• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.146-146
• /
• 2022

A flash flood is one of the most hazardous natural events caused by heavy rainfall in a short period of time in mountainous areas with steep slopes. Early warning of flash flood is vital to minimize damage, but challenges remain in the enhancing accuracy and reliability of flash flood forecasts. The forecasters can easily determine whether flash flood is occurred using the flash flood guidance (FFG) comparing to rainfall volume of the same duration. In terms of this, the hydrological model that can consider the basin characteristics in real time can increase the accuracy of flash flood forecasting. Also, the predicted radar rainfall has a strength for short-lead time can be useful for flash flood forecasting. Therefore, using both hydrological models and radar rainfall forecasts can improve the accuracy of flash flood forecasts. In this study, FFG was applied to simulate some flash flood events in the Taehwa river basin by using of SURR model to consider soil moisture, and applied to the flash flood forecasting using predicted radar rainfall. The hydrometeorological data are gathered from 2011 to 2021. Furthermore, radar rainfall is forecasted up to 6-hours has been used to forecast flash flood during heavy rain in August 2021, Wulsan area. The accuracy of the predicted rainfall is evaluated and the correlation between observed and predicted rainfall is analyzed for quantitative evaluation. The results show that with a short lead time (1-3hr) the result of forecast flash flood events was very close to collected information, but with a larger lead time big difference was observed. The results obtained from this study are expected to use for set up the emergency planning to prevent the damage of flash flood.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.2793-2800
• /
• 2010

In this paper, we propose a quadratic (nonlinear) regression model that forecasts daily demands of electric power in summer. For cost-effective production (and/or procurement) of electric power, forecasting demands of electric power with accuracy is important, especially in summer when temperature is high. In the literature, temperature and daily demands of preceding days are typically employed to construct forecasting models. While, we consider another factor, day of the week, together with temperature and daily demands of preceding days. For validating the proposed model, we demonstrate the forecasting accuracy in terms of MAPE(Mean Absolute Percentage Error) and MPE(Maximum Percentage Error) using field data from KEPCO(Korea Electric Power Corporation) in comparison with two forecasting models in the literature. When compared with the two benchmarks, the proposed forecasting model performs far better providing MAPE and MPE not exceeding 3.08% and 8.99%, respectively, in summer from 2005 to 2009.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1327-1336
• /
• 2017

In this study, the problems in the short term stock market forecasting are analyzed and the feasibility of the ARIMA method and the backpropagation neural network is discussed. Neural network and genetic algorithm in short term stock forecasting is also examined. Since the backpropagation algorithm often falls into the local minima trap, we optimized the backpropagation neural network and established a genetic algorithm based on backpropagation neural network for forecasting model in order to achieve high forecasting accuracy. The experiments adopted the korea composite stock price index series to make prediction and provided corresponding error analysis. The results show that the genetic algorithm based on backpropagation neural network model proposed in this study has a significant improvement in stock price index series forecasting accuracy.

• Asian Journal of Innovation and Policy
• /
• v.3 no.2
• /
• pp.172-192
• /
• 2014

This study aims to analyze the valuation of technology firms in the stock market to answer how before-market entities should be valuated. This study analyzes 230 market reports of 2012 for technology firms in the KOSDAQ under several hypotheses. The results are as follows: 90% used the 3 multiples methods consisting of PER multiples with 80%, PBR multiples 8.7% and EBITDA multiples 1.7%. The average of PER multiples was 15 with the range of 6.9 to 83. That of PBR multiples is 2.27. Forecasting for cash flow is not applied over 4 years, but mainly 2-3 years. The accuracy of forecasting was 18.8%, 34.4% and 8% according to the different definitions. No differences were found in the accuracy of forecasting between valuation methods, between the industries having more intangible assets and the industries having less, and between startups and general companies and between ages and listed ages.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.318-327
• /
• 2000

