• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.1
• /
• pp.84-93
• /
• 2018

In this paper, we propose an Elman recurrent neural network to predict and analyze a time series of power energy consumption. To this end, we consider the volatility of the time series and apply the sample variance and the detrended fluctuation analyses to the volatilities. We demonstrate that there exists a correlation in the time series of the volatilities, which suggests that the power consumption time series contain a non-negligible amount of the non-linear correlation. Based on this finding, we adopt the Elman recurrent neural network as the model for the prediction of the power consumption. As the simplest form of the recurrent network, the Elman network is designed to learn sequential or time-varying pattern and could predict learned series of values. The Elman network has a layer of "context units" in addition to a standard feedforward network. By adjusting two parameters in the model and performing the cross validation, we demonstrated that the proposed model predicts the power consumption with the relative errors and the average errors in the range of 2%~5% and 3kWh~8kWh, respectively. To further confirm the experimental results, we performed two types of the cross validations designed for the time series data. We also support the validity of the model by analyzing the multi-step forecasting. We found that the prediction errors tend to be saturated although they increase as the prediction time step increases. The results of this study can be used to the energy management system in terms of the effective control of the cross usage of the electric and the gas energies.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.23-34
• /
• 2023

Nowadays, the Designated Driver Services employ dynamic pricing, which adapts in real-time based on nearby driver availability, service user volume, and current weather conditions during the user's request. The uncertain volatility is the main cause of price increases, leading to customer attrition and service refusal from driver. To make a good Designated Driver Services, development of a demand forecasting model is required. In this study, we propose developing a demand forecasting model using data from the Designated Driver Service by considering normal and peak periods, such as rush hour and rush day, as prior knowledge to enhance the model performance. We propose a new methodology called Time-Series with Conditional Probability(TSCP), which combines conditional probability and time-series models to enhance performance. Extensive experiments have been conducted with real Designated Driver Service data, and the result demonstrated that our method outperforms the existing time-series models such as SARIMA, Prophet. Therefore, our study can be considered for decision-making to facilitate proactive response in Designated Driver Services.

• Smart Structures and Systems
• /
• v.32 no.4
• /
• pp.267-279
• /
• 2023

Data modelling and interpretation for structural health monitoring (SHM) field data are critical for evaluating structural performance and quantifying the vulnerability of infrastructure systems. In order to improve the data modelling accuracy, and extend the application range from data regression analysis to out-of-sample forecasting analysis, an improved most likely heteroscedastic Gaussian process (iMLHGP) methodology is proposed in this study by the incorporation of the outof-sample forecasting algorithm. The proposed iMLHGP method overcomes this limitation of constant variance of Gaussian process (GP), and can be used for estimating non-stationary typhoon-induced response statistics with high volatility. The first attempt at performing data regression and forecasting analysis on structural responses using the proposed iMLHGP method has been presented by applying it to real-world filed SHM data from an instrumented cable-stay bridge during typhoon events. Uncertainty quantification and correlation analysis were also carried out to investigate the influence of typhoons on bridge strain data. Results show that the iMLHGP method has high accuracy in both regression and out-of-sample forecasting. The iMLHGP framework takes both data heteroscedasticity and accurate analytical processing of noise variance (replace with a point estimation on the most likely value) into account to avoid the intensive computational effort. According to uncertainty quantification and correlation analysis results, the uncertainties of strain measurements are affected by both traffic and wind speed. The overall change of bridge strain is affected by temperature, and the local fluctuation is greatly affected by wind speed in typhoon conditions.

• Asia-Pacific Journal of Business
• /
• v.13 no.3
• /
• pp.183-208
• /
• 2022

Purpose - The main purpose of this study is to widely investigate the impact of recent pandemic crises on the synchronization of the world capital markets through 25 stock indices from major developed countries. Design/methodology/approach - This study collects 25 stock indices from major developed countries and the time period is between January 5, 2001 and February 24, 2022. The data sets used in the study include finance.yahoo.com and Investing.com.. The Granger causality analysis, unit-root test, VAR analysis, and forecasting error variance decomposition were hired in order to analyze the data. Findings - First, there are significant inter-relations among 25 countries around recent major pandemic crises(such as SARS, A(H1N1), MERS, and COVID19), which is consistent result with previous literature. Second, COVID19 shows much stronger impact on the world-wide synchronization than other pandemics. Third, the return volatility of each stock market varies, unit root tests show that daily stock index data are unstable while daily stock index returns are stable, and VAR(Vector Auto Regression) analyses presents significant inter-relations among 25 capital markets. Fourth, from the impulse response function analyses, we find that each market affects the other markets for short term periods, about 2~4 days, and no long term effect was not found. Fifth, Granger causality tests show one-side or two-sides synchronization between capital markets and we estimate, through forecasting error variance decomposition method, that the explanatory portions of each capital market on other markets vary from 10 to 80%. Research implications or Originality - The above results all together show that pandemic crises have strong effects on the synchronization of world capital markets and imply that these synchronizations should be carefully considered both in the investment decisions by individual investors and in the financial and economic policies by governments.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.201-207
• /
• 2023

