• 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 Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.73-82
• /
• 2019

Recently, as the occurrence frequency of sudden floods due to climate change increased, the flood damage on riverside social infrastructures was extended so that there has been a threat of overflow. Therefore, a rapid prediction of potential flooding in riverside social infrastructure is necessary for administrators. However, most current flood forecasting models including hydraulic model have limitations which are the high accuracy of numerical results but longer simulation time. To alleviate such limitation, data driven models using artificial neural network have been widely used. However, there is a limitation that the existing models can not consider the time-series parameters. In this study the water surface elevation of the Hangang River bridge was predicted using the NARX model considering the time-series parameter. And the results of the ANN and RNN models are compared with the NARX model to determine the suitability of NARX model. Using the 10-year hydrological data from 2009 to 2018, 70% of the hydrological data were used for learning and 15% was used for testing and evaluation respectively. As a result of predicting the water surface elevation after 3 hours from the Hangang River bridge in 2018, the ANN, RNN and NARX models for RMSE were 0.20 m, 0.11 m, and 0.09 m, respectively, and 0.12 m, 0.06 m, and 0.05 m for MAE, and 1.56 m, 0.55 m and 0.10 m for peak errors respectively. By analyzing the error of the prediction results considering the time-series parameters, the NARX model is most suitable for predicting water surface elevation. This is because the NARX model can learn the trend of the time series data and also can derive the accurate prediction value even in the high water surface elevation prediction by using the hyperbolic tangent and Rectified Linear Unit function as an activation function. However, the NARX model has a limit to generate a vanishing gradient as the sequence length becomes longer. In the future, the accuracy of the water surface elevation prediction will be examined by using the LSTM model.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.437-445
• /
• 2000

The present paper is introducing a new model so called TAR-GARCH in the context of stock price analysis Conventional models such as AR(l), TAR(l), ARCH(I) and GARCH( 1,1) are briefly reviewed and TAR-GARCH is suggested in analyizing domestic stock prices. Also, relevant iterative estimation procedure is developed. It is seen that TAR-GARCH provides the better fit relative to traditional first order models for stock prices data in Korea.

• Journal of Korea Port Economic Association
• /
• v.32 no.2
• /
• pp.59-71
• /
• 2016

This study empirically examines the dynamic specification of the ship price model based on a vector autoregressive model and data covering from January 2000 to October 2014. Our results are summarized as follows: first, the relationship between ship price and interest rate shows significantly negative and the relationship between ship price and freight rate shows positive. It provides consistent implication that ship price depends on interest rate and freight rate under the dynamic Gordon model. Second, we apply an impulse response analysis to ship price and find the responses of the ship price from both factors, interest rate and freight rate, which affect during seven periods approximately. Finally, the results of a variance decomposition indicate that freight rate is more important than interest rate on the ship price.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.108-118
• /
• 2018

Recently, agricultural sector apply ICT technology such as Smart Farm to pursue innovation in the changing situation that is emerging as the fourth industrial revolution. However, this innovation requires techniques for forecasting and analyzing in various data bases and spatial information provides such infrastructure data. In this study, the cultivation area of Chinese cabbage, radish, garlic, onion, and red pepper were calculated and analyzed by year. The purpose of this analysis is to cope with sudden changes in vegetable crops and changes in cultivated area caused by weather changes to supply and demand of major vegetables and price instability. As a result of this study, spatial information based on time series information of vegetable complex will be used as efficient agricultural environment observation data, as well as interpretation of various spatial ranges such as the estimation of cultivation area using remote sensing.

• Journal of Korea Water Resources Association
• /
• v.32 no.6
• /
• pp.731-740
• /
• 1999

Autocorrelation function is widely used as a tool measuring linear dependence of hydrologic time series. However, it may not be appropriate for choosing decorrelation time or delay time ${\tau}_d$ which is essential in nonlinear dynamics domain and the mutual information have recommended for measuring nonlinear dependence of time series. Furthermore, some researchers have suggested that one should not choose a fixed delay time ${\tau}_d$ but, rather, one should choose an appropriate value for the delay time window ${\tau}_d={\tau}(m-1)$, which is the total time spanned by the components of each embedded point for the analysis of chaotic dynamics. Unfortunately, the delay time window cannot be estimated using the autocorrelation function or the mutual information. Basically, the delay time window is the optimal time for independence of time series and the delay time is the first locally optimal time. In this study, we estimate general dependence of hydrologic time series using the C-C method which can estimate both the delay time and the delay time window and the results may give us whether hydrologic time series depends on its linear or nonlinear characteristics which are very important for modeling and forecasting of underlying system.

• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.297-308
• /
• 2020

We focus on the functional autoregressive conditional heteroscedasticity (fARCH) modelling to analyze intraday volatilities based on high frequency financial time series. Multivariate volatility models are investigated to approximate fARCH(1). A formula of multi-step ahead volatilities for fARCH(1) model is derived. As an application, in implementing fARCH(1), a choice of appropriate time interval for the intraday return is discussed. High frequency KOSPI data analysis is conducted to illustrate the main contributions of the article.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.421-421
• /
• 2012

본 연구의 목적은 SWAT (Soil and Water Assessment Tool) 모형을 이용하여 기후변화가 다목적 댐 유역의 방류량에 미치는 영향을 분석하는 것으로, 연구 대상 유역은 북동부 산악지역에 위치한 충주댐 및 충주조정지댐을 유역 출구로 하는 다목적댐유역(충주댐 유역: $8360km^2$)이다. 모형유역의 32개 AWS와 10개 기상관측소의 강우 및 기상자료를 입력 하였으며, 모형의 검보정을 위해 댐 상 하류 4개 지점(영월1, 영월2, 충주댐, 충주조정지댐) 수위, 방류량 측정자료를 이용하였다. 미래 기후변화가 댐유역에 미치는 영향 분석을 위하여 IPCC (Intergovermental Panel on Climate Change)에서 제공하는 SRES (Special Report on Emission Scenarios) MIROC3.2 hires 모델 AIB와 B1 시나리오를 사용하였으며, LARS-WG (Long Ashton Research Station Weather Generator)를 사용하여 유역 규모의 기후자료를 상세화 하였다. 모형의 결과를 토대로 미래 2040s(2020년-2059년)와 2080s(2060년-2099년)의 환경유지유량을 추정하고, 미래 댐 유입량과 수위 관리의 시계열 변화를 예측하여 관리방안을 제시하고자 한다.

• Korea Trade Review
• /
• v.46 no.6
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• The Korean Journal of Financial Management
• /
• v.23 no.1
• /
• pp.49-67
• /
• 2006

This study examines whether won/dollar futures have price discovery function and volatility spillover effect or not, using intraday won/dollar futures prices, volumes, and spot rates for the interval from March 2, 2005 through May 30, 2005. Futures prices and spot rates are non-stationary, but there is the cointegration relationship between two time series. Futures returns, spot returns, and volumes are stationary. Asymmetric effects on volatility in futures returns and spot returns does not exist. Analytical results of mean equations of the BGARCH-EC (bivariate GARCH-error correction) model show that the increase of futures returns raise spot returns after 5 minutes, which implies that futures returns lead spot returns and won/dollar futures have price discovery function. In addition, the long-run equilibrium relationship between the two returns could help forecast spot returns. Analytical results of variance equations indicate that short-run innovations in the futures market positively affect the conditional variances of spot returns, that is, there is the volatility spillover effect in the won/dollar futures market. A dummy variable of volumes does not have an effect on two returns but influences significantly on two conditional variances.