• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.393-405
• /
• 2023

Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

• The Journal of Economics, Marketing and Management
• /
• v.12 no.4
• /
• pp.27-36
• /
• 2024

Purpose: The paper analyzes for detecting unexpected shocks such as global financial crisis and COVID-19 pandemic, and contagion between countries by capturing in the mean-shift, variance-covariance-shift, and skewness-coskewness-shift parameters of interest rates. Research design, data and methodology: A flexible multivariate model of interest rates is provided by allowing for regime switching and a joint skewed normal distribution. The model is applying to the structural breaks of crisis and contagion between the US and the selected global bond markets during the global financial crisis and COVID-19 pandemic, respectively. Inspection of the moment statistics weakly suggests a flight to safety to the US during the global financial crisis and to Canada during the COVID-19 pandemic. Results: The results indicate that risk averse investors had a higher risk appetite for the US and Canada assets during the crisis regimes, compared to their counterparts. Conclusions: The results show that coskewness contagion dominates correlation contagion, and coskewness contagion is significant for the Korea and Japan-US pairs for the global financial crisis and the Euro-US pair for the COVID-19 pandemic. All channels of structural breaks of crisis and contagion are significant when considered jointly, reinforcing the need to consider contagion and structural breaks during crises in a multivariate setting.

• Journal of the Korean Mathematical Society
• /
• v.54 no.3
• /
• pp.987-997
• /
• 2017

A deterministic model for the spread of pine wilt disease with asymptomatic carrier trees in the host pine population is designed and rigorously analyzed. We have taken four different classes for the trees, namely susceptible, exposed, asymptomatic carrier and infected, and two different classes for the vector population, namely susceptible and infected. A complete global analysis of the model is given, which reveals that the global dynamics of the disease is completely determined by the associated basic reproduction number, denoted by $\mathcal{R}_0$. If $\mathcal{R}_0$ is less than one, the disease-free equilibrium is globally asymptotically stable, and in such a case, the endemic equilibrium does not exist. If $\mathcal{R}_0$ is greater than one, the disease persists and the unique endemic equilibrium is globally asymptotically stable.

• Journal of the Korean Mathematical Society
• /
• v.50 no.4
• /
• pp.695-713
• /
• 2013

We formulate and study a predator-prey model with non-monotonic functional response type and weak Allee effects on the prey, which extends the system studied by Ruan and Xiao in [Global analysis in a predator-prey system with nonmonotonic functional response, SIAM J. Appl. Math. 61 (2001), no. 4, 1445-1472] but containing an extra term describing weak Allee effects on the prey. We obtain the global dynamics of the model by combining the global qualitative and bifurcation analysis. Our bifurcation analysis of the model indicates that it exhibits numerous kinds of bifurcation phenomena, including the saddle-node bifurcation, the supercritical and the subcritical Hopf bifurcations, and the homoclinic bifurcation, as the values of parameters vary. In the generic case, the model has the bifurcation of cusp type of codimension 2 (i.e., Bogdanov-Takens bifurcation).

• International Commerce and Information Review
• /
• v.9 no.3
• /
• pp.161-180
• /
• 2007

The electronic bill of lading system replacing with traditional paper B/L has been evolved from SeaDocs and CMI to Bolero system. Therefore e-B/L is considered as an evolving concept rather than fixed one because it has been changed with development of information technology. Bolero system designed to replicate all functions of a paper B/L has some limitation to be utilized as an e-B/L in changing international business arena because it has a centralized model. Therefore it is considered to be important that the current e-B/L operating system needs to be diversified. This paper aims to provide three types of the operating model of global e-B/L to be applied with feasible solution coping with the current problems, which is expected to contribute to the utilization of electronic bill of lading.

• 한국태양에너지학회:학술대회논문집
• /
• 2009.11a
• /
• pp.110-114
• /
• 2009

The model to calculate the solar radiation at the surface was developed and the annual global solar radiation calculated by the model was compared with the KMA(Korea Meteorological Administration) surface measured data The difference between calculated and measured values was distinguished clearly because of the calibration problem of the pyranometer, but the global distribution of solar radiation calculated by the model was very similar to NREL(National Renewable Energy Laboratory) result of USA.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.127-138
• /
• 2003

Although the research on electronic commerce is plentiful, there is little empirical research related to Web-Based Shopping Systems (WBSS). This is especially so in global electronic commerce circumstances. WBSS are the fastest growing segment of digital economies and are perceived as driving forces of electronic commerce in terms of global markets and digital business. Using WBSS, organizations have a new chance of their business evolving successfully as global marketers. This paper develops a unified model to assess the diffusion of WBSS. Factors that impact WBSS diffusion are identified and analyzed as the basis for empirical testing. A set of propositions is developed that allows operationalization of the model. The ultimate goal is to provide the new research insights for the academic circles and the practical guidelines for organizations wishing to undertake WBSS.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.63-66
• /
• 2018

Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

• Advances in Energy Research
• /
• v.6 no.2
• /
• pp.131-143
• /
• 2019

Global Solar Radiation (GSR) is the key element for performance estimation of any Solar Power Plant (SPP). Its forecasting may help in estimation of power production from a SPP well in advance, and may also render help in optimal use of this power. Seasonal Auto-Regressive Moving Average (SARMA) and Artificial Neural Network (ANN) models are combined in order to develop a hybrid model (SARMA-ANN) conceiving the characteristics of both linear and non-linear prediction models. This developed model has been used for prediction of GSR at Gorakhpur, situated in the northern region of India. The proposed model is beneficial for the univariate forecasting. Along with this model, we have also used Auto-Regressive Moving Average (ARMA), SARMA, ANN based models for 1 - 6 day-ahead forecasting of GSR on hourly basis. It has been found that the proposed model presents least RMSE (Root Mean Square Error) and produces best forecasting results among all the models considered in the present study. As an application, the comparison between the forecasted one and the energy produced by the grid connected PV plant installed on the parking stands of the University shows the superiority of the proposed model.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.2
• /
• pp.113-119
• /
• 2023

Satellite navigation systems, with the exception of the GLObal NAvigation Satellite System (GLONASS), adopt ionosphere models and provide ionospheric coefficients to single-frequency users via navigation messages to correct ionospheric delay, the main source of positioning errors. A Global Navigation Satellite System (GNSS) mostly has its own ionospheric models: the Klobuchar model for Global Positioning System (GPS), the NeQuick-G model for Galileo, and the BeiDou Global Ionospheric delay correction Model (BDGIM) for BeiDou satellite navigation System (BDS)-3. On the other hand, a Regional Navigation Satellite System (RNSS) such as the Quasi-Zenith Satellite System (QZSS) and BDS-2 uses the Klobuchar Model rather than developing a new model. QZSS provides its own coefficients that are customized for its service area while BDS-2 slightly modifies the Klobuchar model to improve accuracy in the Asia-Pacific region. In addition, BDS broadcasts multiple ionospheric parameters depending on the satellites, unlike other systems. In this paper, we analyzed the different ionospheric models of GPS, QZSS, and BDS in Korea. The ionospheric models of QZSS and BDS-2, which are based in Asia, reduced error by at least 25.6% compared to GPS. However, QZSS was less accurate than GPS during geomagnetic storms or at low latitude. The accuracy of the models according to the BDS satellite orbit was also analyzed. The BDS-2 ionospheric model showed an error reduction of more than 5.9% when using GEO coefficients, while in BDS-3, the difference between satellites was within 0.01 m.