Managerial intuition is a well-recognized cognitive ability but still poorly understood for the purpose of developing effective decision support systems. this research investigates whether the differences in accuracy of "time series forecasting" are related to the differences in one's cognitive style, using statistical test The hypotheses established in the research model did not have positive correlation The lack of correlation between "cognitive style and physiological measures" and accuracy in forecasting may be caused by uncontrolled external variable. Thus, further analyses on physiological characteristics and brainwaves are needed. The approaches such as neural network and data mining are proposed.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1300-1312
• /
• 2019

BSTRACT In this paper, PM10 forecast model using DNN(Deep Neural Network) is developed for Seoul region. The previous Julian forecast model has been developed using weather and air quality data of Seoul region only. This model gives excellent results for accuracy and false alarm rates, but poor result for POD(Probability of Detection). To solve this problem, an WA(Wide Area) forecasting model that uses Chinese data is developed. The data is highly correlated with the emergence of high concentrations of PM10 in Korea. As a result, the WA model shows better accuracy, and POD improving of 3%(D+0), 21%(D+1), and 36%(D+2) for each forecast period compared with the Julian model.

• Korean System Dynamics Review
• /
• v.9 no.1
• /
• pp.125-141
• /
• 2008

It is very difficult to predict future demand/supply, price for resources with acceptable accuracy using regression analysis. We try to use system dynamics to forecast the demand/supply and price for nickel. Nickel is very expensive mineral resource used for stainless production or other industrial production like battery, alloy making. Recent nickel price trend showed non-linear pattern and we anticipated the system dynamic method will catch this non-linear pattern better than the regression analysis. Our model has been calibrated for the past 6 year quarterly data (2002-2007) and tested for next 5 year quarterly data(2008-2012). The results were acceptable and showed higher accuracy than the results obtained from the regression analysis. And we ran the simulations for scenarios made by possible future changes in demand or supply related variables. This simulations implied some meaningful price change patterns.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.1812-1821
• /
• 2014

Wind has been a rapidly growing renewable power source for the last twenty years. Since wind behavior is chaotic in nature, its forecasting is not easy. At the same time, developing an accurate forecasting method is essential when wind farms are integrated into the power grid. In fact, wind speed forecasting tools can solve issues related to grid stability and reserve allocation. In this paper 30 hours ahead wind speed profile forecast is proposed using Adaptive Wavelet Neural Network (AWNN). The implemented AWNN uses a Mexican hat mother Wavelet, and Morlet Mother Wavelet for seven, eight and nine levels decompositions. For wind speed forecasting, the time series data on wind speed has been gathered from the National Renewable Energy Laboratory (NREL) website. In this work, hourly averaged 10-min wind speed data sets for the year 2004 in the Midwest ISO region (site number 7263) is taken for analysis. Data sets are normalized in the range of [-1, 1] to improve the training performance of forecasting models. Total 8760 samples were taken for this forecasting analysis. After the forecasting phase, statistical parameters are calculated to evaluate system accuracy, comparing different configurations.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1931-1936
• /
• 2007

Demand forecasting for railroad traffic is fairly important to establish future policy and plan. The future demand of railroad traffic can be predicted by analyzing the demand of air, marine and bus traffic which influence the demand of railroad traffic. In this study, forecasting the demand of railroad traffic is implemented through neural network using the demand of air, marine and bus traffic. Estimate accuracy of the demand of railroad traffic was shown about 84% through neural net model proposed.

• Journal of Communications and Networks
• /
• v.13 no.6
• /
• pp.621-624
• /
• 2011

With the rapid growth of internet traffic, accurate and reliable prediction of internet traffic has been a key issue in network management and planning. This paper proposes an autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) error model for forecasting internet traffic and evaluates its performance by comparing it with seasonal autoregressive integrated moving average (ARIMA) models in terms of root mean square error (RMSE) criterion. The results indicated that the seasonal AR-GARCH models outperformed the seasonal ARIMA models in terms of forecasting accuracy with respect to the RMSE criterion.