• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.1841-1851
• /
• 2018

For the safe and stable operation of the power system, accurate wind power prediction is of great significance. A wind power prediction method based on empirical mode decomposition and improved extreme learning machine is proposed in this paper. Firstly, wind power time series is decomposed into several components with different frequency by empirical mode decomposition, which can reduce the non-stationary of time series. The components after decomposing remove the long correlation and promote the different local characteristics of original wind power time series. Secondly, an improved extreme learning machine prediction model is introduced to overcome the sample data updating disadvantages of standard extreme learning machine. Different improved extreme learning machine prediction model of each component is established. Finally, the prediction value of each component is superimposed to obtain the final result. Compared with other prediction models, the simulation results demonstrate that the proposed prediction method has better prediction accuracy for wind power.

• Journal of Information Technology Applications and Management
• /
• v.20 no.2
• /
• pp.177-191
• /
• 2013

Social network has been expected to increase the value of social capital through online user interactions which remove geographical boundary. However, online users in social networks face challenges of assessing whether the anonymous user and his/her providing information are reliable or not because of limited experiences with a small number of users. Therefore. it is vital to provide a successful trust model which builds and maintains a web of trust. This study aims to propose a prediction method for the interpersonal trust which measures the level of trust about information provider in Facebook. To develop the prediction method. we first investigated behavioral research for trust in social science and extracted 5 antecedents of trust : lenience, ability, steadiness, intimacy, and similarity. Then we measured the antecedents from the history of interactive behavior and built prediction models using the two decision trees and a computational model. We also applied the proposed method to predict interpersonal trust between Facebook users and evaluated the prediction accuracy. The predicted trust metric has dynamic feature which can be adjusted over time according to the interaction between two users.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.64-72
• /
• 2016

In this paper, we utilize a Gaussian process to predict the power consumption in the air-conditioning system. As the power consumption in the air-conditioning system takes a form of a time-series and the prediction of the power consumption becomes very important from the perspective of the efficient energy management, it is worth to investigate the time-series model for the prediction of the power consumption. To this end, we apply the Gaussian process to predict the power consumption, in which the Gaussian process provides a prior probability to every possible function and higher probabilities are given to functions that are more likely consistent with the empirical data. We also discuss how to estimate the hyper-parameters, which are parameters in the covariance function of the Gaussian process model. We estimated the hyper-parameters with two different methods (marginal likelihood and leave-one-out cross validation) and obtained a model that pertinently describes the data and the results are more or less independent of the estimation method of hyper-parameters. We validated the prediction results by the error analysis of the mean relative error and the mean absolute error. The mean relative error analysis showed that about 3.4% of the predicted value came from the error, and the mean absolute error analysis confirmed that the error in within the standard deviation of the predicted value. We also adopt the non-parametric Wilcoxon's sign-rank test to assess the fitness of the proposed model and found that the null hypothesis of uniformity was accepted under the significance level of 5%. These results can be applied to a more elaborate control of the power consumption in the air-conditioning system.

• Journal of the Korean Society for Railway
• /
• v.20 no.4
• /
• pp.474-481
• /
• 2017

When designing photovoltaic power plants in Korea, the prediction of photovoltaic power generation at the design phase is carried out using PVSyst, PVWatts (Overseas power generation prediction software), and overseas weather data even if the test site is a domestic site. In this paper, for a comparative study to predict power generation using weather information, domestic photovoltaic power plants in two regions were selected as target sites. PVsyst, which is a commercial power generation forecasting program, was used to compare the accuracy between the predicted value of power generation (obtained using overseas weather information (Meteonorm 7.1, NASA-SSE)) and the predicted value of power generation obtained by the Korea Meteorological Administration (KMA). In addition, we have studied ways to improve the prediction of power generation through comparative analysis of meteorological data. Finally, we proposed a revised solar power generation prediction model that considers climatic factors by considering the actual generation amount.

• Publications of The Korean Astronomical Society
• /
• v.14 no.2
• /
• pp.91-102
• /
• 1999

We have made intensive calculations on the maximum relative sunspot number and the date of solar maximum of 23rd solar cycle, by using the statistical and precursor methods to predict solar activity cycle. According to our results of solar data processing by statistical method, solar maximum comes at between February and July of 2000 year and at that time, the smoothed sunspot number will reach to $114.3\~122.8$. while precursor method gives rather dispersed value of $118\~17$ maximum sunspot number. It is found that prediction by statistical method using smoothed relative sunspot number is more accurate than by any method to use any data of 10.7cm radio fluxes and geomagnetic aa, Ap indexes, from the full analysis of solar cycle pattern of these data. In fact, current ascending pattern of 23rd solar cycle supports positively our predicted values. Predicted results by precursor method for $Ap_{avg},\;aa_{31-36}$ indexes show similar values to those by statistical method. Therefore, these indexes can be used as new precursors for the prediction of 23rd or next solar cycle.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.51-58
• /
• 2022

