• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.11a
• /
• pp.417-426
• /
• 2000

This study suggests integrated neural network models for Interest rate forecasting using change-point detection, classifiers, and classification functions based on structural change. The proposed model is composed of three phases with tee-staged learning. The first phase is to detect successive and appropriate structural changes in interest rare dataset. The second phase is to forecast change-point group with classifiers (discriminant analysis, logistic regression, and backpropagation neural networks) and their. combined classification functions. The fecal phase is to forecast the interest rate with backpropagation neural networks. We propose some classification functions to overcome the problems of two-staged learning that cannot measure the performance of the first learning. Subsequently, we compare the structured models with a neural network model alone and, in addition, determine which of classifiers and classification functions can perform better. This article then examines the predictability of the proposed classification functions for interest rate forecasting using structural change.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.9 no.2
• /
• pp.121-137
• /
• 2013

Now days, firm's technology capability is recognized as important factor to forecast and to evaluate firm's business performance. There are many efforts to develop useful indicators by applying patent information that includes concrete description about technology. Many previous studies analyzed relationship between patent indicators and firm's performance. But they didn't consider time gap between a point of firm's invention activity and a point of firm's performance improvement. They didn't considered a character of industrial fields either. To overcome these limitations, we selected IT industry for target analysis industry. Time-series patent data and financial data from 41 American IT firms between 2000 and 2011 were used to analyze. In this study, We empirically analyzed subsequent effect of patent indicators on firm's business performance by using correlation analysis and regression analysis.

• Journal of the Korean earth science society
• /
• v.40 no.3
• /
• pp.259-271
• /
• 2019

A statistical downscaling method was adopted in order to establish the high-resolution wave prediction system in the East Sea coastal area. This system used forecast data from the Global Wave Watch (GWW) model, and the East Sea and Busan Coastal Wave Watch (CWW) model operated by the Korea Meteorological Administration (KMA). We used the CWW forecast data until three days and the GWW forecast data from three to seven days to implement the statistical downscaling method (inverse distance weight interpolation and conditional merge). The two-dimensional and station wave heights as well as sea surface wind speed from the high-resolution coastal prediction system were verified with statistical analysis, using an initial analysis field and oceanic observation with buoys carried out by the KMA and the Korea Hydrographic and Oceanographic Agency (KHOA). Similar to the predictive performance of the GWW and the CWW data, the system has a high predictive performance at the initial stages that decreased gradually with forecast time. As a result, during the entire prediction period, the correlation coefficient and root mean square error of the predicted wave heights improved from 0.46 and 0.34 m to 0.6 and 0.28 m before and after applying the statistical downscaling method.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.191-194
• /
• 2002

Lip-reading technology that is studied them is used to compensate speech recognition degradation in noise environment in bi-modal's form. The most important thing is that search for correct lips area in this lip-reading. But, it is hard to forecast stable performance in dynamic environment. Used RASTA filter that show good performance to remove noise in the speech to compensate. This filter shows that improve performance of using time domain of digital filter. To this experiment observes performance of speech recognition only using image information, service chooses possible 22 words and did recognition experiment in car. We used hidden Markov model by speech recognition algorithm to compare this words' recognition performance.

• Atmosphere
• /
• v.23 no.2
• /
• pp.171-186
• /
• 2013

Recently, the number of observations used in a data assimilation system is increasing due to the enormous amount of observations, including satellite data. However, it is not clear that all of these observations are always beneficial to the performance of the numerical weather prediction (NWP). Therefore, it is important to evaluate the effect of observations on these forecasts so that the observations can be used more usefully in NWP process. In this study, the adjoint-based Forecast Sensitivity to Observation (FSO) method with the KMA Unified Model (UM) is applied to two high-impact weather events which occurred in summer and winter in Korea in an effort to investigate the effects of observations on the forecasts of these events. The total dry energy norm is used as a response function to calculate the adjoint sensitivity. For the summer case, TEMP observations have the greatest total impact while BOGUS shows the greatest impact per observation for all of the 24-, 36-, and 48-hour forecasts. For the winter case, aircraft, ATOVS, and ESA have the greatest total impact for the 24-, 36-, and 48-hour forecasts respectively, while ESA has the greatest impact per observation. Most of the observation effects are horizontally located upwind or in the vicinity of the Korean peninsula. The fraction of beneficial observations is less than 50%, which is less than the results in previous studies. As an additional experiment, the total moist energy norm is used as a response function to measure the sensitivity of 24-hour forecast error to observations. The characteristics of the observation impact with the moist energy response function are generally similar to those with the dry energy response function. However, the ATOVS observations were found to be sensitive to the response function, showing a positive (a negative) effect on the forecast when using the dry (moist) norm for the summer case. For the winter case, the dry and moist energy norm experiments show very similar results because the adjoint of KMA UM does not calculate the specific humidity of ice properly such that the dry and moist energy norms are very similar except for the humidity in air that is very low in winter.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2B
• /
• pp.217-227
• /
• 2004