In this paper, we propose an optimal model for mid to long-term price prediction of agricultural products using LGBM, MLP, LSTM, and GRU to compare and analyze the three strategies of the Multi-Step Time Series. The proposed model is designed to find the optimal combination between the models by selecting methods from various angles. Prior agricultural product price prediction studies have mainly adopted traditional econometric models such as ARIMA and LSTM-type models. In contrast, agricultural product price prediction studies related to Multi-Step Time Series were minimal. In this study, the experiment was conducted by dividing it into two periods according to the degree of volatility of agricultural product prices. As a result of the mid-to-long-term price prediction of three strategies, namely direct, hybrid, and multiple outputs, the hybrid approach showed relatively superior performance. This study academically and practically contributes to mid-to-long term daily price prediction by proposing an effective alternative.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.125-130
• /
• 2020

At the end of 1997, the volatility of the exchange rate intensified as the nation's exchange rate system was converted into a free-floating exchange rate system. As a result, managing the exchange rate is becoming a very important task, and the need for forecasting the exchange rate is growing. The exchange rate prediction model using the existing exchange rate prediction method, statistical technique, cannot find a nonlinear pattern of the time series variable, and it is difficult to analyze the time series with the variability cluster phenomenon. And as the number of variables to be analyzed increases, the number of parameters to be estimated increases, and it is not easy to interpret the meaning of the estimated coefficients. Accordingly, the exchange rate prediction model using artificial neural network, rather than statistical technique, is presented. Using DNN, which is the basis of deep learning among artificial neural networks, and LSTM, a recurrent neural network model, the number of hidden layers, neurons, and activation function changes of each model found the optimal exchange rate prediction model. The study found that although there were model differences, LSTM models performed better than DNN models and performed best when the activation function was Tanh.

• The Korean Journal of Applied Statistics
• /
• v.27 no.3
• /
• pp.431-444
• /
• 2014

We introduce the empirical model decomposition (EMD) to decompose a time series into a set of components in the time-frequency domain. By using EMD, we also extract cycle and trend components from major Korean macroeconomic indices and forecast the indices with the components combined. In order to evaluate their efficiencies, we investigate volatility, autocorrelation, persistence, Granger causality, nonstationarity, and forecasting performance. They are then compared with those by Hodrick-Prescott filter which is the most commonly used method.

• Journal of Information Technology Services
• /
• v.22 no.4
• /
• pp.123-140
• /
• 2023

In recent times, the global economy has been subject to increasing volatility, which has made it considerably more difficult to accurately predict economic indicators compared to previous periods. In response to this challenge, the present study conducts an exploratory investigation that aims to predict the Business Survey Index (BSI) by leveraging data mining techniques on both structured and unstructured data sources. For the structured data, we have collected information regarding foreign, domestic, and industrial conditions, while the unstructured data consists of content extracted from newspaper articles. By employing an extensive set of 44 distinct data mining techniques, our research strives to enhance the BSI prediction accuracy and provide valuable insights. The results of our analysis demonstrate that the highest predictive power was attained when using data exclusively from the t-1 period. Interestingly, this suggests that previous timeframes play a vital role in forecasting the BSI effectively. The findings of this study hold significant implications for economic decision-makers, as they will not only facilitate better-informed decisions but also serve as a robust foundation for predicting a wide range of other economic indicators. By improving the prediction of crucial economic metrics, this study ultimately aims to contribute to the overall efficacy of economic policy-making and decision processes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.533-538
• /
• 2013

The damage caused by Recent frequently occurring locality torrential rains is increasing rapidly. In case of densely populated metropolitan area, casualties and property damage is a serious due to landslides and debris flows and floods. Therefore, the importance of predictions about the torrential is increasing. Precipitation characteristic of the bad weather in Korea is divided into typhoons and torrential rains. This seems to vary depending on the duration and area. Rainfall is difficult to predict because regional precipitation is large volatility and nonlinear. In this paper, Very short-term precipitation forecasting pattern model is implemented using KLAPS data used by Korea Meteorological Administration. we designed very short term precipitation forecasting pattern model using GA-based RBFNNs. the structural and parametric values such as the number of Inputs, polynomial type,number of fcm cluster, and fuzzification coefficient are optimized by GA optimization algorithm.

• Economic Analysis
• /
• v.25 no.1
• /
• pp.1-33
• /
• 2019

This paper examines the economic factors that are related to the dynamics of the variance risk premium, and specially, which economic factors are related to the forecasting power of the variance premium regarding future index returns. Eleven general economic variables, eight interest rate variables, and eleven sentiment-associated variables are used to figure out the relevant economic variables that affect the variance risk premium. According to our empirical results, the won-dollar exchange rates, foreign reserves, the historical/implied volatility, and interest rate variables all have significant coefficients. The highest adjusted R-squared is more than 65 percent, indicating their significant explanatory power of the variance risk premium. Next, to verify the economic variables associated with the predictability of the variance risk premium, we conduct forecasting regressions to predict future stock returns and volatilities for one to six months. Our empirical analysis shows that only the won-dollar exchange rate, among the many variables associated with the dynamics of the variance risk premium, has a significant forecasting ability regarding future index returns. These results are consistent with results found in previous studies, including Londono (2012) and Bollerslev et al. (2014), which show that the variance risk premium is related to global risk factors.