Various studies have been conducted from the past to the present because stock price forecasts provide stability in the national economy and huge profits to investors. Recently, there have been many studies that suggest stock price prediction models using various input data such as macroeconomic indicators and emotional analysis. However, since each study was conducted individually, it is difficult to objectively compare each method, and studies on their impact on stock price prediction are still insufficient. In this paper, the effect of input data currently mainly used on the stock price is evaluated through the predicted value of the deep learning model and the error rate of the actual stock price. In addition, unlike most papers in emotional analysis, emotional analysis using the news body was conducted, and a method of supplementing the results of each emotional analysis is proposed through three emotional analysis models. Through experiments predicting Microsoft's revised closing price, the results of emotional analysis were found to be the most important factor in stock price prediction. Especially, when all of input data is used, error rate of ensembled sentiment analysis model is reduced by 58% compared to the baseline.

• Journal of Korea Multimedia Society
• /
• v.25 no.1
• /
• pp.82-91
• /
• 2022

In this paper, time series prediction method of photovoltaic power is introduced using seasonal autoregressive integrated moving average (SARIMA). In order to obtain the best fitting model by a time series method in the absence of an environmental sensor, this research was used data below 50% of cloud cover. Three samples were extracted by time intervals from the raw data. After that, the best fitting models were derived from mean absolute percentage error (MAPE) with the minimum akaike information criterion (AIC) or beysian information criterion (BIC). They are SARIMA (1,0,0)(0,2,2)14, SARIMA (1,0,0)(0,2,2)28, SARIMA (2,0,3)(1,2,2)55. Generally parameter of model derived from BIC was lower than AIC. SARIMA (2,0,3)(1,2,2)55, unlike other models, was drawn by AIC. And the performance of models obtained by SARIMA was compared. MAPE value was affected by the seasonal period of the sample. It is estimated that long seasonal period samples include atmosphere irregularity. Consequently using 1 hour or 30 minutes interval sample is able to be helpful for prediction accuracy improvement.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2001.07a
• /
• pp.319-322
• /
• 2001

The proposed system was composed of pre-processor which was executing binary/high-pass filtering and post-processor which ranged from statistic data to prediction. In post-processor work, step one was filter process of image, step two was image recognition, and step three was destruction degree/time prediction. After these processing, we could predict image of the last destruction timestamp. This research was produced variation value according to growth of tree pattern. This result showed improved correction, when this research was applied image Processing. Pre-processing step of original image had good result binary work after high pass- filter execution. In the case of using partial discharge of the image, our research could predict the last destruction timestamp. By means of experimental data, this Prediction system was acquired ${\pm}$3.2% error range.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.93-101
• /
• 2015

In modern society, various crimes is occurred. It is necessary to predict the criminal in order to prevent crimes, various studies on the prediction of crime is in progress. Crime-related data, is announced to the statistical processing of once a year from the Public Prosecutor's Office. However, relative to the current point in time, data that has been statistical processing is a data of about two years ago. It does not fit to the data of the crime currently being generated. In This paper, crime prediction data was apply with Naver trend data. By using the Web traffic Naver trend, it is possible to obtain the data of interest level for crime currently being generated. It was constructed a modeling that can predict the crime by using traffic data of the Naver web search. There have been applied to Markov chains prediction theory. Among various crimes, murder, arson, rape, predictive modeling was applied to target. And the result of predictive modeling value was analyzed. As a result, it got the same results within 20%, based on the value of crime that actually occurred. In the future, it plan to advance research for the predictive modeling of crime that takes into the characteristics of the season.

• Journal of Advanced Navigation Technology
• /
• v.19 no.3
• /
• pp.199-206
• /
• 2015

For real-time precise positioning, IGS provides ephemeris predictions (IGS ultra-rapid, IGU) and real-time ephemeris estimates (real-time service, RTS). Due to the RTS data latency, which ranges from 5 s to 30 s, a short-term prediction process is necessary before applying the RTS corrections. In this paper, the real-time performance of the RTS correction and IGU prediction are compared. The RTS correction availability for the GPS satellites observed in Korea is computed as 99.3%. The RTS correction is applied to broadcast ephemeris to verify the accuracy of the RTS correction. The 3D orbit RMS error of the RTS correction is 0.043 m. Prediction of the RTS correction is modeled as a polynomial, and then the predicted value is compared with the IGU prediction value. The RTS orbit prediction accuracy is nearly equivalent to the IGU prediction, but RTS clock prediction performance is 0.13 m better than the IGU prediction.