• 대한전기학회논문지
• /
• 제45권4호
• /
• pp.602-611
• /
• 1996

In this paper, radial basis function networks with two hidden layers, which employ the K-means clustering method and the hierarchical training, are proposed for improving the short-term predictability of chaotic time series. Furthermore the recursive training method of radial basis function network using the recursive modified Gram-Schmidt algorithm is proposed for the purpose. In addition, the radial basis function networks trained by the proposed training methods are compared with the X.D. He A Lapedes's model and the radial basis function network by nonrecursive training method. Through this comparison, an improved radial basis function network for predicting chaotic time series is presented. (author). 17 refs., 8 figs., 3 tabs.

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.694-706
• /
• 2019

In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.523-527
• /
• 2004

This paper presents a new design methods of the short-term load forecasting system (STLFS) using the data mining. The proposed predictor takes form of the convex combination of the linear time series predictors for each inputs. The problem of estimating the consequent parameters is formulated by the convex optimization problem, which is to minimize the norm distance between the real load and the output of the linear time series estimator, The problem of estimating the premise parameters is to find the parameter value minimizing the error between the real load and the overall output. Finally, to show the feasibility of the proposed method, this paper provides the short-term load forecasting example.

• Journal of Electrical Engineering and Technology
• /
• 제7권6호
• /
• pp.807-813
• /
• 2012

In this paper, we introduce data mining techniques for short-term load forecasting (STLF). First, we use the K-mean algorithm to classify historical load data by season into four patterns. Second, we use the k-NN algorithm to divide the classified data into four patterns for Mondays, other weekdays, Saturdays, and Sundays. The classified data are used to develop a time series forecasting model. We then forecast the hourly load on weekdays and weekends, excluding special holidays. The historical load data are used as inputs for load forecasting. We compare our results with the KEPCO hourly record for 2008 and conclude that our approach is effective.

• 아태비즈니스연구
• /
• 제14권4호
• /
• pp.343-356
• /
• 2023

Purpose - This study attempted to predict short-term transportation demand using trains and getting off at Gangchon Station. Through this, we present numerical data necessary for future tourist inflow policies in the Gangchon area of Chuncheon and present related implications. Design/methodology/approach - This study collected and analyzed transportation demand data from Gangchon Station using the Gyeongchun Line and ITX-Cheongchun Train from January 2014 to August 2023. Winters exponential smoothing model and ARIMA model were used to reflect the trend and seasonality of the raw data. Findings - First, transportation demand using trains to get off at Gangchon Station in Chuncheon City is expected to show a continuous increase from 2020 until the forecast period is 2024. Second, the number of passengers getting off at Gangchon Station was found to be highest in May and October. Research implications or Originality - As transportation networks are improving nationwide and people's leisure culture is changing, the number of tourists visiting the Gangchon area in Chuncheon City is continuously decreasing. Therefore, in this study, a time series model was used to predict short-term transportation demand alighting at Gangchon Station. In order to calculate more accurate forecasts, we compared models to find an appropriate model and presented forecasts.

• 한국공간구조학회논문집
• /
• 제14권3호
• /
• pp.93-100
• /
• 2014

Ethylene Tetrafluoroethylene (ETFE) has been widely used in long-span buildings because of its light weight and high transparency. This paper studies the short and long term creep behaviour of ETFE foil. A series of short-term creep and recovery tests were performed, in which the residual strain was observed. A long-term creep test of the ETFE foil was also performed over 110 days. A viscoelastic-plastic model was then established to describe the short-term creep and recovery behaviour. The model contains a traditional multi-Kelvin part and an added steady-flow component to represent the viscoelastic and viscoplastic behaviour, respectively. The model successfully fit the data for three stresses and six temperatures. Additionally, time-temperature equivalency was adopted to predict the long-term creep behaviour of ETFE foil. Horizontal shifting factors were determined from the process of shifting creep-curves at six temperatures. The long-term creep behaviours at three temperatures were predicted. Finally, the long-term creep test showed that the short-term creep test at identical temperatures insufficiently predicted additional creep behaviour, and the long-term test verified the horizontal shifting factors derived from the time-temperature equivalency.

• 조명전기설비학회논문지
• /
• 제29권7호
• /
• pp.54-61
• /
• 2015

This paper presents short-term wind farm power forecasting method using multivariate analysis and time series. Based on factor analysis, the proposed method makes new independent variables which newly composed by raw independent variables such as wind speed, ramp rate, wind power. Newly created variables are used in the time series model for forecasting wind farm power. To demonstrate the improved accuracy, the proposed method is compared with persistence model commonly used as reference in wind power forecasting using data from Jeju Island. The results of case studies are presented to show the effectiveness of the proposed forecasting method.

• 대한전기학회논문지:전력기술부문A
• /
• 제52권8호
• /
• pp.450-456
• /
• 2003

This paper proposes a multiple time-series model with dummy variables for one-hour ahead load forecasting. We used 11 dummy variables that were classified by day characteristics such as day of the week, holiday, and special holiday. Also, model specification and selection of input variables including dummy variables were made by test statistics such as AIC(Akaike Information Criterion) and t-test statistics of each coefficient. OLS (Ordinary Least Squares) method was used for estimation and forecasting. We found out that model specifications for each hour are not identical usually at 30％ of optimal significance level, and dummy variables reduce the forecasting error if they are classified properly. The proposed model has much more accurate estimates in forecasting with less MAPE (Mean Absolute Percentage Error).

• 대한전기학회논문지
• /
• 제32권6호
• /
• pp.191-198
• /
• 1983

This paper describes the aplication of different model which can be used for short-term load prediction. The model is based on Bohlin's approach to first develop a load profile model representing the nominal load component and the Box-Jenkins approach is used to predict residuals. An on-line algorithm using Kalman Filter and Time Series is implemented for and hour-ahead prediction. In the Kalman Filter system equation and measurement equation were fixed and parameters of Time Series were varied week after week. A set of data for Korea Electric Power Corporation from April to June 1981 was used for the evaluation of the model. As the result of this simulation 1.2% rms error was acquired.

• 한국인터넷방송통신학회논문지
• /
• 제13권1호
• /
• pp.101-107
• /
• 2013

현실세계에서는 광범위한 업무영역에서 대용량의 시계열자료들이 실시간으로 발생되고 있다. 하지만 동적인 특징으로 표현되는 시계열자료들의 이해와 설명을 위한 최적의 모형을 결정하는 일은 쉽지가 않다. 이러한 시계열자료들의 특징을 잘 설명할 수 있는 모형을 추정하기 위하여 본 연구에서는 시계열데이터의 모형추정에 적합한 은닉마아코프모델을 통해 시계열자료의 장, 단기 예측모형을 추정하였고 이를 통해 미래의 운동패턴예측을 확인하였다. 실제 주식시장의 여러 자료들을 통해 최적의 모형추정을 위한 정보기준과 가장 효율적인 자료길이를 통해 모형의 상태수를 정확하게 추정하는지를 확인하였다. 실험결과 유효한 상태의 수 추정과 단기의 예측이 장기예측보다 유사운동패턴 예측률이 더욱 유사함을 확인하였다.