• Journal of Korea Water Resources Association
• /
• v.46 no.7
• /
• pp.755-765
• /
• 2013

This study developed a real-time dam's hydrologic variables prediction model (DHVPM) and evaluated its performance for simulating historical dam inflow and outflow in the Chungju dam basin. The DHVPM consists of the Sejong University River Forecast (SURF) model for hydrologic modeling and an autoreservoir operation method (Auto ROM) for dam operation. SURF model is continuous rainfall-runoff model with data assimilation using an ensemble Kalman filter technique. The four extreme events including the maximum inflow of each year for 2006~2009 were selected to examine the performance of DHVPM. The statistical criteria, the relative error in peak flow, root mean square error, and model efficiency, demonstrated that DHVPM with data assimilation can simulate more close to observed inflow than those with no data assimilation at both 1-hour lead time, except the relative error in peak flow in 2007. Especially, DHVPM with data assimilation until 10-hour lead time reduced the biases of inflow forecast attributed to observed precipitation error. In conclusion, DHVPM with data assimilation can be useful to improve the accuracy of inflow forecast in the basin where real-time observed inflow are available.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.4
• /
• pp.395-403
• /
• 2005

It is very important to forecast water supply for reasonal operation and management of water utilities. In this paper, water supply forecasting models using artificial intelligence are developed. Artificial intelligence models shows better results by using Temperature(t), water supply discharge (t-1) and water supply discharge (t-2), which are expressed by neural network(LMNNWS; Levenberg-Marquardt Neural Network for Water Supply, MDNNWS; MoDular Neural Network for Water Supply) and neuro fuzzy(ANASWS; Adaptive Neuro-Fuzzy Inference Systems for Water Supply). ANFISWS model which is applied for water supply forecasting shows stable application to the variable water supply data. As results, MDNNWS model shows the highest overall accuracy among proposed water supply forecasting models and the lowest estimation error with the order of ANFISWS, LMNNWS model.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.2
• /
• pp.241-248
• /
• 2005

Conventional estimating methods forecast the future that it usually using the past statistical numerical value. In order to forecast the farming price, it must need many effort and accuracy knowledge. Therefore, to solve the these problems, this paper to improve forecasting farming price using fuzzy rules and neural network as a preprocessing. Also, we developed an intelligent farming expert system for real time forecasting as a postprocessing about unexpectable conditions. Computer simulation results proved reducing pricing error which proposed farming price expecting system better than conventional demand forecasting system does not using fuzzy rules.

• Health Policy and Management
• /
• v.13 no.3
• /
• pp.91-103
• /
• 2003

The purpose of this study was to provide basic reference data for stabilization scheme of health expenditure through forecasting of health expenditure. The authors analyzed the health expenditure from 1985 to 2000 that had been calculated by Korean institute for health and social affair using transfer function model as ARIMA model with input series. They used GDP as the input series for more precise forecasting. The model of error term was identified ARIMA(2,2,0) and Portmanteau statics of residuals was not significant. Forecasting health expenditure as percent of GDP at 2010 was 6.8%, under assumption of 5% GDP increase rate. Moreover that was 7.4%, under assumption of 3% GDP increase rate and that was 6.4%, under assumption of 7% GDP increase rate.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.295-297
• /
• 2000

In case of power demand forecasting the most important problem is to deal with the load of special-days, Accordingly, this paper presents a method that forecasting special-days load with regression models and neural networks. Special-days load in summer season was forecasted by the multiple regression models using weekday change ratio Neural networks models uses pattern conversion ratio, and orthogonal polynomial models was directly forecasted using past special-days load data. forecasting result obtains % forecast error of about $1{\sim}2[%]$. Therefore, it is possible to forecast long and short special-days load.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2003.10a
• /
• pp.535-538
• /
• 2003

A Grey model was developed to forecast short-term runoff from the Naju watershed in Korea. In calibration, the root mean square error(RMSE) of the simulated runoff of six hours ahead using Grey model ranged from 6.3 to $290.52m^3/s,\;R^2$ ranged from 0.91 to 0.99, compared to the observed data. In verification, the RMSE ranged from 75.7 to $218.9m^3/s,\;R^2$ ranged from 0.87 to 0.96, compared to the observed data. The results in this study demonstrate that the proposed model can reasonably forecast runoff one to six hours ahead.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.86-94
• /
• 2018

This study focuses on presenting the IT program module provided by real - time forecasting and database of the voluntary disclosure quality measure in order to solve the problem of capital cost due to information asymmetry of external investors and corporate executives. This study suggests a model of the algorithm that the quality of real - time voluntary disclosure can be provided to all investors immediately by IT program in order to deliver the meaningful value in the domestic capital market. This is a method of generating and analyzing real-time or non-real-time prediction models by transferring the predicted estimates delivered to the Big Data Log Analysis System through the statistical DB to the statistical forecasting engine.

• Journal of Energy Engineering
• /
• v.6 no.1
• /
• pp.68-76
• /
• 1997

This paper presents a new neural network training algorithm which reduces the required training time considerably and overcomes many of the shortcomings presented by the conventional back-propagation algorithm. The algorithm uses a modified form of the back-propagation algorithm to minimize the mean squared error between the desired and actual outputs with respect to the inputs to the nonlinearities. Artificial Neural Network (ANN) model using the new algorithm is applied to forecast the short-term electric load. Inputs to the ANN are past loads and the output of the ANN is the hourly load forecast for a given day.

• Culinary science and hospitality research
• /
• v.5 no.1
• /
• pp.89-101
• /
• 1999

This study attempts to identify the most accurate quantitative forecasting technique for measuring the future level of demand for food ＆ beverage in super deluxe hotel in Seoul, which will subsequently lead to determining the optimal level of purchasing food ＆ beverage. This study, in detail, examines the food purchasing system of H hotel, reviews three rigorous univariate time series models and identify the most accurate forecasting technique. The monthly data ranging from January 1990 to December 1997 (96 observations) were used for the empirical analysis and the 1998 data were left for the comparison with the ex post forecast results. In order to measure the accuracy, MAPE, MAD and RMSE were used as criteria. In this study, Box-Jenkins model was turned out to be the most accurate technique for forecasting hotel food ＆ beverage demand among selected models generating 3.8％ forecast error in average.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.1144-1148
• /
• 1997

In this paper, a method for the daily maximum load forecasting which uses a chaotic time series in power system and artificial neural network. We find the characteristics of chaos in power load curve and then determine a optimal embedding dimension and delay time. For the load forecast of one day ahead daily maximum power, we use the time series load data obtained in previous year. By using of embedding dimension and delay time, we construct a strange attractor in pseudo phase plane and the artificial neural network model trained with the attractor mentioned above. The one day ahead forecast errors are about 1.4% for absolute percentage average error.