With a rapid growth in the Internet technology, the network traffic is increasing swiftly. As for the increase of traffic, it had a large influence on performance of a total network. Therefore, a traffic management became an important issue of network management. In this paper, we study a forecast plan of network traffic in order to analyze network traffic and to establish efficient correspondence. We use time series forecast models and determine fitness whether the model can forecast network traffic exactly. In order to predict a model, AR, MA, ARMA, and ARIMA must be applied. The suitable model can be found that can express the nature of traffic for the forecast among these models. We determines whether it is satisfied with stationary in the assumption step of the model. The stationary can get the results by using ACF(Auto Correlation Function) and PACF(Partial Auto Correlation Function). If the result of this function cannot satisfy then the forecast model is unsuitable. Therefore, we are going to get the correct model that is to satisfy stationary assumption. So, we proposes a way to classify in order to get time series materials to satisfy stationary. The correct prediction method is managed traffic of a network with a way to be better than now. It is possible to manage traffic dynamically if it can be used.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.137-143
• /
• 2018

Korea's air passenger traffic has been growing steadily. In this paper, we propose a forecasting model of air passenger demand to ascertain the growth trend of air passenger transportation performance in Korea. We conducted a simulation based on System Dynamics with the demand as a dependent variable, and international oil prices, GDP and exchange rates as exogenous variables. The accuracy of the model was verified using MAPE and $R^2$, and the proposed prediction model was verified as an accurate prediction model. As a result of the demand forecast, it is predicted that the air passenger demand in Korea will continue to grow, and the share of low cost carriers will increase sharply. The addition of the Korean transportation performance of foreign carriers in Korea and the transportation performance of Korean passengers due to the alliance of airlines will provide a more accurate forecast of passenger demand.

• Journal of the Korean Institute of Gas
• /
• v.20 no.3
• /
• pp.1-11
• /
• 2016

Production data from hydraulically fractured well in coalbed methane (CBM) reservoirs was analyzed using decl ine curve analysis (DCA), flow regime analysis, and flowing material balance to forecast the production performance and to determine estimated ultimate recovery (EUR) and timing for applying the DCA. To generate synthetic production data, reservoir models were built based on the CBM propertie of the Appalachian Basin, USA. Production data analysis shows that the transient flow (TF) occurs for 6~16 years and then the boundary dominated flow (BDF) was reached. In the TF period, it is impossible to forecast the production performance due to the significant errors between predicted data and synthetic data. The prediction can be conducted using the production data of more than a year after reached BDF with EUR error of approximately 5%.

• Journal of Korea Water Resources Association
• /
• v.33 no.3
• /
• pp.341-350
• /
• 2000

The objectives of this study are to develop a state-space form of stochastic dynamic storage function routing model and to test the model performance for real-time flow forecast. The selected study area is the main Han River starting from Paldang Dam site to Indogyo station and the 13 flood events occurred from 1987 to 1998 are selected for computing model parameters and testing the model performance. It was shown that the optimal model parameters are quite different depending on Hood events, but the values used on field work also give reasonable results in this study area. It is also obvious that the model performance from the stochastic-dynamic model developed in this study gives more accurate and reliable results than that from the existing deterministic model. Analysis for allowable forecast lead time leads that under the current time step the reasonable predicted downstream flows in 5 hours time advance are obtained from the stochastic dynamic model on relatively less lateral inflow event in the study area.