, RMSE, R-Squared with the actual value of the solar photovoltaic power generation performance and the predicted value. As a result, it was found that the performance of the LSTM model was the best. Therefor, this research proposes predicting solar photovoltaic power generation using LSTM.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.456-462
• /
• 2022

In this paper, we introduce a method of predicting time offset by applying LSTM, a deep learning model, to a precision time comparison technique based on measurement data extracted from code signals transmitted from GPS satellites to determine Universal Coordinated Time (UTC). First, we introduce a process of extracting time information from code signals received from a GPS satellite on a daily basis and constructing a daily time offset into one time series data. To apply the deep learning model to the constructed time offset time series data, LSTM, one of the recurrent neural networks, was applied to predict the time offset of a GPS satellite. Through this study, the possibility of time offset prediction by applying deep learning in the field of GNSS precise time transfer was confirmed.